Token | Pride |
Token ID | 21735 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Blessing | +0.378 |
WN | +0.364 |
Gutenberg | +0.356 |
advertisement | +0.355 |
Vaugh | +0.344 |
Neg logit contributions | |
erent | -0.427 |
escal | -0.400 |
apo | -0.385 |
iste | -0.383 |
bang | -0.382 |
Token | he |
Token ID | 339 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
erent | +0.282 |
escal | +0.263 |
apo | +0.252 |
iste | +0.251 |
bang | +0.250 |
Neg logit contributions | |
Blessing | -0.302 |
WN | -0.293 |
Gutenberg | -0.287 |
advertisement | -0.287 |
Vaugh | -0.279 |
Token | sought |
Token ID | 7194 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
Blessing | +0.038 |
WN | +0.038 |
advertisement | +0.037 |
Gutenberg | +0.037 |
Vaugh | +0.035 |
Neg logit contributions | |
erent | -0.037 |
escal | -0.035 |
apo | -0.033 |
iste | -0.033 |
bang | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Blessing | +0.138 |
WN | +0.134 |
advertisement | +0.131 |
Gutenberg | +0.131 |
Vaugh | +0.128 |
Neg logit contributions | |
erent | -0.135 |
escal | -0.126 |
apo | -0.121 |
iste | -0.121 |
bang | -0.120 |
Token | st |
Token ID | 336 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
erent | +0.115 |
escal | +0.107 |
apo | +0.103 |
iste | +0.103 |
bang | +0.102 |
Neg logit contributions | |
Blessing | -0.120 |
WN | -0.116 |
advertisement | -0.114 |
Gutenberg | -0.113 |
Vaugh | -0.110 |
Token | oke |
Token ID | 2088 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
Blessing | +0.229 |
WN | +0.222 |
advertisement | +0.217 |
Gutenberg | +0.216 |
Vaugh | +0.210 |
Neg logit contributions | |
erent | -0.252 |
escal | -0.237 |
apo | -0.228 |
iste | -0.228 |
bang | -0.227 |
Token | through |
Token ID | 832 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
Blessing | +2.284 |
WN | +2.234 |
advertisement | +2.203 |
Gutenberg | +2.199 |
Vaugh | +2.107 |
Neg logit contributions | |
erent | -1.679 |
escal | -1.520 |
apo | -1.458 |
bang | -1.455 |
iste | -1.443 |
Token | Pad |
Token ID | 15744 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Blessing | +0.156 |
WN | +0.151 |
Gutenberg | +0.149 |
advertisement | +0.149 |
Vaugh | +0.145 |
Neg logit contributions | |
erent | -0.126 |
escal | -0.116 |
apo | -0.112 |
iste | -0.112 |
bang | -0.110 |
Token | m |
Token ID | 76 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
erent | +0.428 |
escal | +0.397 |
apo | +0.381 |
iste | +0.381 |
bang | +0.379 |
Neg logit contributions | |
Blessing | -0.484 |
WN | -0.471 |
advertisement | -0.461 |
Gutenberg | -0.460 |
Vaugh | -0.448 |
Token | av |
Token ID | 615 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Blessing | +0.183 |
WN | +0.176 |
Gutenberg | +0.173 |
advertisement | +0.173 |
Vaugh | +0.167 |
Neg logit contributions | |
erent | -0.195 |
escal | -0.181 |
iste | -0.175 |
bang | -0.175 |
apo | -0.173 |
Token | ati |
Token ID | 7246 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Blessing | +0.653 |
WN | +0.640 |
advertisement | +0.632 |
Gutenberg | +0.629 |
Vaugh | +0.617 |
Neg logit contributions | |
erent | -0.178 |
escal | -0.147 |
apo | -0.133 |
iste | -0.131 |
bang | -0.128 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Blessing | +0.243 |
WN | +0.238 |
advertisement | +0.231 |
Gutenberg | +0.231 |
Vaugh | +0.224 |
Neg logit contributions | |
erent | -0.247 |
escal | -0.230 |
apo | -0.222 |
iste | -0.220 |
bang | -0.219 |
Token | | |
Token ID | 930 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Blessing | +0.051 |
WN | +0.050 |
Gutenberg | +0.049 |
advertisement | +0.049 |
Vaugh | +0.047 |
Neg logit contributions | |
erent | -0.045 |
escal | -0.042 |
apo | -0.040 |
iste | -0.040 |
bang | -0.040 |
Token | Streaming |
Token ID | 43124 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Blessing | +0.393 |
WN | +0.380 |
Gutenberg | +0.373 |
advertisement | +0.372 |
Vaugh | +0.361 |
Neg logit contributions | |
erent | -0.381 |
escal | -0.357 |
apo | -0.344 |
iste | -0.341 |
bang | -0.340 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
erent | +0.077 |
escal | +0.072 |
apo | +0.069 |
bang | +0.068 |
iste | +0.068 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.078 |
advertisement | -0.077 |
Gutenberg | -0.077 |
Vaugh | -0.074 |
Token | Es |
Token ID | 8678 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
erent | +0.284 |
escal | +0.265 |
apo | +0.256 |
iste | +0.255 |
bang | +0.253 |
Neg logit contributions | |
Blessing | -0.294 |
WN | -0.286 |
advertisement | -0.280 |
Gutenberg | -0.277 |
Vaugh | -0.270 |
Token | port |
Token ID | 634 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
Blessing | +0.324 |
WN | +0.316 |
advertisement | +0.303 |
Gutenberg | +0.302 |
Vaugh | +0.290 |
Neg logit contributions | |
erent | -0.382 |
escal | -0.358 |
iste | -0.346 |
apo | -0.343 |
bang | -0.342 |
Token | Under |
Token ID | 4698 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Blessing | +1.800 |
WN | +1.730 |
advertisement | +1.710 |
Gutenberg | +1.676 |
Vaugh | +1.612 |
Neg logit contributions | |
erent | -1.851 |
escal | -1.767 |
apo | -1.698 |
iste | -1.666 |
bang | -1.648 |
Token | the |
Token ID | 262 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
erent | +0.063 |
escal | +0.059 |
apo | +0.057 |
iste | +0.057 |
bang | +0.057 |
Neg logit contributions | |
Blessing | -0.057 |
WN | -0.055 |
advertisement | -0.054 |
Gutenberg | -0.054 |
Vaugh | -0.051 |
Token | Sun |
Token ID | 3825 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
erent | +0.103 |
escal | +0.096 |
apo | +0.093 |
iste | +0.093 |
bang | +0.092 |
Neg logit contributions | |
Blessing | -0.099 |
WN | -0.097 |
advertisement | -0.094 |
Gutenberg | -0.094 |
Vaugh | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Blessing | +0.736 |
WN | +0.717 |
advertisement | +0.704 |
Gutenberg | +0.701 |
Vaugh | +0.680 |
Neg logit contributions | |
erent | -0.605 |
escal | -0.561 |
apo | -0.539 |
iste | -0.531 |
bang | -0.530 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Blessing | +0.064 |
WN | +0.063 |
advertisement | +0.062 |
Gutenberg | +0.060 |
Majesty | +0.057 |
Neg logit contributions | |
erent | -0.068 |
escal | -0.063 |
apo | -0.061 |
iste | -0.060 |
bang | -0.060 |
Token | ? |
Token ID | 30 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Blessing | +0.178 |
WN | +0.174 |
advertisement | +0.170 |
Gutenberg | +0.169 |
Vaugh | +0.164 |
Neg logit contributions | |
erent | -0.181 |
escal | -0.170 |
apo | -0.164 |
iste | -0.163 |
bang | -0.162 |
Token | If |
Token ID | 1002 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
erent | +0.077 |
escal | +0.073 |
apo | +0.070 |
iste | +0.070 |
bang | +0.070 |
Neg logit contributions | |
Blessing | -0.059 |
WN | -0.057 |
advertisement | -0.056 |
Gutenberg | -0.056 |
Vaugh | -0.054 |
Token | Hong |
Token ID | 9764 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Blessing | +0.113 |
WN | +0.110 |
advertisement | +0.108 |
Gutenberg | +0.108 |
Vaugh | +0.105 |
Neg logit contributions | |
erent | -0.102 |
escal | -0.095 |
iste | -0.092 |
apo | -0.091 |
bang | -0.090 |
Token | Kong |
Token ID | 9071 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
erent | +0.410 |
escal | +0.384 |
iste | +0.371 |
apo | +0.371 |
bang | +0.365 |
Neg logit contributions | |
Blessing | -0.362 |
WN | -0.354 |
advertisement | -0.345 |
Gutenberg | -0.343 |
Vaugh | -0.327 |
Token | ev |
Token ID | 819 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
erent | +0.857 |
escal | +0.799 |
apo | +0.768 |
iste | +0.767 |
bang | +0.763 |
Neg logit contributions | |
Blessing | -0.897 |
WN | -0.873 |
advertisement | -0.855 |
Gutenberg | -0.853 |
Vaugh | -0.830 |
Token | okes |
Token ID | 3369 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Blessing | +0.109 |
WN | +0.107 |
advertisement | +0.105 |
Gutenberg | +0.104 |
Vaugh | +0.101 |
Neg logit contributions | |
erent | -0.086 |
escal | -0.079 |
iste | -0.076 |
bang | -0.076 |
apo | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Blessing | +1.815 |
WN | +1.754 |
Gutenberg | +1.733 |
advertisement | +1.721 |
Vaugh | +1.646 |
Neg logit contributions | |
erent | -1.690 |
escal | -1.575 |
apo | -1.535 |
iste | -1.525 |
bang | -1.486 |
Token | miracle |
Token ID | 20820 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
erent | +0.121 |
escal | +0.112 |
apo | +0.109 |
iste | +0.107 |
bang | +0.106 |
Neg logit contributions | |
Blessing | -0.162 |
WN | -0.157 |
Gutenberg | -0.155 |
advertisement | -0.154 |
Vaugh | -0.149 |
Token | in |
Token ID | 287 |
Feature activation | -5.85e-03 |
Pos logit contributions | |
erent | +0.169 |
escal | +0.157 |
apo | +0.151 |
iste | +0.150 |
bang | +0.148 |
Neg logit contributions | |
Blessing | -0.196 |
WN | -0.191 |
advertisement | -0.187 |
Gutenberg | -0.187 |
Vaugh | -0.181 |
Token | D |
Token ID | 360 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
erent | +0.014 |
escal | +0.013 |
iste | +0.012 |
apo | +0.012 |
bang | +0.012 |
Neg logit contributions | |
Blessing | -0.014 |
WN | -0.014 |
Gutenberg | -0.014 |
advertisement | -0.014 |
Vaugh | -0.013 |
Token | oha |
Token ID | 28083 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
erent | +0.112 |
escal | +0.104 |
apo | +0.099 |
iste | +0.099 |
bang | +0.098 |
Neg logit contributions | |
Blessing | -0.152 |
WN | -0.150 |
advertisement | -0.145 |
Gutenberg | -0.145 |
Vaugh | -0.141 |
Token | : |
Token ID | 25 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
Blessing | +0.988 |
WN | +0.987 |
Gutenberg | +0.960 |
advertisement | +0.953 |
Vaugh | +0.926 |
Neg logit contributions | |
erent | -0.844 |
escal | -0.786 |
apo | -0.761 |
iste | -0.759 |
bang | -0.748 |
Token |
|
Token ID | 198 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
Blessing | +0.199 |
WN | +0.193 |
advertisement | +0.189 |
Gutenberg | +0.189 |
Vaugh | +0.183 |
Neg logit contributions | |
erent | -0.195 |
escal | -0.182 |
apo | -0.175 |
iste | -0.175 |
bang | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Blessing | +0.012 |
WN | +0.012 |
advertisement | +0.011 |
Gutenberg | +0.011 |
Majesty | +0.010 |
Neg logit contributions | |
erent | -0.012 |
escal | -0.012 |
apo | -0.011 |
iste | -0.011 |
bang | -0.011 |
Token | 13 |
Token ID | 1485 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
erent | +0.028 |
escal | +0.026 |
apo | +0.025 |
iste | +0.025 |
bang | +0.025 |
Neg logit contributions | |
Blessing | -0.027 |
WN | -0.026 |
advertisement | -0.026 |
Gutenberg | -0.025 |
Vaugh | -0.024 |
Token | PH |
Token ID | 9370 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Blessing | +0.376 |
WN | +0.369 |
advertisement | +0.358 |
Gutenberg | +0.357 |
Vaugh | +0.348 |
Neg logit contributions | |
erent | -0.359 |
escal | -0.335 |
apo | -0.321 |
iste | -0.321 |
bang | -0.319 |
Token | OTOS |
Token ID | 33291 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
erent | +0.432 |
escal | +0.407 |
apo | +0.395 |
bang | +0.393 |
iste | +0.393 |
Neg logit contributions | |
Blessing | -0.324 |
WN | -0.317 |
advertisement | -0.307 |
Gutenberg | -0.305 |
Vaugh | -0.297 |
Token | Donald |
Token ID | 3759 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Blessing | +1.686 |
WN | +1.648 |
Gutenberg | +1.621 |
advertisement | +1.596 |
Vaugh | +1.527 |
Neg logit contributions | |
erent | -1.820 |
escal | -1.708 |
apo | -1.652 |
bang | -1.647 |
iste | -1.614 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Blessing | +0.908 |
WN | +0.892 |
Gutenberg | +0.878 |
advertisement | +0.861 |
Majesty | +0.833 |
Neg logit contributions | |
erent | -0.633 |
escal | -0.596 |
bang | -0.552 |
apo | -0.552 |
iste | -0.551 |
Token | 's |
Token ID | 338 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Blessing | +0.571 |
WN | +0.552 |
Gutenberg | +0.547 |
advertisement | +0.543 |
Vaugh | +0.527 |
Neg logit contributions | |
erent | -0.465 |
escal | -0.433 |
apo | -0.420 |
iste | -0.414 |
bang | -0.413 |
Token | potential |
Token ID | 2785 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Blessing | +0.106 |
WN | +0.104 |
Gutenberg | +0.102 |
advertisement | +0.101 |
Vaugh | +0.100 |
Neg logit contributions | |
erent | -0.068 |
escal | -0.062 |
apo | -0.060 |
iste | -0.059 |
bang | -0.059 |
Token | running |
Token ID | 2491 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Blessing | +0.710 |
WN | +0.691 |
Gutenberg | +0.677 |
advertisement | +0.669 |
Vaugh | +0.649 |
Neg logit contributions | |
erent | -0.995 |
escal | -0.948 |
apo | -0.919 |
iste | -0.907 |
bang | -0.903 |
Token | reasons |
Token ID | 3840 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Blessing | +0.081 |
WN | +0.078 |
advertisement | +0.077 |
Gutenberg | +0.076 |
Vaugh | +0.074 |
Neg logit contributions | |
erent | -0.075 |
escal | -0.070 |
apo | -0.068 |
iste | -0.067 |
bang | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
Blessing | +0.322 |
WN | +0.313 |
advertisement | +0.309 |
Gutenberg | +0.307 |
Vaugh | +0.297 |
Neg logit contributions | |
erent | -0.269 |
escal | -0.249 |
apo | -0.240 |
iste | -0.239 |
bang | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
Blessing | +0.012 |
WN | +0.011 |
advertisement | +0.011 |
Gutenberg | +0.011 |
Vaugh | +0.011 |
Neg logit contributions | |
erent | -0.012 |
escal | -0.011 |
apo | -0.011 |
iste | -0.011 |
bang | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
erent | +0.010 |
escal | +0.009 |
apo | +0.009 |
iste | +0.009 |
bang | +0.009 |
Neg logit contributions | |
Blessing | -0.010 |
WN | -0.009 |
advertisement | -0.009 |
Gutenberg | -0.009 |
Majesty | -0.008 |
Token | Inter |
Token ID | 9492 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
erent | +0.015 |
escal | +0.014 |
iste | +0.014 |
apo | +0.014 |
bang | +0.014 |
Neg logit contributions | |
Blessing | -0.014 |
WN | -0.014 |
advertisement | -0.013 |
Gutenberg | -0.013 |
Vaugh | -0.013 |
Token | ior |
Token ID | 1504 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
erent | +0.089 |
escal | +0.082 |
apo | +0.079 |
iste | +0.078 |
bang | +0.078 |
Neg logit contributions | |
Blessing | -0.110 |
WN | -0.107 |
advertisement | -0.105 |
Gutenberg | -0.105 |
Vaugh | -0.102 |
Token | Minister |
Token ID | 4139 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Blessing | +1.767 |
WN | +1.690 |
advertisement | +1.649 |
Gutenberg | +1.646 |
Vaugh | +1.589 |
Neg logit contributions | |
erent | -1.745 |
escal | -1.613 |
apo | -1.559 |
iste | -1.540 |
bang | -1.539 |
Token | Oliver |
Token ID | 15416 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Blessing | +0.156 |
WN | +0.150 |
Gutenberg | +0.147 |
advertisement | +0.146 |
Vaugh | +0.142 |
Neg logit contributions | |
erent | -0.180 |
escal | -0.169 |
apo | -0.163 |
iste | -0.162 |
bang | -0.162 |
Token | Sp |
Token ID | 1338 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
Blessing | +0.101 |
WN | +0.098 |
advertisement | +0.096 |
Gutenberg | +0.096 |
Vaugh | +0.093 |
Neg logit contributions | |
erent | -0.111 |
escal | -0.103 |
apo | -0.100 |
iste | -0.100 |
bang | -0.099 |
Token | as |
Token ID | 292 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Blessing | +0.220 |
WN | +0.215 |
advertisement | +0.211 |
Gutenberg | +0.211 |
Vaugh | +0.203 |
Neg logit contributions | |
erent | -0.185 |
escal | -0.173 |
apo | -0.166 |
iste | -0.165 |
bang | -0.165 |
Token | ov |
Token ID | 709 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
Blessing | +0.261 |
WN | +0.254 |
Gutenberg | +0.248 |
advertisement | +0.248 |
Vaugh | +0.240 |
Neg logit contributions | |
erent | -0.245 |
escal | -0.228 |
apo | -0.218 |
iste | -0.218 |
bang | -0.217 |
Token | Black |
Token ID | 2619 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Blessing | +0.117 |
WN | +0.113 |
Gutenberg | +0.111 |
advertisement | +0.110 |
Vaugh | +0.107 |
Neg logit contributions | |
erent | -0.135 |
escal | -0.127 |
apo | -0.122 |
iste | -0.122 |
bang | -0.122 |
Token | Baron |
Token ID | 21770 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Blessing | +0.704 |
WN | +0.668 |
Gutenberg | +0.662 |
advertisement | +0.649 |
Vaugh | +0.632 |
Neg logit contributions | |
erent | -0.832 |
escal | -0.783 |
apo | -0.752 |
iste | -0.748 |
bang | -0.748 |
Token | in |
Token ID | 287 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Blessing | +0.824 |
WN | +0.800 |
Gutenberg | +0.787 |
advertisement | +0.783 |
Vaugh | +0.763 |
Neg logit contributions | |
erent | -0.602 |
escal | -0.554 |
bang | -0.524 |
apo | -0.523 |
iste | -0.521 |
Token | an |
Token ID | 281 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Blessing | +0.033 |
WN | +0.032 |
Gutenberg | +0.031 |
advertisement | +0.031 |
Vaugh | +0.030 |
Neg logit contributions | |
erent | -0.026 |
escal | -0.024 |
apo | -0.023 |
iste | -0.023 |
bang | -0.023 |
Token | Ace |
Token ID | 17102 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Blessing | +0.259 |
WN | +0.253 |
Gutenberg | +0.249 |
advertisement | +0.248 |
Vaugh | +0.240 |
Neg logit contributions | |
erent | -0.199 |
escal | -0.180 |
iste | -0.173 |
apo | -0.172 |
bang | -0.170 |
Token | Combat |
Token ID | 14487 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Blessing | +0.404 |
WN | +0.390 |
advertisement | +0.376 |
Gutenberg | +0.372 |
Vaugh | +0.362 |
Neg logit contributions | |
erent | -0.562 |
escal | -0.527 |
iste | -0.512 |
apo | -0.511 |
bang | -0.505 |
Token | - |
Token ID | 12 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
Blessing | +1.807 |
WN | +1.760 |
advertisement | +1.752 |
Gutenberg | +1.713 |
Vaugh | +1.634 |
Neg logit contributions | |
erent | -1.593 |
escal | -1.450 |
apo | -1.418 |
bang | -1.396 |
iste | -1.389 |
Token | esque |
Token ID | 28939 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Blessing | +0.291 |
WN | +0.287 |
advertisement | +0.284 |
Gutenberg | +0.280 |
Vaugh | +0.274 |
Neg logit contributions | |
erent | -0.126 |
escal | -0.109 |
apo | -0.104 |
iste | -0.104 |
bang | -0.102 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Blessing | +0.380 |
WN | +0.369 |
advertisement | +0.364 |
Gutenberg | +0.362 |
Vaugh | +0.351 |
Neg logit contributions | |
erent | -0.323 |
escal | -0.294 |
apo | -0.287 |
bang | -0.283 |
iste | -0.281 |
Token | fight |
Token ID | 15481 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
erent | +0.296 |
escal | +0.267 |
iste | +0.254 |
apo | +0.254 |
bang | +0.249 |
Neg logit contributions | |
Blessing | -0.521 |
WN | -0.512 |
advertisement | -0.501 |
Gutenberg | -0.497 |
Vaugh | -0.488 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Blessing | +0.988 |
WN | +0.968 |
advertisement | +0.959 |
Gutenberg | +0.938 |
Vaugh | +0.909 |
Neg logit contributions | |
erent | -0.686 |
escal | -0.619 |
apo | -0.595 |
iste | -0.588 |
bang | -0.585 |
Token | Times |
Token ID | 3782 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Blessing | +0.081 |
WN | +0.079 |
advertisement | +0.077 |
Gutenberg | +0.077 |
Vaugh | +0.075 |
Neg logit contributions | |
erent | -0.083 |
escal | -0.078 |
iste | -0.075 |
apo | -0.075 |
bang | -0.074 |
Token | of |
Token ID | 286 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
Blessing | +0.450 |
WN | +0.435 |
Gutenberg | +0.423 |
advertisement | +0.422 |
Vaugh | +0.408 |
Neg logit contributions | |
erent | -0.511 |
escal | -0.479 |
iste | -0.459 |
apo | -0.458 |
bang | -0.453 |
Token | Israel |
Token ID | 2692 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
Blessing | +0.179 |
WN | +0.175 |
Gutenberg | +0.172 |
advertisement | +0.171 |
Vaugh | +0.168 |
Neg logit contributions | |
erent | -0.083 |
escal | -0.074 |
apo | -0.070 |
iste | -0.070 |
bang | -0.069 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
Blessing | +0.007 |
WN | +0.007 |
advertisement | +0.007 |
Gutenberg | +0.007 |
Vaugh | +0.007 |
Neg logit contributions | |
erent | -0.006 |
escal | -0.005 |
apo | -0.005 |
iste | -0.005 |
bang | -0.005 |
Token | St |
Token ID | 1273 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
Blessing | +0.013 |
WN | +0.013 |
advertisement | +0.013 |
Gutenberg | +0.013 |
Vaugh | +0.012 |
Neg logit contributions | |
erent | -0.014 |
escal | -0.013 |
iste | -0.012 |
apo | -0.012 |
bang | -0.012 |
Token | ress |
Token ID | 601 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Blessing | +0.205 |
WN | +0.199 |
advertisement | +0.195 |
Gutenberg | +0.195 |
Vaugh | +0.190 |
Neg logit contributions | |
erent | -0.179 |
escal | -0.166 |
iste | -0.159 |
apo | -0.159 |
bang | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
Blessing | +1.684 |
WN | +1.635 |
Gutenberg | +1.598 |
advertisement | +1.593 |
Vaugh | +1.541 |
Neg logit contributions | |
erent | -1.681 |
escal | -1.561 |
iste | -1.514 |
apo | -1.513 |
bang | -1.494 |
Token | We |
Token ID | 775 |
Feature activation | -5.99e-04 |
Pos logit contributions | |
Blessing | +0.158 |
WN | +0.152 |
advertisement | +0.149 |
Gutenberg | +0.148 |
Vaugh | +0.143 |
Neg logit contributions | |
erent | -0.202 |
escal | -0.190 |
apo | -0.184 |
iste | -0.183 |
bang | -0.182 |
Token | all |
Token ID | 477 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
erent | +0.001 |
escal | +0.001 |
apo | +0.001 |
iste | +0.001 |
bang | +0.001 |
Neg logit contributions | |
Blessing | -0.002 |
WN | -0.001 |
advertisement | -0.001 |
Gutenberg | -0.001 |
Vaugh | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Blessing | +0.063 |
WN | +0.061 |
advertisement | +0.060 |
Gutenberg | +0.059 |
Vaugh | +0.057 |
Neg logit contributions | |
erent | -0.077 |
escal | -0.072 |
apo | -0.070 |
iste | -0.070 |
bang | -0.069 |
Token | it |
Token ID | 340 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Blessing | +0.302 |
WN | +0.292 |
advertisement | +0.288 |
Gutenberg | +0.286 |
Vaugh | +0.277 |
Neg logit contributions | |
erent | -0.292 |
escal | -0.272 |
apo | -0.263 |
bang | -0.259 |
iste | -0.259 |
Token | optional |
Token ID | 11902 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Blessing | +0.152 |
WN | +0.147 |
Gutenberg | +0.145 |
advertisement | +0.145 |
Vaugh | +0.141 |
Neg logit contributions | |
erent | -0.129 |
escal | -0.119 |
apo | -0.115 |
bang | -0.115 |
iste | -0.114 |
Token | side |
Token ID | 1735 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Blessing | +0.674 |
WN | +0.653 |
advertisement | +0.641 |
Gutenberg | +0.640 |
Vaugh | +0.620 |
Neg logit contributions | |
erent | -0.599 |
escal | -0.553 |
apo | -0.535 |
bang | -0.533 |
iste | -0.529 |
Token | quest |
Token ID | 1235 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
Blessing | +0.465 |
WN | +0.450 |
advertisement | +0.445 |
Gutenberg | +0.443 |
Vaugh | +0.431 |
Neg logit contributions | |
erent | -0.384 |
escal | -0.356 |
apo | -0.342 |
iste | -0.341 |
bang | -0.338 |
Token | content |
Token ID | 2695 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
Blessing | +0.009 |
WN | +0.008 |
advertisement | +0.008 |
Gutenberg | +0.008 |
Vaugh | +0.008 |
Neg logit contributions | |
erent | -0.007 |
escal | -0.006 |
apo | -0.006 |
iste | -0.006 |
bang | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
erent | +0.050 |
escal | +0.046 |
apo | +0.044 |
iste | +0.044 |
bang | +0.044 |
Neg logit contributions | |
Blessing | -0.068 |
WN | -0.066 |
Gutenberg | -0.065 |
advertisement | -0.065 |
Vaugh | -0.063 |
Token | combat |
Token ID | 5249 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
Blessing | +0.257 |
WN | +0.249 |
Gutenberg | +0.244 |
advertisement | +0.243 |
Vaugh | +0.236 |
Neg logit contributions | |
erent | -0.235 |
escal | -0.219 |
apo | -0.211 |
iste | -0.210 |
bang | -0.210 |
Token | does |
Token ID | 857 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Blessing | +1.588 |
WN | +1.524 |
advertisement | +1.500 |
Gutenberg | +1.487 |
Vaugh | +1.426 |
Neg logit contributions | |
erent | -1.646 |
escal | -1.522 |
apo | -1.490 |
bang | -1.470 |
iste | -1.448 |
Token | go |
Token ID | 467 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
Blessing | +0.050 |
WN | +0.048 |
advertisement | +0.047 |
Gutenberg | +0.047 |
Vaugh | +0.045 |
Neg logit contributions | |
erent | -0.045 |
escal | -0.041 |
apo | -0.040 |
iste | -0.040 |
bang | -0.040 |
Token | from |
Token ID | 422 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Blessing | +0.182 |
WN | +0.177 |
Gutenberg | +0.171 |
advertisement | +0.171 |
Vaugh | +0.167 |
Neg logit contributions | |
erent | -0.152 |
escal | -0.142 |
apo | -0.137 |
iste | -0.136 |
bang | -0.132 |
Token | too |
Token ID | 1165 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
Blessing | +0.349 |
WN | +0.338 |
advertisement | +0.334 |
Gutenberg | +0.333 |
Vaugh | +0.323 |
Neg logit contributions | |
erent | -0.263 |
escal | -0.240 |
apo | -0.232 |
iste | -0.231 |
bang | -0.227 |
Token | easy |
Token ID | 2562 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Blessing | +0.051 |
WN | +0.050 |
advertisement | +0.049 |
Gutenberg | +0.049 |
Vaugh | +0.048 |
Neg logit contributions | |
erent | -0.034 |
escal | -0.031 |
iste | -0.029 |
apo | -0.029 |
bang | -0.029 |
Token | local |
Token ID | 1957 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Blessing | +0.105 |
WN | +0.101 |
Gutenberg | +0.099 |
advertisement | +0.099 |
Vaugh | +0.097 |
Neg logit contributions | |
erent | -0.094 |
escal | -0.087 |
apo | -0.085 |
iste | -0.084 |
bang | -0.083 |
Token | councils |
Token ID | 27174 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Blessing | +0.404 |
WN | +0.389 |
Gutenberg | +0.382 |
advertisement | +0.379 |
Vaugh | +0.371 |
Neg logit contributions | |
erent | -0.358 |
escal | -0.332 |
apo | -0.320 |
iste | -0.318 |
bang | -0.318 |
Token | have |
Token ID | 423 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
erent | +0.298 |
escal | +0.277 |
apo | +0.269 |
iste | +0.267 |
bang | +0.265 |
Neg logit contributions | |
Blessing | -0.324 |
WN | -0.314 |
advertisement | -0.308 |
Gutenberg | -0.306 |
Vaugh | -0.297 |
Token | adequate |
Token ID | 12872 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
Blessing | +0.125 |
WN | +0.121 |
Gutenberg | +0.118 |
advertisement | +0.118 |
Vaugh | +0.115 |
Neg logit contributions | |
erent | -0.114 |
escal | -0.106 |
apo | -0.102 |
iste | -0.101 |
bang | -0.101 |
Token | sewer |
Token ID | 34327 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
erent | +0.216 |
escal | +0.200 |
apo | +0.192 |
iste | +0.191 |
bang | +0.191 |
Neg logit contributions | |
Blessing | -0.248 |
WN | -0.240 |
Gutenberg | -0.235 |
advertisement | -0.234 |
Vaugh | -0.228 |
Token | age |
Token ID | 496 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Blessing | +0.709 |
WN | +0.690 |
Gutenberg | +0.676 |
advertisement | +0.676 |
Vaugh | +0.657 |
Neg logit contributions | |
erent | -0.621 |
escal | -0.572 |
iste | -0.549 |
apo | -0.548 |
bang | -0.546 |
Token | out |
Token ID | 503 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
Blessing | +1.775 |
WN | +1.724 |
advertisement | +1.684 |
Gutenberg | +1.681 |
Vaugh | +1.647 |
Neg logit contributions | |
erent | -1.457 |
escal | -1.323 |
apo | -1.278 |
iste | -1.270 |
bang | -1.259 |
Token | fall |
Token ID | 7207 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
erent | +0.076 |
escal | +0.071 |
apo | +0.068 |
iste | +0.068 |
bang | +0.067 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.079 |
advertisement | -0.077 |
Gutenberg | -0.077 |
Vaugh | -0.075 |
Token | management |
Token ID | 4542 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
Blessing | +1.291 |
WN | +1.261 |
advertisement | +1.236 |
Gutenberg | +1.228 |
Vaugh | +1.194 |
Neg logit contributions | |
erent | -1.115 |
escal | -1.029 |
iste | -0.989 |
apo | -0.988 |
bang | -0.980 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Blessing | +0.008 |
WN | +0.008 |
advertisement | +0.008 |
Gutenberg | +0.008 |
Vaugh | +0.007 |
Neg logit contributions | |
erent | -0.006 |
escal | -0.006 |
apo | -0.006 |
iste | -0.006 |
bang | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
erent | +0.024 |
escal | +0.022 |
iste | +0.022 |
apo | +0.022 |
bang | +0.021 |
Neg logit contributions | |
Blessing | -0.026 |
WN | -0.025 |
advertisement | -0.024 |
Gutenberg | -0.024 |
Vaugh | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
erent | +0.362 |
escal | +0.334 |
apo | +0.318 |
iste | +0.316 |
bang | +0.315 |
Neg logit contributions | |
Blessing | -0.490 |
WN | -0.478 |
Gutenberg | -0.469 |
advertisement | -0.469 |
Vaugh | -0.456 |
Token | � |
Token ID | 447 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
erent | +0.202 |
escal | +0.190 |
apo | +0.184 |
iste | +0.184 |
bang | +0.183 |
Neg logit contributions | |
Blessing | -0.150 |
WN | -0.145 |
advertisement | -0.141 |
Gutenberg | -0.140 |
Vaugh | -0.136 |
Token | � |
Token ID | 251 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Blessing | +0.030 |
WN | +0.028 |
advertisement | +0.027 |
Gutenberg | +0.027 |
Vaugh | +0.026 |
Neg logit contributions | |
erent | -0.068 |
escal | -0.065 |
iste | -0.064 |
apo | -0.063 |
bang | -0.063 |
Token | Then |
Token ID | 3244 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
erent | +0.085 |
escal | +0.080 |
apo | +0.077 |
iste | +0.077 |
bang | +0.076 |
Neg logit contributions | |
Blessing | -0.073 |
WN | -0.071 |
advertisement | -0.069 |
Gutenberg | -0.069 |
Vaugh | -0.067 |
Token | Black |
Token ID | 2619 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Blessing | +0.144 |
WN | +0.139 |
Gutenberg | +0.139 |
advertisement | +0.137 |
Vaugh | +0.134 |
Neg logit contributions | |
erent | -0.105 |
escal | -0.096 |
apo | -0.092 |
iste | -0.092 |
bang | -0.090 |
Token | Sabbath |
Token ID | 38402 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
Blessing | +0.567 |
WN | +0.547 |
Gutenberg | +0.536 |
advertisement | +0.530 |
Vaugh | +0.516 |
Neg logit contributions | |
erent | -0.623 |
escal | -0.583 |
apo | -0.562 |
iste | -0.558 |
bang | -0.556 |
Token | � |
Token ID | 447 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
Blessing | +1.667 |
WN | +1.622 |
advertisement | +1.603 |
Gutenberg | +1.599 |
Vaugh | +1.536 |
Neg logit contributions | |
erent | -1.501 |
escal | -1.394 |
apo | -1.340 |
iste | -1.322 |
bang | -1.302 |
Token | � |
Token ID | 247 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
Blessing | +0.144 |
WN | +0.138 |
advertisement | +0.135 |
Gutenberg | +0.133 |
Vaugh | +0.127 |
Neg logit contributions | |
erent | -0.254 |
escal | -0.240 |
iste | -0.234 |
apo | -0.234 |
bang | -0.231 |
Token | s |
Token ID | 82 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
Blessing | +0.015 |
WN | +0.015 |
advertisement | +0.014 |
Gutenberg | +0.014 |
Vaugh | +0.014 |
Neg logit contributions | |
erent | -0.018 |
escal | -0.017 |
apo | -0.016 |
iste | -0.016 |
bang | -0.016 |
Token | Born |
Token ID | 18889 |
Feature activation | +4.01e-04 |
Pos logit contributions | |
Blessing | +0.016 |
WN | +0.015 |
advertisement | +0.015 |
Gutenberg | +0.015 |
Vaugh | +0.015 |
Neg logit contributions | |
erent | -0.016 |
escal | -0.015 |
apo | -0.014 |
iste | -0.014 |
bang | -0.014 |
Token | Again |
Token ID | 6521 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Blessing | +0.001 |
WN | +0.001 |
advertisement | +0.001 |
Gutenberg | +0.001 |
Vaugh | +0.001 |
Neg logit contributions | |
erent | -0.001 |
escal | -0.001 |
apo | -0.001 |
iste | -0.001 |
bang | -0.001 |
Token | modern |
Token ID | 3660 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Blessing | +0.182 |
WN | +0.177 |
advertisement | +0.174 |
Gutenberg | +0.173 |
Vaugh | +0.166 |
Neg logit contributions | |
erent | -0.173 |
escal | -0.160 |
apo | -0.156 |
iste | -0.155 |
bang | -0.155 |
Token | ize |
Token ID | 1096 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
erent | +0.110 |
escal | +0.103 |
apo | +0.099 |
iste | +0.099 |
bang | +0.099 |
Neg logit contributions | |
Blessing | -0.097 |
WN | -0.094 |
advertisement | -0.092 |
Gutenberg | -0.092 |
Vaugh | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Blessing | +0.089 |
WN | +0.087 |
advertisement | +0.086 |
Gutenberg | +0.086 |
Vaugh | +0.082 |
Neg logit contributions | |
erent | -0.083 |
escal | -0.078 |
iste | -0.075 |
bang | -0.075 |
apo | -0.075 |
Token | complex |
Token ID | 3716 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
Blessing | +0.039 |
WN | +0.038 |
advertisement | +0.037 |
Gutenberg | +0.037 |
Vaugh | +0.036 |
Neg logit contributions | |
erent | -0.031 |
escal | -0.029 |
bang | -0.028 |
apo | -0.028 |
iste | -0.028 |
Token | electric |
Token ID | 5186 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Blessing | +0.157 |
WN | +0.153 |
Gutenberg | +0.152 |
advertisement | +0.152 |
Vaugh | +0.146 |
Neg logit contributions | |
erent | -0.119 |
escal | -0.111 |
apo | -0.105 |
iste | -0.105 |
bang | -0.104 |
Token | grid |
Token ID | 10706 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
Blessing | +0.336 |
WN | +0.330 |
advertisement | +0.326 |
Gutenberg | +0.325 |
Vaugh | +0.317 |
Neg logit contributions | |
erent | -0.196 |
escal | -0.178 |
apo | -0.171 |
iste | -0.170 |
bang | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
Blessing | +1.723 |
advertisement | +1.689 |
WN | +1.681 |
Gutenberg | +1.656 |
Vaugh | +1.571 |
Neg logit contributions | |
erent | -1.422 |
escal | -1.293 |
iste | -1.257 |
apo | -1.241 |
bang | -1.221 |
Token | But |
Token ID | 887 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Blessing | +0.126 |
WN | +0.121 |
Gutenberg | +0.118 |
advertisement | +0.118 |
Vaugh | +0.113 |
Neg logit contributions | |
erent | -0.173 |
escal | -0.163 |
apo | -0.158 |
iste | -0.158 |
bang | -0.158 |
Token | poor |
Token ID | 3595 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Blessing | +0.143 |
WN | +0.139 |
Gutenberg | +0.138 |
advertisement | +0.136 |
Vaugh | +0.131 |
Neg logit contributions | |
erent | -0.132 |
escal | -0.124 |
iste | -0.119 |
bang | -0.118 |
apo | -0.118 |
Token | choices |
Token ID | 7747 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Blessing | +0.403 |
WN | +0.394 |
advertisement | +0.388 |
Gutenberg | +0.387 |
Vaugh | +0.373 |
Neg logit contributions | |
erent | -0.352 |
escal | -0.329 |
iste | -0.315 |
apo | -0.314 |
bang | -0.313 |
Token | now |
Token ID | 783 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Blessing | +0.321 |
WN | +0.312 |
advertisement | +0.307 |
Gutenberg | +0.305 |
Vaugh | +0.296 |
Neg logit contributions | |
erent | -0.280 |
escal | -0.257 |
apo | -0.249 |
bang | -0.247 |
iste | -0.247 |
Token | you |
Token ID | 345 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
erent | +0.072 |
escal | +0.067 |
apo | +0.064 |
iste | +0.064 |
bang | +0.063 |
Neg logit contributions | |
Blessing | -0.098 |
WN | -0.096 |
advertisement | -0.094 |
Gutenberg | -0.094 |
Vaugh | -0.092 |
Token | cannot |
Token ID | 2314 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
erent | +0.187 |
escal | +0.174 |
apo | +0.168 |
iste | +0.168 |
bang | +0.167 |
Neg logit contributions | |
Blessing | -0.191 |
WN | -0.186 |
advertisement | -0.182 |
Gutenberg | -0.181 |
Vaugh | -0.176 |
Token | Normal |
Token ID | 14435 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
erent | +0.231 |
escal | +0.216 |
apo | +0.208 |
iste | +0.207 |
bang | +0.206 |
Neg logit contributions | |
Blessing | -0.225 |
WN | -0.219 |
advertisement | -0.214 |
Gutenberg | -0.213 |
Vaugh | -0.207 |
Token | or |
Token ID | 393 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Blessing | +0.283 |
WN | +0.269 |
Gutenberg | +0.258 |
advertisement | +0.258 |
Vaugh | +0.245 |
Neg logit contributions | |
erent | -0.670 |
escal | -0.639 |
apo | -0.623 |
iste | -0.621 |
bang | -0.620 |
Token | Special |
Token ID | 6093 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Blessing | +0.032 |
WN | +0.031 |
advertisement | +0.030 |
Gutenberg | +0.030 |
Vaugh | +0.029 |
Neg logit contributions | |
erent | -0.040 |
escal | -0.038 |
apo | -0.036 |
iste | -0.036 |
bang | -0.036 |
Token | Summon |
Token ID | 19515 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Blessing | +0.218 |
WN | +0.207 |
advertisement | +0.199 |
Gutenberg | +0.199 |
Vaugh | +0.189 |
Neg logit contributions | |
erent | -0.526 |
escal | -0.501 |
apo | -0.488 |
iste | -0.488 |
bang | -0.486 |
Token | monsters |
Token ID | 10963 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Blessing | +1.613 |
WN | +1.541 |
Gutenberg | +1.521 |
advertisement | +1.512 |
Vaugh | +1.465 |
Neg logit contributions | |
erent | -1.521 |
escal | -1.429 |
apo | -1.385 |
bang | -1.372 |
iste | -1.370 |
Token | , |
Token ID | 11 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Blessing | +0.045 |
WN | +0.043 |
Gutenberg | +0.042 |
advertisement | +0.042 |
Vaugh | +0.041 |
Neg logit contributions | |
erent | -0.038 |
escal | -0.035 |
apo | -0.034 |
iste | -0.033 |
bang | -0.033 |
Token | except |
Token ID | 2845 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
erent | +0.094 |
escal | +0.087 |
apo | +0.083 |
iste | +0.083 |
bang | +0.083 |
Neg logit contributions | |
Blessing | -0.114 |
WN | -0.111 |
advertisement | -0.109 |
Gutenberg | -0.109 |
Vaugh | -0.106 |
Token | for |
Token ID | 329 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
Blessing | +0.313 |
WN | +0.305 |
advertisement | +0.299 |
Gutenberg | +0.298 |
Vaugh | +0.290 |
Neg logit contributions | |
erent | -0.254 |
escal | -0.235 |
apo | -0.226 |
iste | -0.225 |
bang | -0.224 |
Token | � |
Token ID | 564 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
erent | +0.216 |
escal | +0.201 |
apo | +0.194 |
iste | +0.193 |
bang | +0.192 |
Neg logit contributions | |
Blessing | -0.219 |
WN | -0.213 |
advertisement | -0.208 |
Gutenberg | -0.208 |
Vaugh | -0.202 |
Token | modern |
Token ID | 3660 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Blessing | +0.269 |
WN | +0.261 |
advertisement | +0.256 |
Gutenberg | +0.255 |
Vaugh | +0.249 |
Neg logit contributions | |
erent | -0.229 |
escal | -0.213 |
apo | -0.206 |
iste | -0.205 |
bang | -0.203 |
Token | gameplay |
Token ID | 11327 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
erent | +0.385 |
escal | +0.356 |
apo | +0.344 |
iste | +0.340 |
bang | +0.340 |
Neg logit contributions | |
Blessing | -0.420 |
WN | -0.407 |
advertisement | -0.399 |
Gutenberg | -0.399 |
Vaugh | -0.388 |
Token | elements |
Token ID | 4847 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Blessing | +0.236 |
WN | +0.227 |
advertisement | +0.224 |
Gutenberg | +0.223 |
Vaugh | +0.216 |
Neg logit contributions | |
erent | -0.226 |
escal | -0.210 |
apo | -0.202 |
iste | -0.200 |
bang | -0.197 |
Token | of |
Token ID | 286 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
Blessing | +0.360 |
WN | +0.348 |
advertisement | +0.343 |
Gutenberg | +0.342 |
Vaugh | +0.331 |
Neg logit contributions | |
erent | -0.315 |
escal | -0.292 |
apo | -0.280 |
iste | -0.280 |
bang | -0.277 |
Token | car |
Token ID | 1097 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
Blessing | +0.170 |
WN | +0.165 |
advertisement | +0.162 |
Gutenberg | +0.161 |
Vaugh | +0.157 |
Neg logit contributions | |
erent | -0.141 |
escal | -0.130 |
apo | -0.125 |
iste | -0.125 |
bang | -0.125 |
Token | combat |
Token ID | 5249 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Blessing | +0.022 |
WN | +0.021 |
advertisement | +0.021 |
Gutenberg | +0.020 |
Vaugh | +0.020 |
Neg logit contributions | |
erent | -0.017 |
escal | -0.016 |
apo | -0.015 |
iste | -0.015 |
bang | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Blessing | +1.687 |
WN | +1.640 |
advertisement | +1.627 |
Gutenberg | +1.597 |
Vaugh | +1.536 |
Neg logit contributions | |
erent | -1.422 |
escal | -1.303 |
iste | -1.251 |
apo | -1.250 |
bang | -1.239 |
Token | multiplayer |
Token ID | 16913 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
erent | +0.054 |
escal | +0.050 |
apo | +0.048 |
iste | +0.048 |
bang | +0.048 |
Neg logit contributions | |
Blessing | -0.066 |
WN | -0.064 |
advertisement | -0.063 |
Gutenberg | -0.063 |
Vaugh | -0.061 |
Token | mayhem |
Token ID | 43744 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Blessing | +0.900 |
WN | +0.880 |
advertisement | +0.876 |
Gutenberg | +0.856 |
Vaugh | +0.830 |
Neg logit contributions | |
erent | -0.681 |
escal | -0.624 |
iste | -0.595 |
apo | -0.594 |
bang | -0.585 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Blessing | +0.551 |
WN | +0.536 |
advertisement | +0.530 |
Gutenberg | +0.525 |
Vaugh | +0.511 |
Neg logit contributions | |
erent | -0.379 |
escal | -0.347 |
iste | -0.334 |
apo | -0.331 |
bang | -0.324 |
Token |
|
Token ID | 198 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
erent | +0.136 |
escal | +0.127 |
apo | +0.123 |
iste | +0.123 |
bang | +0.122 |
Neg logit contributions | |
Blessing | -0.124 |
WN | -0.121 |
advertisement | -0.118 |
Gutenberg | -0.118 |
Vaugh | -0.114 |
Token | t |
Token ID | 83 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
Blessing | +0.168 |
WN | +0.164 |
advertisement | +0.161 |
Gutenberg | +0.159 |
Vaugh | +0.152 |
Neg logit contributions | |
erent | -0.136 |
escal | -0.127 |
apo | -0.122 |
bang | -0.121 |
iste | -0.121 |
Token | use |
Token ID | 779 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
Blessing | +0.195 |
WN | +0.188 |
Gutenberg | +0.183 |
advertisement | +0.183 |
Vaugh | +0.178 |
Neg logit contributions | |
erent | -0.198 |
escal | -0.186 |
iste | -0.179 |
apo | -0.179 |
bang | -0.178 |
Token | this |
Token ID | 428 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
erent | +0.105 |
escal | +0.098 |
apo | +0.095 |
iste | +0.095 |
bang | +0.094 |
Neg logit contributions | |
Blessing | -0.106 |
WN | -0.103 |
advertisement | -0.101 |
Gutenberg | -0.101 |
Vaugh | -0.098 |
Token | against |
Token ID | 1028 |
Feature activation | +1.57e-04 |
Pos logit contributions | |
Blessing | +0.063 |
WN | +0.061 |
advertisement | +0.060 |
Gutenberg | +0.060 |
Vaugh | +0.058 |
Neg logit contributions | |
erent | -0.050 |
escal | -0.047 |
apo | -0.045 |
iste | -0.045 |
bang | -0.044 |
Token | X |
Token ID | 1395 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Blessing | +0.000 |
WN | +0.000 |
Gutenberg | +0.000 |
advertisement | +0.000 |
Vaugh | +0.000 |
Neg logit contributions | |
erent | -0.000 |
escal | -0.000 |
apo | -0.000 |
iste | -0.000 |
bang | -0.000 |
Token | yz |
Token ID | 45579 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
Blessing | +0.226 |
WN | +0.218 |
advertisement | +0.212 |
Gutenberg | +0.210 |
Vaugh | +0.203 |
Neg logit contributions | |
erent | -0.392 |
escal | -0.371 |
apo | -0.360 |
iste | -0.360 |
bang | -0.358 |
Token | Monsters |
Token ID | 21464 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
Blessing | +1.662 |
WN | +1.607 |
Gutenberg | +1.579 |
advertisement | +1.573 |
Vaugh | +1.529 |
Neg logit contributions | |
erent | -1.434 |
escal | -1.330 |
apo | -1.284 |
iste | -1.279 |
bang | -1.273 |
Token | or |
Token ID | 393 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
erent | +0.088 |
escal | +0.081 |
apo | +0.078 |
iste | +0.077 |
bang | +0.077 |
Neg logit contributions | |
Blessing | -0.116 |
WN | -0.113 |
Gutenberg | -0.111 |
advertisement | -0.111 |
Vaugh | -0.108 |
Token | Link |
Token ID | 7502 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
Blessing | +0.217 |
WN | +0.210 |
advertisement | +0.205 |
Gutenberg | +0.205 |
Vaugh | +0.199 |
Neg logit contributions | |
erent | -0.223 |
escal | -0.209 |
apo | -0.202 |
iste | -0.201 |
bang | -0.200 |
Token | Monsters |
Token ID | 21464 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
Blessing | +0.124 |
WN | +0.121 |
advertisement | +0.119 |
Gutenberg | +0.118 |
Vaugh | +0.115 |
Neg logit contributions | |
erent | -0.119 |
escal | -0.111 |
iste | -0.107 |
apo | -0.107 |
bang | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
erent | +0.092 |
escal | +0.084 |
apo | +0.081 |
iste | +0.080 |
bang | +0.080 |
Neg logit contributions | |
Blessing | -0.130 |
WN | -0.126 |
Gutenberg | -0.124 |
advertisement | -0.124 |
Vaugh | -0.120 |
Token | will |
Token ID | 481 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
Blessing | +0.450 |
WN | +0.448 |
advertisement | +0.429 |
Gutenberg | +0.426 |
Vaugh | +0.419 |
Neg logit contributions | |
erent | -0.382 |
escal | -0.359 |
apo | -0.343 |
iste | -0.342 |
bang | -0.340 |
Token | be |
Token ID | 307 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Blessing | +0.137 |
WN | +0.133 |
advertisement | +0.129 |
Gutenberg | +0.128 |
Vaugh | +0.125 |
Neg logit contributions | |
erent | -0.142 |
escal | -0.133 |
apo | -0.129 |
iste | -0.129 |
bang | -0.127 |
Token | headed |
Token ID | 9153 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
erent | +0.048 |
escal | +0.045 |
apo | +0.044 |
iste | +0.044 |
bang | +0.043 |
Neg logit contributions | |
Blessing | -0.050 |
WN | -0.049 |
advertisement | -0.047 |
Gutenberg | -0.047 |
Vaugh | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
erent | +0.187 |
escal | +0.175 |
apo | +0.168 |
iste | +0.168 |
bang | +0.165 |
Neg logit contributions | |
Blessing | -0.193 |
WN | -0.188 |
advertisement | -0.183 |
Gutenberg | -0.183 |
Vaugh | -0.178 |
Token | Fort |
Token ID | 6401 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Blessing | +0.209 |
WN | +0.203 |
Gutenberg | +0.197 |
advertisement | +0.197 |
Vaugh | +0.191 |
Neg logit contributions | |
erent | -0.236 |
escal | -0.223 |
iste | -0.215 |
apo | -0.215 |
bang | -0.212 |
Token | Worth |
Token ID | 22301 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Blessing | +0.332 |
WN | +0.318 |
Gutenberg | +0.310 |
advertisement | +0.309 |
Vaugh | +0.301 |
Neg logit contributions | |
erent | -0.451 |
escal | -0.426 |
iste | -0.415 |
apo | -0.413 |
bang | -0.410 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Blessing | +1.675 |
WN | +1.627 |
Gutenberg | +1.586 |
advertisement | +1.582 |
Vaugh | +1.533 |
Neg logit contributions | |
erent | -1.411 |
escal | -1.317 |
iste | -1.254 |
apo | -1.245 |
bang | -1.238 |
Token | cover |
Token ID | 3002 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Blessing | +0.080 |
WN | +0.078 |
advertisement | +0.076 |
Gutenberg | +0.075 |
Vaugh | +0.073 |
Neg logit contributions | |
erent | -0.080 |
escal | -0.075 |
apo | -0.073 |
iste | -0.073 |
bang | -0.071 |
Token | Utah |
Token ID | 10202 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
erent | +0.076 |
escal | +0.071 |
apo | +0.068 |
iste | +0.068 |
bang | +0.068 |
Neg logit contributions | |
Blessing | -0.080 |
WN | -0.078 |
advertisement | -0.076 |
Gutenberg | -0.075 |
Vaugh | -0.074 |
Token | - |
Token ID | 12 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
Blessing | +0.096 |
WN | +0.094 |
advertisement | +0.091 |
Gutenberg | +0.091 |
Vaugh | +0.089 |
Neg logit contributions | |
erent | -0.080 |
escal | -0.075 |
iste | -0.072 |
bang | -0.071 |
apo | -0.071 |
Token | TC |
Token ID | 4825 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
Blessing | +0.211 |
WN | +0.210 |
advertisement | +0.205 |
Gutenberg | +0.198 |
Vaugh | +0.194 |
Neg logit contributions | |
erent | -0.207 |
escal | -0.192 |
iste | -0.188 |
apo | -0.184 |
bang | -0.183 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
Blessing | +0.094 |
WN | +0.091 |
advertisement | +0.089 |
Gutenberg | +0.089 |
Vaugh | +0.087 |
Neg logit contributions | |
erent | -0.081 |
escal | -0.075 |
apo | -0.073 |
iste | -0.072 |
bang | -0.071 |
Token | we |
Token ID | 356 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
Blessing | +0.110 |
WN | +0.107 |
Gutenberg | +0.104 |
advertisement | +0.104 |
Vaugh | +0.102 |
Neg logit contributions | |
erent | -0.103 |
escal | -0.095 |
apo | -0.091 |
iste | -0.091 |
bang | -0.090 |
Token | were |
Token ID | 547 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
Blessing | +0.092 |
WN | +0.089 |
Gutenberg | +0.086 |
advertisement | +0.086 |
Vaugh | +0.084 |
Neg logit contributions | |
erent | -0.105 |
escal | -0.098 |
apo | -0.094 |
bang | -0.094 |
iste | -0.094 |
Token | still |
Token ID | 991 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Blessing | +0.196 |
WN | +0.188 |
advertisement | +0.184 |
Gutenberg | +0.183 |
Vaugh | +0.180 |
Neg logit contributions | |
erent | -0.182 |
escal | -0.170 |
apo | -0.164 |
iste | -0.162 |
bang | -0.162 |
Token | gro |
Token ID | 7128 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
Blessing | +0.372 |
WN | +0.360 |
advertisement | +0.351 |
Gutenberg | +0.350 |
Vaugh | +0.343 |
Neg logit contributions | |
erent | -0.328 |
escal | -0.305 |
apo | -0.293 |
iste | -0.292 |
bang | -0.290 |
Token | ggy |
Token ID | 19970 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Blessing | +0.213 |
WN | +0.206 |
advertisement | +0.201 |
Gutenberg | +0.201 |
Vaugh | +0.195 |
Neg logit contributions | |
erent | -0.264 |
escal | -0.249 |
apo | -0.240 |
iste | -0.240 |
bang | -0.239 |
Token | from |
Token ID | 422 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
Blessing | +1.637 |
WN | +1.594 |
advertisement | +1.554 |
Gutenberg | +1.544 |
Vaugh | +1.515 |
Neg logit contributions | |
erent | -1.423 |
escal | -1.321 |
apo | -1.269 |
iste | -1.255 |
bang | -1.242 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
Blessing | +0.037 |
WN | +0.035 |
Gutenberg | +0.035 |
advertisement | +0.035 |
Vaugh | +0.034 |
Neg logit contributions | |
erent | -0.034 |
escal | -0.031 |
apo | -0.030 |
iste | -0.030 |
bang | -0.030 |
Token | night |
Token ID | 1755 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Blessing | +0.082 |
WN | +0.079 |
Gutenberg | +0.078 |
advertisement | +0.077 |
Vaugh | +0.076 |
Neg logit contributions | |
erent | -0.063 |
escal | -0.058 |
apo | -0.055 |
iste | -0.055 |
bang | -0.055 |
Token | before |
Token ID | 878 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Blessing | +0.166 |
WN | +0.161 |
Gutenberg | +0.158 |
advertisement | +0.157 |
Vaugh | +0.154 |
Neg logit contributions | |
erent | -0.129 |
escal | -0.118 |
iste | -0.112 |
bang | -0.112 |
apo | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
erent | +0.254 |
escal | +0.233 |
iste | +0.222 |
apo | +0.220 |
bang | +0.219 |
Neg logit contributions | |
Blessing | -0.375 |
WN | -0.364 |
advertisement | -0.358 |
Gutenberg | -0.357 |
Vaugh | -0.349 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Blessing | +0.084 |
WN | +0.082 |
advertisement | +0.080 |
Gutenberg | +0.080 |
Vaugh | +0.077 |
Neg logit contributions | |
erent | -0.074 |
escal | -0.069 |
apo | -0.067 |
iste | -0.067 |
bang | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
erent | +0.027 |
escal | +0.025 |
apo | +0.024 |
iste | +0.024 |
bang | +0.024 |
Neg logit contributions | |
Blessing | -0.029 |
WN | -0.028 |
advertisement | -0.028 |
Gutenberg | -0.028 |
Vaugh | -0.027 |
Token | then |
Token ID | 788 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Blessing | +0.029 |
WN | +0.028 |
Gutenberg | +0.028 |
advertisement | +0.028 |
Vaugh | +0.027 |
Neg logit contributions | |
erent | -0.028 |
escal | -0.026 |
iste | -0.025 |
apo | -0.025 |
bang | -0.025 |
Token | you |
Token ID | 345 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
Blessing | +0.280 |
WN | +0.269 |
Gutenberg | +0.265 |
advertisement | +0.264 |
Vaugh | +0.256 |
Neg logit contributions | |
erent | -0.248 |
escal | -0.231 |
iste | -0.223 |
apo | -0.223 |
bang | -0.220 |
Token | Special |
Token ID | 6093 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
erent | +0.112 |
escal | +0.104 |
iste | +0.101 |
apo | +0.101 |
bang | +0.100 |
Neg logit contributions | |
Blessing | -0.122 |
WN | -0.118 |
Gutenberg | -0.115 |
advertisement | -0.115 |
Vaugh | -0.112 |
Token | Summon |
Token ID | 19515 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
Blessing | +0.120 |
WN | +0.115 |
advertisement | +0.111 |
Gutenberg | +0.110 |
Vaugh | +0.106 |
Neg logit contributions | |
erent | -0.276 |
escal | -0.262 |
iste | -0.255 |
apo | -0.255 |
bang | -0.254 |
Token | an |
Token ID | 281 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Blessing | +1.585 |
WN | +1.533 |
Gutenberg | +1.502 |
advertisement | +1.500 |
Vaugh | +1.453 |
Neg logit contributions | |
erent | -1.480 |
escal | -1.380 |
apo | -1.335 |
iste | -1.329 |
bang | -1.322 |
Token | ATK |
Token ID | 24526 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
erent | +0.068 |
escal | +0.064 |
apo | +0.061 |
iste | +0.061 |
bang | +0.061 |
Neg logit contributions | |
Blessing | -0.060 |
WN | -0.059 |
advertisement | -0.057 |
Gutenberg | -0.057 |
Vaugh | -0.056 |
Token | 0 |
Token ID | 657 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Blessing | +0.643 |
WN | +0.629 |
advertisement | +0.620 |
Gutenberg | +0.616 |
Vaugh | +0.603 |
Neg logit contributions | |
erent | -0.509 |
escal | -0.470 |
iste | -0.449 |
apo | -0.447 |
bang | -0.445 |
Token | / |
Token ID | 14 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
erent | +0.055 |
escal | +0.051 |
iste | +0.049 |
apo | +0.049 |
bang | +0.048 |
Neg logit contributions | |
Blessing | -0.067 |
WN | -0.066 |
advertisement | -0.065 |
Gutenberg | -0.064 |
Vaugh | -0.063 |
Token | DEF |
Token ID | 32988 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
erent | +0.415 |
escal | +0.388 |
apo | +0.374 |
bang | +0.371 |
iste | +0.370 |
Neg logit contributions | |
Blessing | -0.383 |
WN | -0.367 |
Gutenberg | -0.364 |
advertisement | -0.361 |
Vaugh | -0.356 |
Token | as |
Token ID | 355 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
erent | +0.016 |
escal | +0.015 |
apo | +0.015 |
bang | +0.015 |
iste | +0.015 |
Neg logit contributions | |
Blessing | -0.019 |
WN | -0.019 |
advertisement | -0.018 |
Gutenberg | -0.018 |
Vaugh | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
erent | +0.073 |
escal | +0.068 |
iste | +0.065 |
apo | +0.065 |
bang | +0.065 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.079 |
advertisement | -0.077 |
Gutenberg | -0.077 |
Vaugh | -0.075 |
Token | possibly |
Token ID | 5457 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
erent | +0.018 |
escal | +0.017 |
apo | +0.016 |
bang | +0.016 |
iste | +0.016 |
Neg logit contributions | |
Blessing | -0.027 |
WN | -0.026 |
advertisement | -0.025 |
Gutenberg | -0.025 |
Vaugh | -0.025 |
Token | remedy |
Token ID | 21210 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Blessing | +0.493 |
WN | +0.482 |
advertisement | +0.472 |
Gutenberg | +0.471 |
Vaugh | +0.456 |
Neg logit contributions | |
erent | -0.401 |
escal | -0.369 |
apo | -0.355 |
iste | -0.353 |
bang | -0.351 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Blessing | +0.731 |
WN | +0.713 |
advertisement | +0.698 |
Gutenberg | +0.697 |
Vaugh | +0.677 |
Neg logit contributions | |
erent | -0.633 |
escal | -0.586 |
apo | -0.563 |
iste | -0.562 |
bang | -0.561 |
Token | combat |
Token ID | 5249 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Blessing | +0.036 |
WN | +0.035 |
advertisement | +0.035 |
Gutenberg | +0.034 |
Vaugh | +0.033 |
Neg logit contributions | |
erent | -0.030 |
escal | -0.028 |
iste | -0.027 |
bang | -0.027 |
apo | -0.027 |
Token | losses |
Token ID | 9089 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Blessing | +1.603 |
WN | +1.561 |
advertisement | +1.540 |
Gutenberg | +1.531 |
Vaugh | +1.461 |
Neg logit contributions | |
erent | -1.422 |
escal | -1.315 |
iste | -1.270 |
apo | -1.269 |
bang | -1.264 |
Token | from |
Token ID | 422 |
Feature activation | -4.84e-03 |
Pos logit contributions | |
erent | +0.078 |
escal | +0.073 |
iste | +0.070 |
apo | +0.070 |
bang | +0.070 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.079 |
Gutenberg | -0.077 |
advertisement | -0.077 |
Vaugh | -0.074 |
Token | customers |
Token ID | 4297 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
erent | +0.010 |
escal | +0.010 |
apo | +0.009 |
iste | +0.009 |
bang | +0.009 |
Neg logit contributions | |
Blessing | -0.013 |
WN | -0.013 |
Gutenberg | -0.012 |
advertisement | -0.012 |
Vaugh | -0.012 |
Token | who |
Token ID | 508 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
Blessing | +0.594 |
WN | +0.580 |
Gutenberg | +0.573 |
advertisement | +0.571 |
Vaugh | +0.547 |
Neg logit contributions | |
erent | -0.505 |
escal | -0.466 |
apo | -0.457 |
iste | -0.453 |
bang | -0.443 |
Token | are |
Token ID | 389 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Blessing | +0.194 |
WN | +0.190 |
Gutenberg | +0.187 |
advertisement | +0.184 |
Vaugh | +0.179 |
Neg logit contributions | |
erent | -0.180 |
escal | -0.167 |
apo | -0.163 |
iste | -0.162 |
bang | -0.159 |
Token | coded |
Token ID | 30817 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
erent | +0.287 |
escal | +0.269 |
apo | +0.260 |
iste | +0.258 |
bang | +0.257 |
Neg logit contributions | |
Blessing | -0.257 |
WN | -0.250 |
advertisement | -0.244 |
Gutenberg | -0.244 |
Vaugh | -0.236 |
Token | The |
Token ID | 383 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
erent | +0.197 |
escal | +0.181 |
apo | +0.173 |
iste | +0.173 |
bang | +0.171 |
Neg logit contributions | |
Blessing | -0.251 |
WN | -0.245 |
advertisement | -0.241 |
Gutenberg | -0.240 |
Vaugh | -0.232 |
Token | boot |
Token ID | 6297 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Blessing | +0.379 |
WN | +0.368 |
Gutenberg | +0.361 |
advertisement | +0.361 |
Vaugh | +0.350 |
Neg logit contributions | |
erent | -0.332 |
escal | -0.309 |
iste | -0.295 |
apo | -0.295 |
bang | -0.293 |
Token | loader |
Token ID | 29356 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Blessing | +0.391 |
WN | +0.379 |
advertisement | +0.371 |
Gutenberg | +0.371 |
Vaugh | +0.359 |
Neg logit contributions | |
erent | -0.418 |
escal | -0.391 |
apo | -0.376 |
iste | -0.376 |
bang | -0.373 |
Token | res |
Token ID | 581 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Blessing | +0.330 |
WN | +0.320 |
advertisement | +0.314 |
Gutenberg | +0.313 |
Vaugh | +0.302 |
Neg logit contributions | |
erent | -0.322 |
escal | -0.300 |
apo | -0.289 |
iste | -0.287 |
bang | -0.285 |
Token | ets |
Token ID | 1039 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
Blessing | +0.440 |
WN | +0.430 |
advertisement | +0.423 |
Gutenberg | +0.421 |
Vaugh | +0.411 |
Neg logit contributions | |
erent | -0.332 |
escal | -0.306 |
apo | -0.293 |
iste | -0.292 |
bang | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Blessing | +1.625 |
WN | +1.574 |
Gutenberg | +1.563 |
advertisement | +1.538 |
Vaugh | +1.489 |
Neg logit contributions | |
erent | -1.380 |
escal | -1.282 |
iste | -1.226 |
apo | -1.224 |
bang | -1.218 |
Token | power |
Token ID | 1176 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Blessing | +0.310 |
WN | +0.301 |
advertisement | +0.295 |
Gutenberg | +0.294 |
Vaugh | +0.286 |
Neg logit contributions | |
erent | -0.282 |
escal | -0.262 |
iste | -0.251 |
apo | -0.251 |
bang | -0.250 |
Token | key |
Token ID | 1994 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
Blessing | +0.227 |
WN | +0.221 |
advertisement | +0.217 |
Gutenberg | +0.216 |
Vaugh | +0.210 |
Neg logit contributions | |
erent | -0.197 |
escal | -0.183 |
iste | -0.176 |
apo | -0.175 |
bang | -0.174 |
Token | status |
Token ID | 3722 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
Blessing | +0.214 |
WN | +0.208 |
advertisement | +0.204 |
Gutenberg | +0.204 |
Vaugh | +0.196 |
Neg logit contributions | |
erent | -0.197 |
escal | -0.184 |
iste | -0.177 |
apo | -0.175 |
bang | -0.174 |
Token | on |
Token ID | 319 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
erent | +0.079 |
escal | +0.074 |
iste | +0.071 |
apo | +0.071 |
bang | +0.070 |
Neg logit contributions | |
Blessing | -0.082 |
WN | -0.079 |
Gutenberg | -0.078 |
advertisement | -0.077 |
Vaugh | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Blessing | +0.113 |
WN | +0.110 |
advertisement | +0.109 |
Gutenberg | +0.106 |
Majesty | +0.099 |
Neg logit contributions | |
erent | -0.122 |
escal | -0.113 |
apo | -0.110 |
iste | -0.109 |
bang | -0.108 |
Token | With |
Token ID | 3152 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Blessing | +0.038 |
WN | +0.038 |
advertisement | +0.037 |
Gutenberg | +0.036 |
Vaugh | +0.035 |
Neg logit contributions | |
erent | -0.042 |
escal | -0.039 |
apo | -0.038 |
iste | -0.038 |
bang | -0.037 |
Token | filming |
Token ID | 17691 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
erent | +0.046 |
escal | +0.043 |
iste | +0.042 |
apo | +0.042 |
bang | +0.041 |
Neg logit contributions | |
Blessing | -0.051 |
WN | -0.049 |
Gutenberg | -0.049 |
advertisement | -0.048 |
Vaugh | -0.047 |
Token | for |
Token ID | 329 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
Blessing | +0.556 |
WN | +0.537 |
Gutenberg | +0.529 |
advertisement | +0.526 |
Vaugh | +0.511 |
Neg logit contributions | |
erent | -0.485 |
escal | -0.443 |
apo | -0.429 |
iste | -0.428 |
bang | -0.420 |
Token | Teen |
Token ID | 21432 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
Blessing | +0.222 |
WN | +0.214 |
Gutenberg | +0.210 |
advertisement | +0.208 |
Vaugh | +0.204 |
Neg logit contributions | |
erent | -0.217 |
escal | -0.203 |
iste | -0.196 |
apo | -0.196 |
bang | -0.194 |
Token | age |
Token ID | 496 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
Blessing | +0.107 |
WN | +0.103 |
advertisement | +0.099 |
Gutenberg | +0.099 |
Vaugh | +0.097 |
Neg logit contributions | |
erent | -0.158 |
escal | -0.149 |
apo | -0.144 |
iste | -0.144 |
bang | -0.143 |
Token | Mutant |
Token ID | 35319 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Blessing | +0.959 |
WN | +0.894 |
Gutenberg | +0.863 |
advertisement | +0.860 |
Vaugh | +0.824 |
Neg logit contributions | |
erent | -2.047 |
escal | -1.942 |
apo | -1.893 |
iste | -1.877 |
bang | -1.871 |
Token | Ninja |
Token ID | 14152 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Blessing | +0.110 |
WN | +0.107 |
advertisement | +0.104 |
Gutenberg | +0.104 |
Vaugh | +0.101 |
Neg logit contributions | |
erent | -0.143 |
escal | -0.135 |
iste | -0.131 |
apo | -0.130 |
bang | -0.130 |
Token | Turtles |
Token ID | 44356 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Blessing | +0.201 |
WN | +0.194 |
advertisement | +0.191 |
Gutenberg | +0.189 |
Vaugh | +0.184 |
Neg logit contributions | |
erent | -0.223 |
escal | -0.208 |
apo | -0.201 |
iste | -0.199 |
bang | -0.199 |
Token | II |
Token ID | 2873 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
Blessing | +0.712 |
WN | +0.689 |
advertisement | +0.679 |
Gutenberg | +0.676 |
Vaugh | +0.656 |
Neg logit contributions | |
erent | -0.670 |
escal | -0.616 |
apo | -0.597 |
iste | -0.596 |
bang | -0.593 |
Token | : |
Token ID | 25 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
Blessing | +0.045 |
WN | +0.044 |
advertisement | +0.043 |
Gutenberg | +0.043 |
Vaugh | +0.042 |
Neg logit contributions | |
erent | -0.039 |
escal | -0.036 |
iste | -0.035 |
apo | -0.035 |
bang | -0.034 |
Token | first |
Token ID | 717 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
erent | +0.255 |
escal | +0.239 |
apo | +0.230 |
iste | +0.230 |
bang | +0.229 |
Neg logit contributions | |
Blessing | -0.242 |
WN | -0.235 |
advertisement | -0.230 |
Gutenberg | -0.229 |
Vaugh | -0.223 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Blessing | +0.028 |
WN | +0.027 |
advertisement | +0.026 |
Gutenberg | +0.026 |
Vaugh | +0.025 |
Neg logit contributions | |
erent | -0.033 |
escal | -0.031 |
iste | -0.030 |
apo | -0.030 |
bang | -0.030 |
Token | hear |
Token ID | 3285 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
erent | +0.292 |
escal | +0.274 |
apo | +0.262 |
iste | +0.261 |
bang | +0.259 |
Neg logit contributions | |
Blessing | -0.295 |
Gutenberg | -0.279 |
advertisement | -0.278 |
WN | -0.275 |
Vaugh | -0.274 |
Token | about |
Token ID | 546 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Blessing | +0.104 |
WN | +0.102 |
advertisement | +0.099 |
Gutenberg | +0.099 |
Vaugh | +0.096 |
Neg logit contributions | |
erent | -0.111 |
escal | -0.104 |
apo | -0.100 |
iste | -0.100 |
bang | -0.100 |
Token | Nation |
Token ID | 8741 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
erent | +0.841 |
escal | +0.800 |
iste | +0.778 |
apo | +0.768 |
bang | +0.762 |
Neg logit contributions | |
Blessing | -0.451 |
WN | -0.446 |
Gutenberg | -0.411 |
advertisement | -0.406 |
Vaugh | -0.389 |
Token | Travels |
Token ID | 48899 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
erent | +0.192 |
escal | +0.178 |
apo | +0.172 |
iste | +0.169 |
bang | +0.168 |
Neg logit contributions | |
Blessing | -0.197 |
WN | -0.192 |
advertisement | -0.188 |
Gutenberg | -0.186 |
Vaugh | -0.181 |
Token | destinations |
Token ID | 23982 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
erent | +1.493 |
escal | +1.372 |
iste | +1.330 |
apo | +1.311 |
bang | +1.287 |
Neg logit contributions | |
Blessing | -2.025 |
WN | -1.960 |
advertisement | -1.939 |
Gutenberg | -1.926 |
Vaugh | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
erent | +0.814 |
escal | +0.758 |
iste | +0.723 |
apo | +0.721 |
bang | +0.706 |
Neg logit contributions | |
Blessing | -1.123 |
WN | -1.092 |
Gutenberg | -1.071 |
advertisement | -1.063 |
Vaugh | -1.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
erent | +0.466 |
escal | +0.434 |
iste | +0.419 |
apo | +0.417 |
bang | +0.412 |
Neg logit contributions | |
Blessing | -0.471 |
WN | -0.458 |
advertisement | -0.450 |
Gutenberg | -0.447 |
Vaugh | -0.428 |
Token | explore |
Token ID | 7301 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
erent | +0.474 |
escal | +0.444 |
apo | +0.427 |
iste | +0.426 |
bang | +0.426 |
Neg logit contributions | |
Blessing | -0.453 |
WN | -0.440 |
Gutenberg | -0.430 |
advertisement | -0.430 |
Vaugh | -0.418 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
erent | +0.278 |
escal | +0.260 |
iste | +0.251 |
apo | +0.250 |
bang | +0.247 |
Neg logit contributions | |
Blessing | -0.263 |
WN | -0.257 |
advertisement | -0.250 |
Gutenberg | -0.250 |
Vaugh | -0.238 |
Token | first |
Token ID | 717 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
erent | +0.251 |
escal | +0.235 |
apo | +0.227 |
iste | +0.226 |
bang | +0.226 |
Neg logit contributions | |
Blessing | -0.224 |
WN | -0.215 |
advertisement | -0.212 |
Gutenberg | -0.211 |
Vaugh | -0.203 |
Token | to |
Token ID | 284 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
erent | +0.068 |
escal | +0.063 |
iste | +0.062 |
apo | +0.062 |
bang | +0.061 |
Neg logit contributions | |
Blessing | -0.055 |
WN | -0.054 |
advertisement | -0.053 |
Gutenberg | -0.052 |
Vaugh | -0.049 |
Token | hear |
Token ID | 3285 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
erent | +0.112 |
escal | +0.106 |
iste | +0.104 |
apo | +0.104 |
bang | +0.103 |
Neg logit contributions | |
WN | -0.075 |
Blessing | -0.075 |
advertisement | -0.073 |
Gutenberg | -0.072 |
Vaugh | -0.066 |
Token | about |
Token ID | 546 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Blessing | +0.205 |
WN | +0.199 |
advertisement | +0.195 |
Gutenberg | +0.194 |
Vaugh | +0.185 |
Neg logit contributions | |
erent | -0.228 |
escal | -0.214 |
apo | -0.207 |
iste | -0.205 |
bang | -0.205 |
Token | Nation |
Token ID | 8741 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
erent | +0.563 |
escal | +0.536 |
iste | +0.520 |
apo | +0.519 |
bang | +0.517 |
Neg logit contributions | |
Blessing | -0.325 |
WN | -0.315 |
advertisement | -0.303 |
Gutenberg | -0.301 |
Vaugh | -0.283 |
Token | Travels |
Token ID | 48899 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
erent | +0.070 |
escal | +0.065 |
apo | +0.063 |
iste | +0.063 |
bang | +0.062 |
Neg logit contributions | |
Blessing | -0.070 |
WN | -0.068 |
advertisement | -0.067 |
Gutenberg | -0.066 |
Vaugh | -0.064 |
Token | destinations |
Token ID | 23982 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
erent | +1.511 |
escal | +1.387 |
iste | +1.343 |
apo | +1.334 |
bang | +1.304 |
Neg logit contributions | |
Blessing | -1.978 |
WN | -1.923 |
advertisement | -1.888 |
Gutenberg | -1.880 |
Vaugh | -1.859 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
erent | +0.668 |
escal | +0.613 |
apo | +0.587 |
iste | +0.582 |
bang | +0.576 |
Neg logit contributions | |
Blessing | -0.936 |
WN | -0.916 |
advertisement | -0.903 |
Gutenberg | -0.894 |
Vaugh | -0.846 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
erent | +0.323 |
escal | +0.299 |
apo | +0.292 |
iste | +0.287 |
bang | +0.286 |
Neg logit contributions | |
Blessing | -0.319 |
WN | -0.309 |
advertisement | -0.306 |
Gutenberg | -0.302 |
Vaugh | -0.285 |
Token | explore |
Token ID | 7301 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
erent | +0.295 |
escal | +0.274 |
bang | +0.267 |
apo | +0.267 |
iste | +0.265 |
Neg logit contributions | |
Blessing | -0.221 |
WN | -0.217 |
advertisement | -0.217 |
Gutenberg | -0.215 |
Vaugh | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
erent | +0.180 |
escal | +0.168 |
apo | +0.165 |
bang | +0.162 |
iste | +0.161 |
Neg logit contributions | |
Blessing | -0.159 |
WN | -0.155 |
advertisement | -0.153 |
Gutenberg | -0.152 |
Majesty | -0.142 |
Token | of |
Token ID | 286 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
erent | +0.347 |
escal | +0.321 |
iste | +0.310 |
apo | +0.309 |
bang | +0.308 |
Neg logit contributions | |
Blessing | -0.375 |
WN | -0.367 |
advertisement | -0.358 |
Gutenberg | -0.357 |
Vaugh | -0.349 |
Token | all |
Token ID | 477 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
erent | +0.065 |
escal | +0.061 |
iste | +0.059 |
apo | +0.059 |
bang | +0.058 |
Neg logit contributions | |
Blessing | -0.063 |
WN | -0.061 |
Gutenberg | -0.060 |
advertisement | -0.059 |
Vaugh | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
erent | +0.115 |
escal | +0.107 |
iste | +0.102 |
apo | +0.102 |
bang | +0.101 |
Neg logit contributions | |
Blessing | -0.134 |
WN | -0.131 |
Gutenberg | -0.128 |
advertisement | -0.127 |
Vaugh | -0.124 |
Token | key |
Token ID | 1994 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
erent | +0.231 |
escal | +0.215 |
iste | +0.206 |
apo | +0.206 |
bang | +0.204 |
Neg logit contributions | |
Blessing | -0.233 |
WN | -0.226 |
Gutenberg | -0.221 |
advertisement | -0.220 |
Vaugh | -0.214 |
Token | major |
Token ID | 1688 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
erent | +0.113 |
escal | +0.106 |
iste | +0.102 |
apo | +0.102 |
bang | +0.100 |
Neg logit contributions | |
Blessing | -0.111 |
WN | -0.108 |
Gutenberg | -0.105 |
advertisement | -0.105 |
Vaugh | -0.102 |
Token | foundations |
Token ID | 19369 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Blessing | +0.118 |
WN | +0.114 |
Gutenberg | +0.112 |
advertisement | +0.111 |
Vaugh | +0.107 |
Neg logit contributions | |
erent | -0.124 |
escal | -0.116 |
iste | -0.111 |
apo | -0.111 |
bang | -0.109 |
Token | in |
Token ID | 287 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
erent | +1.588 |
escal | +1.475 |
apo | +1.416 |
iste | +1.415 |
bang | +1.407 |
Neg logit contributions | |
Blessing | -1.799 |
WN | -1.752 |
advertisement | -1.717 |
Gutenberg | -1.712 |
Vaugh | -1.669 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
erent | +0.196 |
escal | +0.183 |
apo | +0.176 |
iste | +0.175 |
bang | +0.174 |
Neg logit contributions | |
Blessing | -0.204 |
WN | -0.199 |
Gutenberg | -0.195 |
advertisement | -0.194 |
Vaugh | -0.188 |
Token | financing |
Token ID | 15435 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
erent | +0.241 |
escal | +0.224 |
iste | +0.215 |
apo | +0.215 |
bang | +0.212 |
Neg logit contributions | |
Blessing | -0.259 |
WN | -0.250 |
Gutenberg | -0.247 |
advertisement | -0.244 |
Vaugh | -0.238 |
Token | of |
Token ID | 286 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
erent | +0.090 |
escal | +0.084 |
apo | +0.081 |
iste | +0.081 |
bang | +0.080 |
Neg logit contributions | |
Blessing | -0.089 |
WN | -0.087 |
advertisement | -0.085 |
Gutenberg | -0.085 |
Vaugh | -0.082 |
Token | environmental |
Token ID | 6142 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
erent | +0.103 |
escal | +0.096 |
iste | +0.092 |
apo | +0.092 |
bang | +0.091 |
Neg logit contributions | |
Blessing | -0.105 |
WN | -0.102 |
Gutenberg | -0.100 |
advertisement | -0.099 |
Vaugh | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
erent | +0.430 |
escal | +0.400 |
apo | +0.384 |
iste | +0.384 |
bang | +0.382 |
Neg logit contributions | |
Blessing | -0.469 |
WN | -0.456 |
advertisement | -0.446 |
Gutenberg | -0.446 |
Vaugh | -0.433 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
erent | +0.265 |
escal | +0.247 |
apo | +0.240 |
iste | +0.237 |
bang | +0.234 |
Neg logit contributions | |
Blessing | -0.256 |
WN | -0.249 |
advertisement | -0.245 |
Gutenberg | -0.240 |
Majesty | -0.225 |
Token | Ko |
Token ID | 48735 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
erent | +0.287 |
escal | +0.267 |
iste | +0.257 |
apo | +0.257 |
bang | +0.255 |
Neg logit contributions | |
Blessing | -0.286 |
WN | -0.280 |
advertisement | -0.274 |
Gutenberg | -0.271 |
Vaugh | -0.262 |
Token | Do |
Token ID | 5211 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
erent | +0.643 |
escal | +0.597 |
iste | +0.578 |
apo | +0.577 |
bang | +0.572 |
Neg logit contributions | |
Blessing | -0.646 |
WN | -0.623 |
advertisement | -0.615 |
Gutenberg | -0.613 |
Vaugh | -0.598 |
Token | Profile |
Token ID | 13118 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Blessing | +0.150 |
WN | +0.146 |
advertisement | +0.143 |
Gutenberg | +0.143 |
Vaugh | +0.139 |
Neg logit contributions | |
erent | -0.150 |
escal | -0.140 |
apo | -0.134 |
iste | -0.134 |
bang | -0.134 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
erent | +0.582 |
escal | +0.545 |
iste | +0.529 |
apo | +0.527 |
bang | +0.527 |
Neg logit contributions | |
Blessing | -0.523 |
WN | -0.510 |
advertisement | -0.502 |
Gutenberg | -0.496 |
Vaugh | -0.483 |
Token | December |
Token ID | 3426 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
erent | +1.646 |
escal | +1.535 |
apo | +1.486 |
iste | +1.473 |
bang | +1.466 |
Neg logit contributions | |
Blessing | -1.608 |
WN | -1.553 |
advertisement | -1.518 |
Gutenberg | -1.518 |
Vaugh | -1.471 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
erent | +0.237 |
escal | +0.222 |
apo | +0.214 |
iste | +0.211 |
bang | +0.211 |
Neg logit contributions | |
Blessing | -0.218 |
WN | -0.209 |
Gutenberg | -0.205 |
advertisement | -0.203 |
Vaugh | -0.198 |
Token | United |
Token ID | 1578 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
erent | +0.567 |
escal | +0.528 |
apo | +0.508 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.598 |
WN | -0.582 |
advertisement | -0.569 |
Gutenberg | -0.568 |
Vaugh | -0.553 |
Token | States |
Token ID | 1829 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
erent | +0.838 |
escal | +0.793 |
apo | +0.769 |
iste | +0.769 |
bang | +0.766 |
Neg logit contributions | |
Blessing | -0.512 |
WN | -0.494 |
advertisement | -0.481 |
Gutenberg | -0.478 |
Vaugh | -0.462 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
erent | +0.565 |
escal | +0.527 |
apo | +0.511 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.524 |
WN | -0.507 |
Gutenberg | -0.496 |
advertisement | -0.493 |
Vaugh | -0.481 |
Token | and |
Token ID | 290 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
Blessing | +0.221 |
WN | +0.212 |
Gutenberg | +0.209 |
advertisement | +0.207 |
Vaugh | +0.201 |
Neg logit contributions | |
erent | -0.234 |
escal | -0.217 |
apo | -0.210 |
iste | -0.209 |
bang | -0.208 |
Token | Laurie |
Token ID | 40811 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
erent | +0.252 |
escal | +0.236 |
apo | +0.228 |
iste | +0.228 |
bang | +0.227 |
Neg logit contributions | |
Blessing | -0.205 |
WN | -0.197 |
Gutenberg | -0.193 |
advertisement | -0.192 |
Vaugh | -0.187 |
Token | Land |
Token ID | 6379 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Blessing | +0.036 |
WN | +0.035 |
advertisement | +0.035 |
Gutenberg | +0.034 |
Vaugh | +0.033 |
Neg logit contributions | |
erent | -0.042 |
escal | -0.040 |
apo | -0.038 |
iste | -0.038 |
bang | -0.038 |
Token | e |
Token ID | 68 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
erent | +0.610 |
escal | +0.572 |
apo | +0.551 |
iste | +0.549 |
bang | +0.549 |
Neg logit contributions | |
Blessing | -0.569 |
WN | -0.552 |
Gutenberg | -0.540 |
advertisement | -0.539 |
Vaugh | -0.522 |
Token | au |
Token ID | 559 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
erent | +0.527 |
escal | +0.493 |
iste | +0.473 |
apo | +0.473 |
bang | +0.470 |
Neg logit contributions | |
Blessing | -0.528 |
WN | -0.513 |
advertisement | -0.501 |
Gutenberg | -0.500 |
Vaugh | -0.486 |
Token | foundations |
Token ID | 19369 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
erent | +0.493 |
escal | +0.461 |
apo | +0.444 |
iste | +0.443 |
bang | +0.441 |
Neg logit contributions | |
Blessing | -0.475 |
WN | -0.461 |
advertisement | -0.451 |
Gutenberg | -0.450 |
Vaugh | -0.437 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
erent | +1.253 |
escal | +1.145 |
apo | +1.091 |
iste | +1.091 |
bang | +1.083 |
Neg logit contributions | |
Blessing | -1.915 |
WN | -1.875 |
advertisement | -1.839 |
Gutenberg | -1.833 |
Vaugh | -1.802 |
Token | as |
Token ID | 355 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
erent | +0.235 |
escal | +0.219 |
apo | +0.210 |
iste | +0.210 |
bang | +0.209 |
Neg logit contributions | |
Blessing | -0.247 |
WN | -0.241 |
advertisement | -0.236 |
Gutenberg | -0.235 |
Vaugh | -0.229 |
Token | well |
Token ID | 880 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
erent | +0.195 |
escal | +0.183 |
apo | +0.177 |
iste | +0.177 |
bang | +0.176 |
Neg logit contributions | |
Blessing | -0.156 |
WN | -0.151 |
advertisement | -0.148 |
Gutenberg | -0.147 |
Vaugh | -0.142 |
Token | as |
Token ID | 355 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
erent | +0.201 |
escal | +0.187 |
iste | +0.180 |
apo | +0.180 |
bang | +0.179 |
Neg logit contributions | |
Blessing | -0.218 |
WN | -0.212 |
advertisement | -0.208 |
Gutenberg | -0.208 |
Vaugh | -0.197 |
Token | awards |
Token ID | 13304 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
erent | +0.007 |
escal | +0.006 |
iste | +0.006 |
apo | +0.006 |
bang | +0.006 |
Neg logit contributions | |
Blessing | -0.007 |
WN | -0.007 |
Gutenberg | -0.007 |
advertisement | -0.007 |
Vaugh | -0.007 |
Token | leave |
Token ID | 2666 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
erent | +0.536 |
escal | +0.504 |
iste | +0.486 |
apo | +0.486 |
bang | +0.484 |
Neg logit contributions | |
Blessing | -0.442 |
WN | -0.429 |
advertisement | -0.418 |
Gutenberg | -0.417 |
Vaugh | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
erent | +0.505 |
escal | +0.463 |
apo | +0.443 |
iste | +0.441 |
bang | +0.438 |
Neg logit contributions | |
Blessing | -0.719 |
WN | -0.702 |
advertisement | -0.692 |
Gutenberg | -0.686 |
Vaugh | -0.669 |
Token | OS |
Token ID | 7294 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
erent | +0.162 |
escal | +0.152 |
apo | +0.148 |
iste | +0.147 |
bang | +0.147 |
Neg logit contributions | |
Blessing | -0.118 |
WN | -0.114 |
advertisement | -0.111 |
Gutenberg | -0.111 |
Vaugh | -0.107 |
Token | HA |
Token ID | 7801 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
erent | +0.235 |
escal | +0.219 |
apo | +0.211 |
iste | +0.211 |
bang | +0.210 |
Neg logit contributions | |
Blessing | -0.241 |
WN | -0.234 |
advertisement | -0.229 |
Gutenberg | -0.229 |
Vaugh | -0.223 |
Token | ( |
Token ID | 357 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
Blessing | +0.662 |
WN | +0.643 |
advertisement | +0.631 |
Gutenberg | +0.626 |
Vaugh | +0.606 |
Neg logit contributions | |
erent | -0.606 |
escal | -0.561 |
apo | -0.542 |
iste | -0.538 |
bang | -0.537 |
Token | Occup |
Token ID | 47658 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
erent | +0.015 |
escal | +0.014 |
iste | +0.013 |
apo | +0.013 |
bang | +0.013 |
Neg logit contributions | |
Blessing | -0.017 |
WN | -0.016 |
advertisement | -0.016 |
Gutenberg | -0.016 |
Vaugh | -0.015 |
Token | ational |
Token ID | 864 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
erent | +1.667 |
escal | +1.560 |
iste | +1.510 |
apo | +1.503 |
bang | +1.484 |
Neg logit contributions | |
Blessing | -1.488 |
WN | -1.446 |
advertisement | -1.409 |
Gutenberg | -1.405 |
Vaugh | -1.375 |
Token | Health |
Token ID | 3893 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Blessing | +0.157 |
WN | +0.153 |
advertisement | +0.149 |
Gutenberg | +0.149 |
Vaugh | +0.145 |
Neg logit contributions | |
erent | -0.172 |
escal | -0.162 |
iste | -0.156 |
apo | -0.154 |
bang | -0.154 |
Token | and |
Token ID | 290 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
erent | +0.457 |
escal | +0.426 |
iste | +0.410 |
apo | +0.408 |
bang | +0.406 |
Neg logit contributions | |
Blessing | -0.531 |
WN | -0.518 |
Gutenberg | -0.509 |
advertisement | -0.508 |
Vaugh | -0.495 |
Token | Safety |
Token ID | 11233 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
erent | +0.011 |
escal | +0.010 |
iste | +0.010 |
apo | +0.010 |
bang | +0.010 |
Neg logit contributions | |
Blessing | -0.010 |
WN | -0.010 |
advertisement | -0.010 |
Gutenberg | -0.010 |
Vaugh | -0.010 |
Token | Administration |
Token ID | 8694 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
Blessing | +0.163 |
WN | +0.158 |
advertisement | +0.155 |
Gutenberg | +0.152 |
Vaugh | +0.149 |
Neg logit contributions | |
erent | -0.170 |
escal | -0.158 |
apo | -0.153 |
iste | -0.152 |
bang | -0.152 |
Token | 's |
Token ID | 338 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
Blessing | +0.225 |
WN | +0.222 |
advertisement | +0.219 |
Gutenberg | +0.216 |
Majesty | +0.206 |
Neg logit contributions | |
erent | -0.131 |
escal | -0.119 |
apo | -0.114 |
iste | -0.113 |
bang | -0.111 |
Token | products |
Token ID | 3186 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Blessing | +0.154 |
WN | +0.151 |
advertisement | +0.148 |
Gutenberg | +0.146 |
Vaugh | +0.140 |
Neg logit contributions | |
erent | -0.151 |
escal | -0.141 |
iste | -0.136 |
apo | -0.134 |
bang | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Blessing | +0.403 |
WN | +0.391 |
Gutenberg | +0.384 |
advertisement | +0.384 |
Vaugh | +0.354 |
Neg logit contributions | |
erent | -0.450 |
escal | -0.416 |
apo | -0.411 |
iste | -0.400 |
bang | -0.399 |
Token | services |
Token ID | 2594 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
erent | +0.036 |
escal | +0.033 |
bang | +0.032 |
iste | +0.031 |
apo | +0.031 |
Neg logit contributions | |
Blessing | -0.059 |
WN | -0.058 |
advertisement | -0.057 |
Gutenberg | -0.057 |
Vaugh | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Blessing | +0.565 |
WN | +0.553 |
advertisement | +0.548 |
Gutenberg | +0.541 |
Majesty | +0.513 |
Neg logit contributions | |
erent | -0.367 |
escal | -0.334 |
apo | -0.321 |
bang | -0.315 |
iste | -0.315 |
Token | Thank |
Token ID | 6952 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
erent | +0.311 |
escal | +0.294 |
apo | +0.284 |
iste | +0.282 |
bang | +0.282 |
Neg logit contributions | |
Blessing | -0.234 |
WN | -0.228 |
advertisement | -0.223 |
Gutenberg | -0.221 |
Vaugh | -0.217 |
Token | you |
Token ID | 345 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
erent | +1.170 |
escal | +1.061 |
apo | +1.008 |
iste | +1.005 |
bang | +0.999 |
Neg logit contributions | |
Blessing | -1.975 |
WN | -1.931 |
advertisement | -1.898 |
Gutenberg | -1.896 |
Vaugh | -1.841 |
Token | for |
Token ID | 329 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
erent | +0.071 |
escal | +0.065 |
apo | +0.062 |
iste | +0.062 |
bang | +0.062 |
Neg logit contributions | |
Blessing | -0.098 |
WN | -0.096 |
advertisement | -0.095 |
Gutenberg | -0.094 |
Vaugh | -0.090 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
erent | +0.042 |
escal | +0.038 |
iste | +0.037 |
apo | +0.037 |
bang | +0.036 |
Neg logit contributions | |
Blessing | -0.067 |
WN | -0.066 |
advertisement | -0.065 |
Gutenberg | -0.065 |
Vaugh | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
erent | +0.595 |
escal | +0.539 |
apo | +0.513 |
iste | +0.506 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -1.039 |
WN | -1.025 |
advertisement | -1.004 |
Gutenberg | -0.998 |
Vaugh | -0.959 |
Token | An |
Token ID | 1052 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
erent | +0.258 |
escal | +0.246 |
bang | +0.236 |
iste | +0.236 |
apo | +0.235 |
Neg logit contributions | |
Blessing | -0.195 |
WN | -0.190 |
advertisement | -0.187 |
Gutenberg | -0.186 |
Vaugh | -0.183 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
erent | +0.237 |
escal | +0.222 |
apo | +0.214 |
iste | +0.211 |
bang | +0.211 |
Neg logit contributions | |
Blessing | -0.218 |
WN | -0.209 |
Gutenberg | -0.205 |
advertisement | -0.203 |
Vaugh | -0.198 |
Token | United |
Token ID | 1578 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
erent | +0.567 |
escal | +0.528 |
apo | +0.508 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.598 |
WN | -0.582 |
advertisement | -0.569 |
Gutenberg | -0.568 |
Vaugh | -0.553 |
Token | States |
Token ID | 1829 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
erent | +0.838 |
escal | +0.793 |
apo | +0.769 |
iste | +0.769 |
bang | +0.766 |
Neg logit contributions | |
Blessing | -0.512 |
WN | -0.494 |
advertisement | -0.481 |
Gutenberg | -0.478 |
Vaugh | -0.462 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
erent | +0.565 |
escal | +0.527 |
apo | +0.511 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.524 |
WN | -0.507 |
Gutenberg | -0.496 |
advertisement | -0.493 |
Vaugh | -0.481 |
Token | 83 |
Token ID | 5999 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
erent | +0.635 |
escal | +0.592 |
apo | +0.569 |
iste | +0.568 |
bang | +0.565 |
Neg logit contributions | |
Blessing | -0.637 |
WN | -0.620 |
advertisement | -0.606 |
Gutenberg | -0.604 |
Vaugh | -0.587 |
Token | Posts |
Token ID | 12043 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
erent | +0.454 |
escal | +0.428 |
apo | +0.416 |
iste | +0.412 |
bang | +0.412 |
Neg logit contributions | |
Blessing | -0.302 |
WN | -0.291 |
advertisement | -0.280 |
Gutenberg | -0.280 |
Vaugh | -0.263 |
Token | Last |
Token ID | 4586 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
erent | +1.669 |
escal | +1.557 |
iste | +1.514 |
apo | +1.500 |
bang | +1.498 |
Neg logit contributions | |
Blessing | -1.359 |
WN | -1.343 |
advertisement | -1.330 |
Gutenberg | -1.292 |
Vaugh | -1.285 |
Token | Edited |
Token ID | 34212 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
erent | +1.737 |
escal | +1.652 |
apo | +1.605 |
iste | +1.604 |
bang | +1.596 |
Neg logit contributions | |
Blessing | -0.805 |
WN | -0.773 |
Gutenberg | -0.739 |
advertisement | -0.737 |
Vaugh | -0.688 |
Token | : |
Token ID | 25 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
erent | +0.766 |
escal | +0.710 |
apo | +0.684 |
iste | +0.677 |
bang | +0.671 |
Neg logit contributions | |
Blessing | -0.883 |
WN | -0.858 |
advertisement | -0.843 |
Gutenberg | -0.832 |
Majesty | -0.788 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
erent | +0.102 |
escal | +0.095 |
apo | +0.093 |
bang | +0.090 |
iste | +0.089 |
Neg logit contributions | |
Blessing | -0.117 |
WN | -0.114 |
advertisement | -0.112 |
Gutenberg | -0.111 |
Majesty | -0.105 |
Token | - |
Token ID | 12 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
erent | +0.441 |
escal | +0.409 |
apo | +0.396 |
iste | +0.394 |
bang | +0.386 |
Neg logit contributions | |
Blessing | -0.429 |
WN | -0.416 |
Gutenberg | -0.406 |
advertisement | -0.405 |
Vaugh | -0.384 |
Token | neoliberal |
Token ID | 31972 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Blessing | +0.074 |
WN | +0.071 |
Gutenberg | +0.070 |
advertisement | +0.070 |
Vaugh | +0.068 |
Neg logit contributions | |
erent | -0.061 |
escal | -0.057 |
apo | -0.055 |
bang | -0.054 |
iste | -0.054 |
Token | model |
Token ID | 2746 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Blessing | +0.201 |
WN | +0.194 |
Gutenberg | +0.193 |
advertisement | +0.190 |
Vaugh | +0.184 |
Neg logit contributions | |
erent | -0.168 |
escal | -0.155 |
apo | -0.151 |
bang | -0.148 |
iste | -0.147 |
Token | only |
Token ID | 691 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
erent | +0.585 |
escal | +0.544 |
apo | +0.524 |
bang | +0.520 |
iste | +0.520 |
Neg logit contributions | |
Blessing | -0.618 |
WN | -0.601 |
advertisement | -0.590 |
Gutenberg | -0.588 |
Vaugh | -0.569 |
Token | after |
Token ID | 706 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
erent | +0.315 |
escal | +0.292 |
apo | +0.281 |
iste | +0.280 |
bang | +0.279 |
Neg logit contributions | |
Blessing | -0.343 |
WN | -0.333 |
Gutenberg | -0.327 |
advertisement | -0.326 |
Vaugh | -0.316 |
Token | heter |
Token ID | 14445 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
Blessing | +0.149 |
WN | +0.144 |
Gutenberg | +0.142 |
advertisement | +0.141 |
Vaugh | +0.137 |
Neg logit contributions | |
erent | -0.132 |
escal | -0.122 |
apo | -0.118 |
iste | -0.118 |
bang | -0.117 |
Token | odox |
Token ID | 11430 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
erent | +0.153 |
escal | +0.139 |
apo | +0.132 |
iste | +0.132 |
bang | +0.131 |
Neg logit contributions | |
Blessing | -0.260 |
WN | -0.254 |
advertisement | -0.250 |
Gutenberg | -0.249 |
Vaugh | -0.244 |
Token | policies |
Token ID | 4788 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
erent | +1.447 |
escal | +1.343 |
iste | +1.290 |
apo | +1.289 |
bang | +1.279 |
Neg logit contributions | |
Blessing | -1.634 |
WN | -1.591 |
advertisement | -1.561 |
Gutenberg | -1.555 |
Vaugh | -1.518 |
Token | , |
Token ID | 11 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
Blessing | +0.285 |
WN | +0.276 |
Gutenberg | +0.270 |
advertisement | +0.269 |
Vaugh | +0.261 |
Neg logit contributions | |
erent | -0.276 |
escal | -0.252 |
apo | -0.248 |
bang | -0.246 |
iste | -0.244 |
Token | which |
Token ID | 543 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
erent | +0.130 |
escal | +0.119 |
apo | +0.115 |
bang | +0.114 |
iste | +0.113 |
Neg logit contributions | |
Blessing | -0.168 |
WN | -0.162 |
Gutenberg | -0.160 |
advertisement | -0.160 |
Vaugh | -0.155 |
Token | he |
Token ID | 339 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
erent | +0.109 |
escal | +0.101 |
bang | +0.098 |
apo | +0.098 |
iste | +0.098 |
Neg logit contributions | |
Blessing | -0.117 |
WN | -0.113 |
Gutenberg | -0.112 |
advertisement | -0.110 |
Vaugh | -0.108 |
Token | campaigned |
Token ID | 32853 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Blessing | +0.192 |
WN | +0.187 |
Gutenberg | +0.183 |
advertisement | +0.182 |
Vaugh | +0.177 |
Neg logit contributions | |
erent | -0.205 |
escal | -0.190 |
apo | -0.184 |
bang | -0.182 |
iste | -0.181 |
Token | also |
Token ID | 635 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
erent | +0.273 |
escal | +0.254 |
apo | +0.246 |
iste | +0.245 |
bang | +0.243 |
Neg logit contributions | |
Blessing | -0.233 |
WN | -0.227 |
advertisement | -0.223 |
Gutenberg | -0.221 |
Vaugh | -0.214 |
Token | had |
Token ID | 550 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
erent | +0.306 |
escal | +0.285 |
apo | +0.276 |
iste | +0.275 |
bang | +0.272 |
Neg logit contributions | |
Blessing | -0.267 |
WN | -0.259 |
advertisement | -0.254 |
Gutenberg | -0.253 |
Vaugh | -0.244 |
Token | trials |
Token ID | 9867 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
erent | +0.547 |
escal | +0.509 |
apo | +0.490 |
iste | +0.489 |
bang | +0.486 |
Neg logit contributions | |
Blessing | -0.592 |
WN | -0.576 |
advertisement | -0.564 |
Gutenberg | -0.562 |
Vaugh | -0.548 |
Token | at |
Token ID | 379 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
Blessing | +0.165 |
WN | +0.161 |
advertisement | +0.158 |
Gutenberg | +0.157 |
Vaugh | +0.153 |
Neg logit contributions | |
erent | -0.148 |
escal | -0.137 |
apo | -0.132 |
iste | -0.131 |
bang | -0.131 |
Token | FC |
Token ID | 10029 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Blessing | +0.130 |
WN | +0.126 |
advertisement | +0.123 |
Gutenberg | +0.123 |
Vaugh | +0.119 |
Neg logit contributions | |
erent | -0.143 |
escal | -0.134 |
apo | -0.129 |
iste | -0.129 |
bang | -0.128 |
Token | Ing |
Token ID | 17589 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Blessing | +0.144 |
WN | +0.139 |
advertisement | +0.136 |
Gutenberg | +0.135 |
Vaugh | +0.132 |
Neg logit contributions | |
erent | -0.173 |
escal | -0.162 |
apo | -0.157 |
iste | -0.156 |
bang | -0.156 |
Token | ol |
Token ID | 349 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
erent | +1.482 |
escal | +1.383 |
apo | +1.330 |
iste | +1.327 |
bang | +1.321 |
Neg logit contributions | |
Blessing | -1.567 |
WN | -1.526 |
advertisement | -1.490 |
Gutenberg | -1.488 |
Vaugh | -1.446 |
Token | stadt |
Token ID | 38863 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
Blessing | +0.211 |
WN | +0.207 |
Gutenberg | +0.204 |
advertisement | +0.203 |
Vaugh | +0.198 |
Neg logit contributions | |
erent | -0.097 |
escal | -0.087 |
bang | -0.080 |
iste | -0.079 |
apo | -0.078 |
Token | 04 |
Token ID | 8702 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Blessing | +0.261 |
WN | +0.254 |
advertisement | +0.249 |
Gutenberg | +0.249 |
Vaugh | +0.242 |
Neg logit contributions | |
erent | -0.208 |
escal | -0.192 |
apo | -0.184 |
iste | -0.184 |
bang | -0.183 |
Token | , |
Token ID | 11 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
erent | +0.268 |
escal | +0.248 |
apo | +0.238 |
iste | +0.237 |
bang | +0.236 |
Neg logit contributions | |
Blessing | -0.336 |
WN | -0.328 |
advertisement | -0.322 |
Gutenberg | -0.320 |
Vaugh | -0.312 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Blessing | +0.100 |
WN | +0.097 |
advertisement | +0.095 |
Gutenberg | +0.094 |
Vaugh | +0.092 |
Neg logit contributions | |
erent | -0.111 |
escal | -0.104 |
apo | -0.100 |
iste | -0.100 |
bang | -0.100 |
Token | 's |
Token ID | 338 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Blessing | +0.314 |
WN | +0.309 |
advertisement | +0.305 |
Gutenberg | +0.301 |
Majesty | +0.286 |
Neg logit contributions | |
erent | -0.183 |
escal | -0.166 |
apo | -0.160 |
iste | -0.159 |
bang | -0.155 |
Token | products |
Token ID | 3186 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Blessing | +0.159 |
WN | +0.156 |
advertisement | +0.153 |
Gutenberg | +0.150 |
Vaugh | +0.143 |
Neg logit contributions | |
erent | -0.158 |
escal | -0.148 |
iste | -0.144 |
apo | -0.141 |
bang | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Blessing | +0.465 |
WN | +0.452 |
advertisement | +0.445 |
Gutenberg | +0.444 |
Vaugh | +0.408 |
Neg logit contributions | |
erent | -0.522 |
escal | -0.483 |
apo | -0.478 |
iste | -0.465 |
bang | -0.464 |
Token | services |
Token ID | 2594 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
erent | +0.024 |
escal | +0.022 |
bang | +0.021 |
iste | +0.021 |
apo | +0.021 |
Neg logit contributions | |
Blessing | -0.039 |
WN | -0.038 |
advertisement | -0.037 |
Gutenberg | -0.037 |
Vaugh | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
Blessing | +0.475 |
WN | +0.466 |
advertisement | +0.462 |
Gutenberg | +0.455 |
Majesty | +0.431 |
Neg logit contributions | |
erent | -0.309 |
escal | -0.281 |
apo | -0.270 |
bang | -0.265 |
iste | -0.265 |
Token | Thank |
Token ID | 6952 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
erent | +0.274 |
escal | +0.258 |
apo | +0.250 |
iste | +0.249 |
bang | +0.248 |
Neg logit contributions | |
Blessing | -0.202 |
WN | -0.196 |
advertisement | -0.191 |
Gutenberg | -0.190 |
Vaugh | -0.185 |
Token | you |
Token ID | 345 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
erent | +1.138 |
escal | +1.031 |
apo | +0.980 |
iste | +0.977 |
bang | +0.972 |
Neg logit contributions | |
Blessing | -1.900 |
WN | -1.857 |
advertisement | -1.827 |
Gutenberg | -1.824 |
Vaugh | -1.766 |
Token | for |
Token ID | 329 |
Feature activation | +8.90e-04 |
Pos logit contributions | |
erent | +0.037 |
escal | +0.034 |
apo | +0.033 |
bang | +0.033 |
iste | +0.033 |
Neg logit contributions | |
Blessing | -0.051 |
WN | -0.050 |
advertisement | -0.049 |
Gutenberg | -0.049 |
Vaugh | -0.046 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Blessing | +0.003 |
WN | +0.003 |
advertisement | +0.003 |
Gutenberg | +0.003 |
Vaugh | +0.002 |
Neg logit contributions | |
erent | -0.002 |
escal | -0.002 |
iste | -0.001 |
apo | -0.001 |
bang | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
erent | +0.585 |
escal | +0.530 |
apo | +0.505 |
iste | +0.498 |
bang | +0.496 |
Neg logit contributions | |
Blessing | -1.016 |
WN | -1.002 |
advertisement | -0.982 |
Gutenberg | -0.976 |
Vaugh | -0.936 |
Token | An |
Token ID | 1052 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
erent | +0.251 |
escal | +0.239 |
iste | +0.230 |
bang | +0.229 |
apo | +0.229 |
Neg logit contributions | |
Blessing | -0.185 |
WN | -0.180 |
advertisement | -0.176 |
Gutenberg | -0.175 |
Vaugh | -0.172 |
Token | 's |
Token ID | 338 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
Blessing | +0.306 |
WN | +0.302 |
advertisement | +0.298 |
Gutenberg | +0.294 |
Majesty | +0.280 |
Neg logit contributions | |
erent | -0.179 |
escal | -0.162 |
apo | -0.156 |
iste | -0.155 |
bang | -0.151 |
Token | products |
Token ID | 3186 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Blessing | +0.103 |
WN | +0.102 |
advertisement | +0.099 |
Gutenberg | +0.098 |
Vaugh | +0.093 |
Neg logit contributions | |
erent | -0.102 |
escal | -0.095 |
iste | -0.093 |
apo | -0.091 |
bang | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
Blessing | +0.447 |
WN | +0.434 |
Gutenberg | +0.426 |
advertisement | +0.425 |
Vaugh | +0.392 |
Neg logit contributions | |
erent | -0.498 |
escal | -0.461 |
apo | -0.454 |
iste | -0.442 |
bang | -0.441 |
Token | services |
Token ID | 2594 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
erent | +0.065 |
escal | +0.060 |
bang | +0.057 |
iste | +0.057 |
apo | +0.056 |
Neg logit contributions | |
Blessing | -0.106 |
WN | -0.103 |
advertisement | -0.101 |
Gutenberg | -0.101 |
Vaugh | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Blessing | +0.444 |
WN | +0.435 |
advertisement | +0.431 |
Gutenberg | +0.425 |
Majesty | +0.403 |
Neg logit contributions | |
erent | -0.288 |
escal | -0.261 |
apo | -0.251 |
bang | -0.247 |
iste | -0.247 |
Token | Thank |
Token ID | 6952 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
erent | +0.356 |
escal | +0.336 |
apo | +0.325 |
iste | +0.323 |
bang | +0.322 |
Neg logit contributions | |
Blessing | -0.268 |
WN | -0.260 |
advertisement | -0.254 |
Gutenberg | -0.252 |
Vaugh | -0.247 |
Token | you |
Token ID | 345 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
erent | +1.131 |
escal | +1.024 |
apo | +0.974 |
iste | +0.971 |
bang | +0.965 |
Neg logit contributions | |
Blessing | -1.900 |
WN | -1.857 |
advertisement | -1.826 |
Gutenberg | -1.824 |
Vaugh | -1.769 |
Token | for |
Token ID | 329 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
erent | +0.113 |
escal | +0.104 |
apo | +0.100 |
bang | +0.099 |
iste | +0.099 |
Neg logit contributions | |
Blessing | -0.157 |
WN | -0.155 |
advertisement | -0.152 |
Gutenberg | -0.151 |
Vaugh | -0.144 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
erent | +0.061 |
escal | +0.055 |
iste | +0.053 |
apo | +0.053 |
bang | +0.052 |
Neg logit contributions | |
Blessing | -0.096 |
WN | -0.094 |
advertisement | -0.093 |
Gutenberg | -0.092 |
Vaugh | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
erent | +0.611 |
escal | +0.553 |
apo | +0.527 |
iste | +0.520 |
bang | +0.518 |
Neg logit contributions | |
Blessing | -1.063 |
WN | -1.048 |
advertisement | -1.026 |
Gutenberg | -1.021 |
Vaugh | -0.980 |
Token | An |
Token ID | 1052 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
erent | +0.371 |
escal | +0.353 |
iste | +0.339 |
bang | +0.339 |
apo | +0.338 |
Neg logit contributions | |
Blessing | -0.275 |
WN | -0.268 |
advertisement | -0.263 |
Gutenberg | -0.262 |
Vaugh | -0.257 |
Token | � |
Token ID | 564 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
Blessing | +0.165 |
WN | +0.160 |
advertisement | +0.158 |
Gutenberg | +0.158 |
Vaugh | +0.152 |
Neg logit contributions | |
erent | -0.147 |
escal | -0.134 |
bang | -0.130 |
apo | -0.129 |
iste | -0.129 |
Token | � |
Token ID | 250 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
erent | +0.138 |
escal | +0.131 |
iste | +0.129 |
apo | +0.128 |
bang | +0.126 |
Neg logit contributions | |
Blessing | -0.069 |
WN | -0.066 |
advertisement | -0.065 |
Gutenberg | -0.063 |
Vaugh | -0.060 |
Token | may |
Token ID | 11261 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
erent | +0.132 |
escal | +0.121 |
iste | +0.118 |
apo | +0.118 |
bang | +0.117 |
Neg logit contributions | |
Blessing | -0.145 |
WN | -0.142 |
advertisement | -0.140 |
Gutenberg | -0.137 |
Vaugh | -0.133 |
Token | be |
Token ID | 307 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
erent | +0.384 |
escal | +0.353 |
apo | +0.344 |
iste | +0.342 |
bang | +0.341 |
Neg logit contributions | |
Blessing | -0.398 |
WN | -0.387 |
advertisement | -0.381 |
Gutenberg | -0.375 |
Vaugh | -0.365 |
Token | fue |
Token ID | 37911 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
erent | +0.009 |
escal | +0.008 |
apo | +0.008 |
iste | +0.008 |
bang | +0.008 |
Neg logit contributions | |
Blessing | -0.010 |
WN | -0.009 |
advertisement | -0.009 |
Gutenberg | -0.009 |
Vaugh | -0.009 |
Token | lling |
Token ID | 2680 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
erent | +0.240 |
escal | +0.221 |
iste | +0.212 |
bang | +0.209 |
apo | +0.209 |
Neg logit contributions | |
Blessing | -0.375 |
WN | -0.367 |
advertisement | -0.362 |
Gutenberg | -0.361 |
Vaugh | -0.347 |
Token | xen |
Token ID | 27132 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
erent | +1.352 |
escal | +1.251 |
apo | +1.198 |
iste | +1.197 |
bang | +1.190 |
Neg logit contributions | |
Blessing | -1.671 |
WN | -1.629 |
advertisement | -1.598 |
Gutenberg | -1.594 |
Vaugh | -1.554 |
Token | ophobic |
Token ID | 23468 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
Blessing | +0.210 |
WN | +0.204 |
advertisement | +0.201 |
Gutenberg | +0.200 |
Vaugh | +0.195 |
Neg logit contributions | |
erent | -0.166 |
escal | -0.153 |
bang | -0.146 |
apo | -0.146 |
iste | -0.146 |
Token | sentiment |
Token ID | 15598 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
Blessing | +0.188 |
WN | +0.182 |
advertisement | +0.180 |
Gutenberg | +0.179 |
Vaugh | +0.174 |
Neg logit contributions | |
erent | -0.160 |
escal | -0.146 |
apo | -0.142 |
bang | -0.142 |
iste | -0.140 |
Token | � |
Token ID | 447 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
Blessing | +0.041 |
WN | +0.040 |
advertisement | +0.040 |
Gutenberg | +0.039 |
Vaugh | +0.038 |
Neg logit contributions | |
erent | -0.032 |
escal | -0.030 |
bang | -0.029 |
apo | -0.029 |
iste | -0.029 |
Token | � |
Token ID | 251 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
erent | +0.070 |
escal | +0.066 |
apo | +0.064 |
iste | +0.064 |
bang | +0.064 |
Neg logit contributions | |
Blessing | -0.036 |
WN | -0.035 |
advertisement | -0.034 |
Gutenberg | -0.034 |
Vaugh | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
erent | +0.066 |
escal | +0.062 |
apo | +0.059 |
iste | +0.059 |
bang | +0.059 |
Neg logit contributions | |
Blessing | -0.067 |
WN | -0.065 |
advertisement | -0.064 |
Gutenberg | -0.064 |
Vaugh | -0.062 |
Token | significant |
Token ID | 2383 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Blessing | +0.052 |
WN | +0.051 |
advertisement | +0.050 |
Gutenberg | +0.050 |
Vaugh | +0.048 |
Neg logit contributions | |
erent | -0.048 |
escal | -0.044 |
apo | -0.043 |
iste | -0.042 |
bang | -0.042 |
Token | public |
Token ID | 1171 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
erent | +0.331 |
escal | +0.306 |
apo | +0.296 |
iste | +0.292 |
bang | +0.291 |
Neg logit contributions | |
Blessing | -0.363 |
WN | -0.352 |
advertisement | -0.345 |
Gutenberg | -0.345 |
Vaugh | -0.334 |
Token | support |
Token ID | 1104 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
erent | +0.045 |
escal | +0.042 |
apo | +0.041 |
iste | +0.040 |
bang | +0.040 |
Neg logit contributions | |
Blessing | -0.041 |
WN | -0.040 |
advertisement | -0.039 |
Gutenberg | -0.039 |
Vaugh | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
erent | +0.876 |
escal | +0.807 |
apo | +0.770 |
iste | +0.766 |
bang | +0.761 |
Neg logit contributions | |
Blessing | -1.258 |
WN | -1.229 |
advertisement | -1.207 |
Gutenberg | -1.200 |
Vaugh | -1.172 |
Token | renegoti |
Token ID | 48312 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
erent | +0.231 |
escal | +0.214 |
apo | +0.207 |
iste | +0.204 |
bang | +0.204 |
Neg logit contributions | |
Blessing | -0.247 |
WN | -0.239 |
Gutenberg | -0.234 |
advertisement | -0.234 |
Vaugh | -0.226 |
Token | ating |
Token ID | 803 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
erent | +1.618 |
escal | +1.520 |
apo | +1.466 |
iste | +1.465 |
bang | +1.457 |
Neg logit contributions | |
Blessing | -1.399 |
WN | -1.358 |
advertisement | -1.324 |
Gutenberg | -1.322 |
Vaugh | -1.290 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
erent | +0.145 |
escal | +0.135 |
apo | +0.130 |
iste | +0.129 |
bang | +0.129 |
Neg logit contributions | |
Blessing | -0.157 |
WN | -0.153 |
advertisement | -0.149 |
Gutenberg | -0.149 |
Vaugh | -0.145 |
Token | UK |
Token ID | 3482 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
erent | +0.094 |
escal | +0.086 |
apo | +0.084 |
iste | +0.083 |
bang | +0.082 |
Neg logit contributions | |
Blessing | -0.102 |
WN | -0.098 |
Gutenberg | -0.096 |
advertisement | -0.096 |
Vaugh | -0.092 |
Token | 's |
Token ID | 338 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
erent | +0.140 |
escal | +0.126 |
apo | +0.119 |
iste | +0.118 |
bang | +0.117 |
Neg logit contributions | |
Blessing | -0.275 |
WN | -0.270 |
advertisement | -0.265 |
Gutenberg | -0.265 |
Vaugh | -0.259 |
Token | EU |
Token ID | 4576 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
erent | +0.264 |
escal | +0.247 |
apo | +0.240 |
iste | +0.239 |
bang | +0.238 |
Neg logit contributions | |
Blessing | -0.198 |
WN | -0.190 |
advertisement | -0.185 |
Gutenberg | -0.185 |
Vaugh | -0.177 |
Token | June |
Token ID | 2795 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
erent | +1.457 |
escal | +1.359 |
apo | +1.312 |
iste | +1.303 |
bang | +1.297 |
Neg logit contributions | |
Blessing | -1.458 |
WN | -1.410 |
advertisement | -1.378 |
Gutenberg | -1.378 |
Vaugh | -1.337 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
erent | +0.617 |
escal | +0.575 |
apo | +0.557 |
iste | +0.549 |
bang | +0.547 |
Neg logit contributions | |
Blessing | -0.587 |
WN | -0.566 |
Gutenberg | -0.554 |
advertisement | -0.553 |
Vaugh | -0.535 |
Token | Canada |
Token ID | 3340 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
erent | +0.260 |
escal | +0.242 |
apo | +0.234 |
iste | +0.232 |
bang | +0.231 |
Neg logit contributions | |
Blessing | -0.263 |
WN | -0.254 |
Gutenberg | -0.249 |
advertisement | -0.248 |
Vaugh | -0.242 |
Token | 16 |
Token ID | 1467 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
erent | +0.739 |
escal | +0.689 |
apo | +0.670 |
iste | +0.661 |
bang | +0.657 |
Neg logit contributions | |
Blessing | -0.666 |
WN | -0.640 |
Gutenberg | -0.628 |
advertisement | -0.621 |
Vaugh | -0.606 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
erent | +0.109 |
escal | +0.102 |
apo | +0.098 |
iste | +0.097 |
bang | +0.097 |
Neg logit contributions | |
Blessing | -0.106 |
WN | -0.103 |
advertisement | -0.100 |
Gutenberg | -0.100 |
Vaugh | -0.097 |
Token | Posts |
Token ID | 12043 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
erent | +0.596 |
escal | +0.561 |
apo | +0.545 |
iste | +0.542 |
bang | +0.539 |
Neg logit contributions | |
Blessing | -0.408 |
WN | -0.392 |
Gutenberg | -0.378 |
advertisement | -0.378 |
Vaugh | -0.361 |
Token | # |
Token ID | 1303 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
erent | +1.619 |
escal | +1.516 |
iste | +1.474 |
apo | +1.463 |
bang | +1.457 |
Neg logit contributions | |
Blessing | -1.332 |
WN | -1.319 |
advertisement | -1.309 |
Gutenberg | -1.272 |
Vaugh | -1.262 |
Token | 14 |
Token ID | 1415 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
erent | +0.858 |
escal | +0.793 |
iste | +0.750 |
bang | +0.749 |
apo | +0.746 |
Neg logit contributions | |
WN | -1.015 |
Blessing | -1.008 |
advertisement | -1.005 |
Gutenberg | -0.936 |
Majesty | -0.886 |
Token | On |
Token ID | 1550 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
erent | +0.437 |
escal | +0.412 |
apo | +0.399 |
iste | +0.397 |
bang | +0.395 |
Neg logit contributions | |
Blessing | -0.344 |
WN | -0.330 |
Gutenberg | -0.321 |
advertisement | -0.320 |
Vaugh | -0.309 |
Token | September |
Token ID | 2693 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
erent | +0.382 |
escal | +0.355 |
apo | +0.341 |
iste | +0.339 |
bang | +0.339 |
Neg logit contributions | |
Blessing | -0.392 |
WN | -0.377 |
Gutenberg | -0.374 |
advertisement | -0.369 |
Vaugh | -0.354 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
erent | +0.645 |
escal | +0.605 |
iste | +0.585 |
bang | +0.579 |
apo | +0.579 |
Neg logit contributions | |
Blessing | -0.615 |
WN | -0.611 |
advertisement | -0.591 |
Gutenberg | -0.589 |
Vaugh | -0.579 |
Token | forest |
Token ID | 8222 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
erent | +0.012 |
escal | +0.011 |
apo | +0.010 |
iste | +0.010 |
bang | +0.010 |
Neg logit contributions | |
Blessing | -0.015 |
WN | -0.014 |
advertisement | -0.014 |
Gutenberg | -0.014 |
Vaugh | -0.014 |
Token | ed |
Token ID | 276 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
erent | +0.462 |
escal | +0.434 |
apo | +0.421 |
bang | +0.418 |
iste | +0.418 |
Neg logit contributions | |
Blessing | -0.393 |
WN | -0.380 |
advertisement | -0.372 |
Gutenberg | -0.370 |
Vaugh | -0.358 |
Token | landscape |
Token ID | 10747 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
erent | +0.145 |
escal | +0.134 |
apo | +0.132 |
iste | +0.130 |
bang | +0.129 |
Neg logit contributions | |
Blessing | -0.167 |
WN | -0.161 |
Gutenberg | -0.158 |
advertisement | -0.157 |
Vaugh | -0.154 |
Token | inter |
Token ID | 987 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
erent | +0.448 |
escal | +0.413 |
apo | +0.399 |
iste | +0.396 |
bang | +0.393 |
Neg logit contributions | |
Blessing | -0.521 |
WN | -0.505 |
advertisement | -0.497 |
Gutenberg | -0.494 |
Vaugh | -0.480 |
Token | l |
Token ID | 75 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
erent | +0.196 |
escal | +0.179 |
apo | +0.170 |
iste | +0.170 |
bang | +0.169 |
Neg logit contributions | |
Blessing | -0.316 |
WN | -0.309 |
advertisement | -0.304 |
Gutenberg | -0.303 |
Vaugh | -0.296 |
Token | aced |
Token ID | 2286 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Blessing | +0.027 |
WN | +0.027 |
advertisement | +0.026 |
Gutenberg | +0.026 |
Vaugh | +0.025 |
Neg logit contributions | |
erent | -0.022 |
escal | -0.020 |
iste | -0.020 |
apo | -0.020 |
bang | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
erent | +1.282 |
escal | +1.180 |
iste | +1.136 |
bang | +1.116 |
apo | +1.115 |
Neg logit contributions | |
Blessing | -1.722 |
WN | -1.685 |
Gutenberg | -1.647 |
advertisement | -1.645 |
Vaugh | -1.606 |
Token | c |
Token ID | 269 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
erent | +0.227 |
escal | +0.208 |
apo | +0.201 |
iste | +0.199 |
bang | +0.198 |
Neg logit contributions | |
Blessing | -0.302 |
WN | -0.292 |
Gutenberg | -0.288 |
advertisement | -0.286 |
Vaugh | -0.281 |
Token | ree |
Token ID | 631 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Blessing | +0.070 |
WN | +0.068 |
advertisement | +0.067 |
Gutenberg | +0.066 |
Vaugh | +0.064 |
Neg logit contributions | |
erent | -0.089 |
escal | -0.083 |
apo | -0.081 |
iste | -0.080 |
bang | -0.080 |
Token | ks |
Token ID | 591 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Blessing | +0.312 |
WN | +0.303 |
advertisement | +0.295 |
Gutenberg | +0.291 |
Vaugh | +0.277 |
Neg logit contributions | |
erent | -0.521 |
escal | -0.490 |
iste | -0.478 |
bang | -0.475 |
apo | -0.475 |
Token | and |
Token ID | 290 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
Blessing | +0.277 |
WN | +0.269 |
advertisement | +0.265 |
Gutenberg | +0.263 |
Vaugh | +0.256 |
Neg logit contributions | |
erent | -0.234 |
escal | -0.214 |
iste | -0.206 |
apo | -0.206 |
bang | -0.204 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
erent | +0.590 |
escal | +0.541 |
iste | +0.514 |
apo | +0.512 |
bang | +0.509 |
Neg logit contributions | |
Blessing | -0.938 |
WN | -0.918 |
advertisement | -0.904 |
Gutenberg | -0.899 |
Vaugh | -0.881 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
erent | +0.029 |
escal | +0.027 |
iste | +0.026 |
apo | +0.026 |
bang | +0.026 |
Neg logit contributions | |
Blessing | -0.032 |
WN | -0.031 |
Gutenberg | -0.031 |
advertisement | -0.031 |
Vaugh | -0.030 |
Token | hat |
Token ID | 6877 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
erent | +0.035 |
escal | +0.033 |
apo | +0.031 |
iste | +0.031 |
bang | +0.031 |
Neg logit contributions | |
Blessing | -0.037 |
WN | -0.036 |
Gutenberg | -0.035 |
advertisement | -0.035 |
Vaugh | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | +1.35e-04 |
Pos logit contributions | |
Blessing | +0.131 |
WN | +0.127 |
Gutenberg | +0.124 |
advertisement | +0.124 |
Vaugh | +0.119 |
Neg logit contributions | |
erent | -0.117 |
escal | -0.108 |
apo | -0.104 |
bang | -0.103 |
iste | -0.102 |
Token | tr |
Token ID | 2213 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
Blessing | +0.001 |
WN | +0.001 |
advertisement | +0.001 |
Gutenberg | +0.001 |
Vaugh | +0.001 |
Neg logit contributions | |
erent | -0.000 |
escal | -0.000 |
iste | -0.000 |
apo | -0.000 |
bang | -0.000 |
Token | ick |
Token ID | 624 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
erent | +0.214 |
escal | +0.197 |
iste | +0.188 |
apo | +0.187 |
bang | +0.185 |
Neg logit contributions | |
Blessing | -0.254 |
WN | -0.248 |
advertisement | -0.242 |
Gutenberg | -0.238 |
Vaugh | -0.233 |
Token | is |
Token ID | 318 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
erent | +1.439 |
escal | +1.342 |
iste | +1.291 |
apo | +1.289 |
bang | +1.286 |
Neg logit contributions | |
Blessing | -1.558 |
WN | -1.519 |
advertisement | -1.486 |
Gutenberg | -1.482 |
Vaugh | -1.447 |
Token | a |
Token ID | 257 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
erent | +0.143 |
escal | +0.133 |
apo | +0.128 |
iste | +0.128 |
bang | +0.126 |
Neg logit contributions | |
Blessing | -0.155 |
WN | -0.150 |
advertisement | -0.147 |
Gutenberg | -0.147 |
Vaugh | -0.143 |
Token | 106 |
Token ID | 15696 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
erent | +0.111 |
escal | +0.103 |
apo | +0.099 |
iste | +0.098 |
bang | +0.097 |
Neg logit contributions | |
Blessing | -0.130 |
WN | -0.126 |
Gutenberg | -0.124 |
advertisement | -0.123 |
Vaugh | -0.119 |
Token | – |
Token ID | 1906 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Blessing | +0.158 |
WN | +0.154 |
advertisement | +0.151 |
Gutenberg | +0.151 |
Vaugh | +0.146 |
Neg logit contributions | |
erent | -0.126 |
escal | -0.116 |
apo | -0.111 |
iste | -0.111 |
bang | -0.109 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
erent | +0.466 |
escal | +0.436 |
iste | +0.421 |
apo | +0.420 |
bang | +0.417 |
Neg logit contributions | |
Blessing | -0.422 |
WN | -0.412 |
advertisement | -0.403 |
Gutenberg | -0.399 |
Vaugh | -0.385 |
Token |
|
Token ID | 198 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
Blessing | +0.108 |
WN | +0.107 |
advertisement | +0.105 |
Gutenberg | +0.102 |
Majesty | +0.096 |
Neg logit contributions | |
erent | -0.113 |
escal | -0.104 |
apo | -0.101 |
iste | -0.101 |
bang | -0.099 |
Token | pur |
Token ID | 14225 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
erent | +0.142 |
escal | +0.132 |
apo | +0.127 |
iste | +0.127 |
bang | +0.126 |
Neg logit contributions | |
Blessing | -0.136 |
WN | -0.134 |
advertisement | -0.132 |
Gutenberg | -0.129 |
Vaugh | -0.125 |
Token | ak |
Token ID | 461 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Blessing | +0.158 |
WN | +0.154 |
advertisement | +0.151 |
Gutenberg | +0.151 |
Vaugh | +0.147 |
Neg logit contributions | |
erent | -0.121 |
escal | -0.111 |
iste | -0.106 |
apo | -0.106 |
bang | -0.105 |
Token | ushi |
Token ID | 17731 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
erent | +0.045 |
escal | +0.042 |
apo | +0.040 |
iste | +0.040 |
bang | +0.040 |
Neg logit contributions | |
Blessing | -0.050 |
WN | -0.049 |
advertisement | -0.048 |
Gutenberg | -0.048 |
Vaugh | -0.046 |
Token | Profile |
Token ID | 13118 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
erent | +0.114 |
escal | +0.106 |
apo | +0.102 |
iste | +0.102 |
bang | +0.101 |
Neg logit contributions | |
Blessing | -0.116 |
WN | -0.113 |
advertisement | -0.111 |
Gutenberg | -0.110 |
Vaugh | -0.107 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
erent | +0.738 |
escal | +0.693 |
iste | +0.672 |
apo | +0.671 |
bang | +0.669 |
Neg logit contributions | |
Blessing | -0.602 |
WN | -0.585 |
advertisement | -0.572 |
Gutenberg | -0.568 |
Vaugh | -0.552 |
Token | August |
Token ID | 2932 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
erent | +1.498 |
escal | +1.397 |
apo | +1.347 |
iste | +1.341 |
bang | +1.335 |
Neg logit contributions | |
Blessing | -1.496 |
WN | -1.451 |
advertisement | -1.420 |
Gutenberg | -1.415 |
Vaugh | -1.374 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
erent | +0.566 |
escal | +0.529 |
apo | +0.509 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.561 |
WN | -0.543 |
advertisement | -0.531 |
Gutenberg | -0.531 |
Vaugh | -0.516 |
Token | United |
Token ID | 1578 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
erent | +0.369 |
escal | +0.344 |
apo | +0.332 |
iste | +0.330 |
bang | +0.328 |
Neg logit contributions | |
Blessing | -0.377 |
WN | -0.365 |
Gutenberg | -0.357 |
advertisement | -0.356 |
Vaugh | -0.347 |
Token | States |
Token ID | 1829 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
erent | +0.560 |
escal | +0.529 |
iste | +0.515 |
apo | +0.515 |
bang | +0.511 |
Neg logit contributions | |
Blessing | -0.370 |
WN | -0.357 |
advertisement | -0.356 |
Gutenberg | -0.349 |
Vaugh | -0.337 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
erent | +0.484 |
escal | +0.451 |
apo | +0.436 |
iste | +0.433 |
bang | +0.431 |
Neg logit contributions | |
Blessing | -0.451 |
WN | -0.436 |
Gutenberg | -0.426 |
advertisement | -0.424 |
Vaugh | -0.413 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
erent | +0.566 |
escal | +0.529 |
apo | +0.509 |
iste | +0.507 |
bang | +0.504 |
Neg logit contributions | |
Blessing | -0.561 |
WN | -0.543 |
advertisement | -0.531 |
Gutenberg | -0.531 |
Vaugh | -0.516 |
Token | United |
Token ID | 1578 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
erent | +0.369 |
escal | +0.344 |
apo | +0.332 |
iste | +0.330 |
bang | +0.328 |
Neg logit contributions | |
Blessing | -0.377 |
WN | -0.365 |
Gutenberg | -0.357 |
advertisement | -0.356 |
Vaugh | -0.347 |
Token | States |
Token ID | 1829 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
erent | +0.560 |
escal | +0.529 |
iste | +0.515 |
apo | +0.515 |
bang | +0.511 |
Neg logit contributions | |
Blessing | -0.370 |
WN | -0.357 |
advertisement | -0.356 |
Gutenberg | -0.349 |
Vaugh | -0.337 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
erent | +0.484 |
escal | +0.451 |
apo | +0.436 |
iste | +0.433 |
bang | +0.431 |
Neg logit contributions | |
Blessing | -0.451 |
WN | -0.436 |
Gutenberg | -0.426 |
advertisement | -0.424 |
Vaugh | -0.413 |
Token | 240 |
Token ID | 16102 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
erent | +0.850 |
escal | +0.796 |
apo | +0.769 |
iste | +0.768 |
bang | +0.764 |
Neg logit contributions | |
Blessing | -0.713 |
WN | -0.693 |
advertisement | -0.674 |
Gutenberg | -0.673 |
Vaugh | -0.651 |
Token | Posts |
Token ID | 12043 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
erent | +0.993 |
escal | +0.939 |
iste | +0.914 |
apo | +0.910 |
bang | +0.905 |
Neg logit contributions | |
Blessing | -0.653 |
WN | -0.631 |
advertisement | -0.603 |
Gutenberg | -0.603 |
Vaugh | -0.578 |
Token | # |
Token ID | 1303 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
erent | +1.637 |
escal | +1.537 |
iste | +1.491 |
apo | +1.487 |
bang | +1.480 |
Neg logit contributions | |
Blessing | -1.256 |
WN | -1.226 |
advertisement | -1.210 |
Gutenberg | -1.195 |
Vaugh | -1.178 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
erent | +0.847 |
escal | +0.789 |
apo | +0.759 |
iste | +0.759 |
bang | +0.755 |
Neg logit contributions | |
Blessing | -0.830 |
WN | -0.811 |
advertisement | -0.791 |
Gutenberg | -0.786 |
Vaugh | -0.762 |
Token | Happy |
Token ID | 14628 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
erent | +0.779 |
escal | +0.732 |
apo | +0.707 |
iste | +0.706 |
bang | +0.702 |
Neg logit contributions | |
Blessing | -0.647 |
WN | -0.627 |
advertisement | -0.611 |
Gutenberg | -0.610 |
Vaugh | -0.591 |
Token | it |
Token ID | 340 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
erent | +0.993 |
escal | +0.929 |
iste | +0.895 |
apo | +0.894 |
bang | +0.892 |
Neg logit contributions | |
Blessing | -0.909 |
WN | -0.885 |
advertisement | -0.866 |
Gutenberg | -0.864 |
Vaugh | -0.838 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
erent | +0.146 |
escal | +0.134 |
apo | +0.128 |
iste | +0.128 |
bang | +0.127 |
Neg logit contributions | |
Blessing | -0.201 |
WN | -0.196 |
advertisement | -0.192 |
Gutenberg | -0.192 |
Vaugh | -0.187 |
Token | result |
Token ID | 1255 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
erent | +0.232 |
escal | +0.219 |
apo | +0.213 |
iste | +0.212 |
bang | +0.212 |
Neg logit contributions | |
Blessing | -0.164 |
WN | -0.157 |
advertisement | -0.154 |
Gutenberg | -0.153 |
Vaugh | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
erent | +0.255 |
escal | +0.230 |
iste | +0.219 |
apo | +0.218 |
bang | +0.216 |
Neg logit contributions | |
Blessing | -0.434 |
WN | -0.424 |
advertisement | -0.417 |
Gutenberg | -0.416 |
Vaugh | -0.409 |
Token | a |
Token ID | 257 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
erent | +0.229 |
escal | +0.215 |
iste | +0.207 |
apo | +0.206 |
bang | +0.205 |
Neg logit contributions | |
Blessing | -0.221 |
WN | -0.212 |
Gutenberg | -0.208 |
advertisement | -0.208 |
Vaugh | -0.203 |
Token | National |
Token ID | 2351 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
erent | +0.104 |
escal | +0.097 |
apo | +0.094 |
iste | +0.093 |
bang | +0.093 |
Neg logit contributions | |
Blessing | -0.123 |
WN | -0.119 |
advertisement | -0.117 |
Gutenberg | -0.116 |
Vaugh | -0.112 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
Blessing | +0.143 |
WN | +0.138 |
Gutenberg | +0.136 |
advertisement | +0.135 |
Vaugh | +0.130 |
Neg logit contributions | |
erent | -0.150 |
escal | -0.141 |
apo | -0.135 |
iste | -0.135 |
bang | -0.133 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Blessing | +0.010 |
WN | +0.010 |
Gutenberg | +0.010 |
advertisement | +0.010 |
Vaugh | +0.009 |
Neg logit contributions | |
erent | -0.010 |
escal | -0.010 |
apo | -0.009 |
iste | -0.009 |
bang | -0.009 |
Token | poll |
Token ID | 3278 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
erent | +1.434 |
escal | +1.336 |
apo | +1.284 |
iste | +1.283 |
bang | +1.278 |
Neg logit contributions | |
Blessing | -1.489 |
WN | -1.449 |
advertisement | -1.417 |
Gutenberg | -1.415 |
Vaugh | -1.378 |
Token | found |
Token ID | 1043 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
erent | +0.521 |
escal | +0.486 |
apo | +0.466 |
iste | +0.466 |
bang | +0.465 |
Neg logit contributions | |
Blessing | -0.541 |
WN | -0.530 |
advertisement | -0.522 |
Gutenberg | -0.517 |
Vaugh | -0.502 |
Token | that |
Token ID | 326 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
Blessing | +0.450 |
WN | +0.436 |
advertisement | +0.426 |
Gutenberg | +0.424 |
Vaugh | +0.411 |
Neg logit contributions | |
erent | -0.454 |
escal | -0.428 |
apo | -0.412 |
iste | -0.410 |
bang | -0.409 |
Token | 59 |
Token ID | 7863 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
erent | +0.184 |
escal | +0.173 |
apo | +0.167 |
iste | +0.165 |
bang | +0.164 |
Neg logit contributions | |
Blessing | -0.203 |
WN | -0.196 |
advertisement | -0.193 |
Gutenberg | -0.192 |
Vaugh | -0.186 |
Token | percent |
Token ID | 1411 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Blessing | +0.465 |
WN | +0.453 |
Gutenberg | +0.444 |
advertisement | +0.444 |
Vaugh | +0.433 |
Neg logit contributions | |
erent | -0.352 |
escal | -0.323 |
apo | -0.309 |
iste | -0.309 |
bang | -0.307 |
Token | is |
Token ID | 318 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Blessing | +0.084 |
WN | +0.082 |
advertisement | +0.081 |
Gutenberg | +0.080 |
Vaugh | +0.078 |
Neg logit contributions | |
erent | -0.063 |
escal | -0.059 |
apo | -0.057 |
iste | -0.055 |
bang | -0.055 |
Token | transgender |
Token ID | 10637 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
erent | +0.068 |
escal | +0.064 |
apo | +0.062 |
bang | +0.061 |
iste | +0.061 |
Neg logit contributions | |
Blessing | -0.072 |
WN | -0.070 |
advertisement | -0.069 |
Gutenberg | -0.068 |
Vaugh | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
Blessing | +0.276 |
WN | +0.269 |
advertisement | +0.264 |
Gutenberg | +0.263 |
Vaugh | +0.252 |
Neg logit contributions | |
erent | -0.250 |
escal | -0.234 |
apo | -0.224 |
bang | -0.224 |
iste | -0.222 |
Token | society |
Token ID | 3592 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
erent | +0.136 |
escal | +0.128 |
apo | +0.123 |
iste | +0.123 |
bang | +0.122 |
Neg logit contributions | |
Blessing | -0.133 |
WN | -0.128 |
advertisement | -0.126 |
Gutenberg | -0.125 |
Vaugh | -0.121 |
Token | inst |
Token ID | 916 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Blessing | +0.815 |
advertisement | +0.776 |
WN | +0.774 |
Gutenberg | +0.752 |
Vaugh | +0.738 |
Neg logit contributions | |
erent | -0.765 |
escal | -0.731 |
apo | -0.707 |
iste | -0.686 |
bang | -0.681 |
Token | ills |
Token ID | 2171 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
erent | +0.709 |
escal | +0.673 |
iste | +0.655 |
apo | +0.655 |
bang | +0.653 |
Neg logit contributions | |
Blessing | -0.355 |
WN | -0.339 |
advertisement | -0.330 |
Gutenberg | -0.327 |
Vaugh | -0.312 |
Token | in |
Token ID | 287 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Blessing | +1.313 |
advertisement | +1.264 |
WN | +1.240 |
Gutenberg | +1.205 |
Vaugh | +1.173 |
Neg logit contributions | |
erent | -1.253 |
escal | -1.191 |
apo | -1.175 |
bang | -1.146 |
iste | -1.137 |
Token | them |
Token ID | 606 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
erent | +0.047 |
escal | +0.045 |
apo | +0.043 |
iste | +0.043 |
bang | +0.043 |
Neg logit contributions | |
Blessing | -0.036 |
WN | -0.034 |
advertisement | -0.034 |
Gutenberg | -0.033 |
Vaugh | -0.032 |
Token | rules |
Token ID | 3173 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
erent | +0.033 |
escal | +0.031 |
apo | +0.030 |
iste | +0.029 |
bang | +0.029 |
Neg logit contributions | |
Blessing | -0.033 |
WN | -0.032 |
advertisement | -0.032 |
Gutenberg | -0.031 |
Vaugh | -0.030 |
Token | about |
Token ID | 546 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
Blessing | +0.133 |
WN | +0.128 |
advertisement | +0.126 |
Gutenberg | +0.125 |
Vaugh | +0.121 |
Neg logit contributions | |
erent | -0.132 |
escal | -0.123 |
apo | -0.120 |
iste | -0.119 |
bang | -0.118 |
Token | one |
Token ID | 530 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
erent | +0.161 |
escal | +0.150 |
apo | +0.146 |
iste | +0.144 |
bang | +0.143 |
Neg logit contributions | |
Blessing | -0.155 |
WN | -0.150 |
advertisement | -0.148 |
Gutenberg | -0.145 |
Vaugh | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
Blessing | +0.394 |
WN | +0.383 |
advertisement | +0.373 |
Gutenberg | +0.371 |
Vaugh | +0.360 |
Neg logit contributions | |
erent | -0.423 |
escal | -0.396 |
apo | -0.382 |
iste | -0.381 |
bang | -0.378 |
Token |
|
Token ID | 198 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Blessing | +0.170 |
WN | +0.168 |
advertisement | +0.164 |
Gutenberg | +0.160 |
Majesty | +0.150 |
Neg logit contributions | |
erent | -0.175 |
escal | -0.163 |
apo | -0.157 |
iste | -0.157 |
bang | -0.154 |
Token | GPU |
Token ID | 33346 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
Blessing | +0.170 |
WN | +0.167 |
advertisement | +0.163 |
Gutenberg | +0.161 |
Vaugh | +0.156 |
Neg logit contributions | |
erent | -0.173 |
escal | -0.162 |
apo | -0.155 |
iste | -0.155 |
bang | -0.154 |
Token | : |
Token ID | 25 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Blessing | +0.233 |
WN | +0.228 |
advertisement | +0.223 |
Gutenberg | +0.223 |
Vaugh | +0.218 |
Neg logit contributions | |
erent | -0.192 |
escal | -0.178 |
apo | -0.171 |
iste | -0.170 |
bang | -0.170 |
Token | AMD |
Token ID | 10324 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Blessing | +0.433 |
WN | +0.418 |
advertisement | +0.407 |
Gutenberg | +0.405 |
Vaugh | +0.392 |
Neg logit contributions | |
erent | -0.567 |
escal | -0.533 |
apo | -0.516 |
iste | -0.515 |
bang | -0.513 |
Token | Radeon |
Token ID | 13082 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Blessing | +1.226 |
WN | +1.172 |
advertisement | +1.149 |
Gutenberg | +1.136 |
Vaugh | +1.107 |
Neg logit contributions | |
erent | -1.381 |
escal | -1.298 |
apo | -1.254 |
bang | -1.251 |
iste | -1.246 |
Token | HD |
Token ID | 5572 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Blessing | +1.254 |
WN | +1.213 |
advertisement | +1.175 |
Gutenberg | +1.173 |
Vaugh | +1.143 |
Neg logit contributions | |
erent | -1.433 |
escal | -1.347 |
apo | -1.305 |
bang | -1.299 |
iste | -1.290 |
Token | 78 |
Token ID | 8699 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Blessing | +0.769 |
WN | +0.750 |
advertisement | +0.731 |
Gutenberg | +0.731 |
Vaugh | +0.713 |
Neg logit contributions | |
erent | -0.673 |
escal | -0.624 |
apo | -0.598 |
bang | -0.591 |
iste | -0.589 |
Token | 70 |
Token ID | 2154 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
Blessing | +0.253 |
WN | +0.247 |
advertisement | +0.240 |
Gutenberg | +0.238 |
Vaugh | +0.232 |
Neg logit contributions | |
erent | -0.314 |
escal | -0.293 |
apo | -0.285 |
iste | -0.283 |
bang | -0.283 |
Token | - |
Token ID | 532 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Blessing | +0.240 |
WN | +0.233 |
advertisement | +0.228 |
Gutenberg | +0.227 |
Vaugh | +0.221 |
Neg logit contributions | |
erent | -0.236 |
escal | -0.220 |
apo | -0.212 |
iste | -0.211 |
bang | -0.210 |
Token | 1100 |
Token ID | 36566 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Blessing | +0.472 |
WN | +0.459 |
advertisement | +0.446 |
Gutenberg | +0.444 |
Vaugh | +0.430 |
Neg logit contributions | |
erent | -0.536 |
escal | -0.502 |
apo | -0.485 |
iste | -0.484 |
bang | -0.482 |
Token | himself |
Token ID | 2241 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Blessing | +0.306 |
WN | +0.299 |
Gutenberg | +0.293 |
advertisement | +0.293 |
Vaugh | +0.284 |
Neg logit contributions | |
erent | -0.247 |
escal | -0.229 |
apo | -0.219 |
bang | -0.218 |
iste | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
Blessing | +0.448 |
WN | +0.438 |
advertisement | +0.431 |
Gutenberg | +0.429 |
Vaugh | +0.419 |
Neg logit contributions | |
erent | -0.293 |
escal | -0.268 |
apo | -0.255 |
iste | -0.255 |
bang | -0.254 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
Blessing | +0.004 |
WN | +0.004 |
advertisement | +0.004 |
Gutenberg | +0.004 |
Vaugh | +0.004 |
Neg logit contributions | |
erent | -0.004 |
escal | -0.004 |
apo | -0.004 |
iste | -0.004 |
bang | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Blessing | +0.107 |
WN | +0.105 |
advertisement | +0.103 |
Gutenberg | +0.101 |
Majesty | +0.095 |
Neg logit contributions | |
erent | -0.110 |
escal | -0.102 |
apo | -0.099 |
iste | -0.098 |
bang | -0.098 |
Token | My |
Token ID | 3666 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
Blessing | +0.032 |
WN | +0.032 |
advertisement | +0.031 |
Gutenberg | +0.031 |
Vaugh | +0.029 |
Neg logit contributions | |
erent | -0.032 |
escal | -0.030 |
iste | -0.029 |
apo | -0.029 |
bang | -0.029 |
Token | advice |
Token ID | 5608 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Blessing | +0.136 |
WN | +0.132 |
Gutenberg | +0.130 |
advertisement | +0.129 |
Vaugh | +0.126 |
Neg logit contributions | |
erent | -0.123 |
escal | -0.115 |
apo | -0.110 |
iste | -0.110 |
bang | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Blessing | +1.081 |
WN | +1.049 |
advertisement | +1.031 |
Gutenberg | +1.027 |
Vaugh | +0.997 |
Neg logit contributions | |
erent | -1.064 |
escal | -0.990 |
iste | -0.953 |
apo | -0.952 |
bang | -0.951 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Blessing | +0.246 |
WN | +0.239 |
Gutenberg | +0.235 |
advertisement | +0.234 |
Vaugh | +0.228 |
Neg logit contributions | |
erent | -0.210 |
escal | -0.195 |
iste | -0.188 |
bang | -0.187 |
apo | -0.187 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
Blessing | +0.507 |
WN | +0.496 |
advertisement | +0.487 |
Gutenberg | +0.486 |
Vaugh | +0.475 |
Neg logit contributions | |
erent | -0.307 |
escal | -0.280 |
apo | -0.266 |
iste | -0.265 |
bang | -0.263 |
Token | is |
Token ID | 318 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Blessing | +0.139 |
WN | +0.136 |
advertisement | +0.133 |
Gutenberg | +0.132 |
Vaugh | +0.129 |
Neg logit contributions | |
erent | -0.134 |
escal | -0.125 |
apo | -0.120 |
iste | -0.120 |
bang | -0.119 |
Token | simply |
Token ID | 2391 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
erent | +0.032 |
escal | +0.029 |
apo | +0.028 |
iste | +0.028 |
bang | +0.028 |
Neg logit contributions | |
Blessing | -0.034 |
WN | -0.033 |
advertisement | -0.032 |
Gutenberg | -0.032 |
Vaugh | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
erent | +0.079 |
escal | +0.074 |
apo | +0.071 |
iste | +0.071 |
bang | +0.071 |
Neg logit contributions | |
Blessing | -0.080 |
WN | -0.078 |
advertisement | -0.076 |
Gutenberg | -0.076 |
Vaugh | -0.074 |
Token | company |
Token ID | 1664 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Blessing | +0.101 |
WN | +0.097 |
Gutenberg | +0.096 |
advertisement | +0.096 |
Vaugh | +0.093 |
Neg logit contributions | |
erent | -0.091 |
escal | -0.085 |
apo | -0.082 |
iste | -0.082 |
bang | -0.081 |
Token | 's |
Token ID | 338 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Blessing | +0.685 |
WN | +0.671 |
advertisement | +0.660 |
Gutenberg | +0.659 |
Vaugh | +0.646 |
Neg logit contributions | |
erent | -0.337 |
escal | -0.303 |
apo | -0.285 |
iste | -0.285 |
bang | -0.283 |
Token | enroll |
Token ID | 14627 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
erent | +0.051 |
escal | +0.048 |
apo | +0.046 |
iste | +0.046 |
bang | +0.046 |
Neg logit contributions | |
Blessing | -0.053 |
WN | -0.051 |
Gutenberg | -0.050 |
advertisement | -0.050 |
Vaugh | -0.049 |
Token | ments |
Token ID | 902 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
erent | +0.326 |
escal | +0.306 |
apo | +0.296 |
iste | +0.295 |
bang | +0.294 |
Neg logit contributions | |
Blessing | -0.284 |
WN | -0.276 |
advertisement | -0.270 |
Gutenberg | -0.269 |
Vaugh | -0.260 |
Token | allegedly |
Token ID | 7910 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
erent | +0.043 |
escal | +0.040 |
bang | +0.039 |
apo | +0.039 |
iste | +0.039 |
Neg logit contributions | |
Blessing | -0.038 |
WN | -0.037 |
Gutenberg | -0.036 |
advertisement | -0.036 |
Vaugh | -0.035 |
Token | involved |
Token ID | 2950 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Blessing | +0.915 |
WN | +0.883 |
Gutenberg | +0.872 |
advertisement | +0.864 |
Vaugh | +0.832 |
Neg logit contributions | |
erent | -1.187 |
escal | -1.105 |
bang | -1.080 |
apo | -1.077 |
iste | -1.059 |
Token | overriding |
Token ID | 44987 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
Blessing | +0.577 |
WN | +0.558 |
Gutenberg | +0.550 |
advertisement | +0.546 |
Vaugh | +0.534 |
Neg logit contributions | |
erent | -0.481 |
escal | -0.450 |
apo | -0.430 |
iste | -0.428 |
bang | -0.426 |
Token | a |
Token ID | 257 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
Blessing | +0.144 |
WN | +0.140 |
advertisement | +0.137 |
Gutenberg | +0.137 |
Vaugh | +0.132 |
Neg logit contributions | |
erent | -0.141 |
escal | -0.132 |
apo | -0.127 |
iste | -0.126 |
bang | -0.126 |
Token | system |
Token ID | 1080 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Blessing | +0.099 |
WN | +0.095 |
advertisement | +0.093 |
Gutenberg | +0.093 |
Vaugh | +0.090 |
Neg logit contributions | |
erent | -0.104 |
escal | -0.098 |
apo | -0.095 |
bang | -0.095 |
iste | -0.094 |
Token | designed |
Token ID | 3562 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Blessing | +0.072 |
WN | +0.069 |
advertisement | +0.068 |
Gutenberg | +0.068 |
Vaugh | +0.066 |
Neg logit contributions | |
erent | -0.063 |
escal | -0.059 |
apo | -0.057 |
bang | -0.056 |
iste | -0.056 |
Token | as |
Token ID | 355 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
erent | +0.016 |
escal | +0.015 |
apo | +0.015 |
bang | +0.015 |
iste | +0.015 |
Neg logit contributions | |
Blessing | -0.019 |
WN | -0.019 |
advertisement | -0.018 |
Gutenberg | -0.018 |
Vaugh | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
erent | +0.073 |
escal | +0.068 |
iste | +0.065 |
apo | +0.065 |
bang | +0.065 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.079 |
advertisement | -0.077 |
Gutenberg | -0.077 |
Vaugh | -0.075 |
Token | possibly |
Token ID | 5457 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
erent | +0.018 |
escal | +0.017 |
apo | +0.016 |
bang | +0.016 |
iste | +0.016 |
Neg logit contributions | |
Blessing | -0.027 |
WN | -0.026 |
advertisement | -0.025 |
Gutenberg | -0.025 |
Vaugh | -0.025 |
Token | remedy |
Token ID | 21210 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Blessing | +0.493 |
WN | +0.482 |
advertisement | +0.472 |
Gutenberg | +0.471 |
Vaugh | +0.456 |
Neg logit contributions | |
erent | -0.401 |
escal | -0.369 |
apo | -0.355 |
iste | -0.353 |
bang | -0.351 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Blessing | +0.731 |
WN | +0.713 |
advertisement | +0.698 |
Gutenberg | +0.697 |
Vaugh | +0.677 |
Neg logit contributions | |
erent | -0.633 |
escal | -0.586 |
apo | -0.563 |
iste | -0.562 |
bang | -0.561 |
Token | combat |
Token ID | 5249 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Blessing | +0.036 |
WN | +0.035 |
advertisement | +0.035 |
Gutenberg | +0.034 |
Vaugh | +0.033 |
Neg logit contributions | |
erent | -0.030 |
escal | -0.028 |
iste | -0.027 |
bang | -0.027 |
apo | -0.027 |
Token | losses |
Token ID | 9089 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Blessing | +1.603 |
WN | +1.561 |
advertisement | +1.540 |
Gutenberg | +1.531 |
Vaugh | +1.461 |
Neg logit contributions | |
erent | -1.422 |
escal | -1.315 |
iste | -1.270 |
apo | -1.269 |
bang | -1.264 |
Token | from |
Token ID | 422 |
Feature activation | -4.84e-03 |
Pos logit contributions | |
erent | +0.078 |
escal | +0.073 |
iste | +0.070 |
apo | +0.070 |
bang | +0.070 |
Neg logit contributions | |
Blessing | -0.081 |
WN | -0.079 |
Gutenberg | -0.077 |
advertisement | -0.077 |
Vaugh | -0.074 |
Token | customers |
Token ID | 4297 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
erent | +0.010 |
escal | +0.010 |
apo | +0.009 |
iste | +0.009 |
bang | +0.009 |
Neg logit contributions | |
Blessing | -0.013 |
WN | -0.013 |
Gutenberg | -0.012 |
advertisement | -0.012 |
Vaugh | -0.012 |
Token | who |
Token ID | 508 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
Blessing | +0.594 |
WN | +0.580 |
Gutenberg | +0.573 |
advertisement | +0.571 |
Vaugh | +0.547 |
Neg logit contributions | |
erent | -0.505 |
escal | -0.466 |
apo | -0.457 |
iste | -0.453 |
bang | -0.443 |
Token | are |
Token ID | 389 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Blessing | +0.194 |
WN | +0.190 |
Gutenberg | +0.187 |
advertisement | +0.184 |
Vaugh | +0.179 |
Neg logit contributions | |
erent | -0.180 |
escal | -0.167 |
apo | -0.163 |
iste | -0.162 |
bang | -0.159 |
Token | said |
Token ID | 531 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
erent | +0.562 |
escal | +0.529 |
apo | +0.511 |
iste | +0.511 |
bang | +0.508 |
Neg logit contributions | |
Blessing | -0.451 |
WN | -0.437 |
advertisement | -0.426 |
Gutenberg | -0.425 |
Vaugh | -0.412 |
Token | , |
Token ID | 11 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
erent | +0.336 |
escal | +0.311 |
iste | +0.299 |
apo | +0.299 |
bang | +0.297 |
Neg logit contributions | |
Blessing | -0.403 |
WN | -0.392 |
advertisement | -0.385 |
Gutenberg | -0.384 |
Vaugh | -0.374 |
Token | � |
Token ID | 564 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
erent | +0.020 |
escal | +0.019 |
apo | +0.018 |
iste | +0.018 |
bang | +0.018 |
Neg logit contributions | |
Blessing | -0.017 |
WN | -0.017 |
Gutenberg | -0.016 |
advertisement | -0.016 |
Vaugh | -0.016 |
Token | � |
Token ID | 250 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
Blessing | +0.027 |
WN | +0.025 |
advertisement | +0.025 |
Gutenberg | +0.024 |
Vaugh | +0.023 |
Neg logit contributions | |
erent | -0.053 |
escal | -0.050 |
iste | -0.049 |
apo | -0.049 |
bang | -0.049 |
Token | He |
Token ID | 1544 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
erent | +0.232 |
escal | +0.216 |
iste | +0.210 |
apo | +0.209 |
bang | +0.208 |
Neg logit contributions | |
Blessing | -0.233 |
WN | -0.229 |
advertisement | -0.225 |
Gutenberg | -0.221 |
Vaugh | -0.214 |
Token | wants |
Token ID | 3382 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
erent | +0.216 |
escal | +0.199 |
apo | +0.192 |
iste | +0.191 |
bang | +0.190 |
Neg logit contributions | |
Blessing | -0.241 |
WN | -0.236 |
advertisement | -0.230 |
Gutenberg | -0.229 |
Vaugh | -0.222 |
Token | to |
Token ID | 284 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
Blessing | +0.173 |
WN | +0.169 |
advertisement | +0.165 |
Gutenberg | +0.165 |
Vaugh | +0.160 |
Neg logit contributions | |
erent | -0.172 |
escal | -0.160 |
apo | -0.154 |
iste | -0.154 |
bang | -0.153 |
Token | make |
Token ID | 787 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
erent | +0.080 |
escal | +0.074 |
apo | +0.072 |
iste | +0.072 |
bang | +0.071 |
Neg logit contributions | |
Blessing | -0.080 |
WN | -0.077 |
advertisement | -0.075 |
Gutenberg | -0.075 |
Vaugh | -0.072 |
Token | sure |
Token ID | 1654 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
erent | +0.055 |
escal | +0.052 |
apo | +0.051 |
iste | +0.051 |
bang | +0.050 |
Neg logit contributions | |
Blessing | -0.038 |
WN | -0.037 |
Gutenberg | -0.036 |
advertisement | -0.036 |
Vaugh | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
erent | +0.504 |
escal | +0.467 |
iste | +0.450 |
apo | +0.449 |
bang | +0.447 |
Neg logit contributions | |
Blessing | -0.576 |
WN | -0.560 |
advertisement | -0.549 |
Gutenberg | -0.548 |
Vaugh | -0.533 |
Token | any |
Token ID | 597 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Blessing | +0.060 |
WN | +0.058 |
Gutenberg | +0.057 |
advertisement | +0.057 |
Vaugh | +0.055 |
Neg logit contributions | |
erent | -0.053 |
escal | -0.049 |
iste | -0.048 |
apo | -0.048 |
bang | -0.048 |
Token | remains |
Token ID | 3793 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Blessing | +0.104 |
WN | +0.100 |
Gutenberg | +0.098 |
advertisement | +0.098 |
Vaugh | +0.094 |
Neg logit contributions | |
erent | -0.106 |
escal | -0.099 |
apo | -0.096 |
iste | -0.094 |
bang | -0.093 |
Token | an |
Token ID | 281 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Blessing | +0.036 |
WN | +0.034 |
advertisement | +0.034 |
Gutenberg | +0.033 |
Vaugh | +0.032 |
Neg logit contributions | |
erent | -0.035 |
escal | -0.033 |
apo | -0.031 |
iste | -0.031 |
bang | -0.031 |
Token | EU |
Token ID | 4576 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Blessing | +0.044 |
WN | +0.043 |
advertisement | +0.042 |
Gutenberg | +0.042 |
Vaugh | +0.040 |
Neg logit contributions | |
erent | -0.040 |
escal | -0.037 |
iste | -0.035 |
apo | -0.035 |
bang | -0.035 |
Token | member |
Token ID | 2888 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Blessing | +0.605 |
WN | +0.585 |
advertisement | +0.573 |
Gutenberg | +0.569 |
Vaugh | +0.545 |
Neg logit contributions | |
erent | -0.610 |
escal | -0.576 |
apo | -0.547 |
bang | -0.544 |
iste | -0.541 |
Token | or |
Token ID | 393 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
Blessing | +0.364 |
WN | +0.353 |
advertisement | +0.347 |
Gutenberg | +0.346 |
Vaugh | +0.333 |
Neg logit contributions | |
erent | -0.303 |
escal | -0.281 |
apo | -0.269 |
bang | -0.266 |
iste | -0.263 |
Token | not |
Token ID | 407 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Blessing | +0.019 |
WN | +0.018 |
Gutenberg | +0.018 |
advertisement | +0.017 |
Vaugh | +0.017 |
Neg logit contributions | |
erent | -0.020 |
escal | -0.019 |
apo | -0.018 |
iste | -0.018 |
bang | -0.018 |
Token | ," |
Token ID | 553 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
Blessing | +0.167 |
WN | +0.163 |
advertisement | +0.160 |
Gutenberg | +0.160 |
Vaugh | +0.155 |
Neg logit contributions | |
erent | -0.128 |
escal | -0.118 |
apo | -0.113 |
iste | -0.112 |
bang | -0.112 |
Token | she |
Token ID | 673 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
erent | +0.161 |
escal | +0.150 |
iste | +0.145 |
apo | +0.144 |
bang | +0.144 |
Neg logit contributions | |
Blessing | -0.164 |
WN | -0.160 |
advertisement | -0.157 |
Gutenberg | -0.156 |
Vaugh | -0.152 |
Token | said |
Token ID | 531 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
erent | +0.344 |
escal | +0.326 |
apo | +0.316 |
iste | +0.314 |
bang | +0.314 |
Neg logit contributions | |
Blessing | -0.201 |
WN | -0.193 |
advertisement | -0.187 |
Gutenberg | -0.187 |
Vaugh | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
erent | +0.278 |
escal | +0.255 |
apo | +0.243 |
iste | +0.242 |
bang | +0.241 |
Neg logit contributions | |
Blessing | -0.411 |
WN | -0.401 |
advertisement | -0.395 |
Gutenberg | -0.394 |
Vaugh | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
erent | +0.125 |
escal | +0.117 |
apo | +0.112 |
iste | +0.112 |
bang | +0.111 |
Neg logit contributions | |
Blessing | -0.148 |
WN | -0.146 |
advertisement | -0.142 |
Gutenberg | -0.142 |
Vaugh | -0.138 |
Token | online |
Token ID | 2691 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
erent | +0.121 |
escal | +0.112 |
apo | +0.108 |
iste | +0.108 |
bang | +0.107 |
Neg logit contributions | |
Blessing | -0.141 |
WN | -0.137 |
advertisement | -0.135 |
Gutenberg | -0.134 |
Vaugh | -0.130 |
Token | � |
Token ID | 447 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
erent | +0.059 |
escal | +0.055 |
apo | +0.053 |
iste | +0.053 |
bang | +0.052 |
Neg logit contributions | |
Blessing | -0.072 |
WN | -0.070 |
advertisement | -0.069 |
Gutenberg | -0.069 |
Vaugh | -0.067 |
Token | � |
Token ID | 251 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
erent | +0.109 |
escal | +0.103 |
apo | +0.100 |
iste | +0.100 |
bang | +0.100 |
Neg logit contributions | |
Blessing | -0.069 |
WN | -0.067 |
Gutenberg | -0.065 |
advertisement | -0.064 |
Vaugh | -0.062 |
Token | who |
Token ID | 508 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Blessing | +0.052 |
WN | +0.051 |
advertisement | +0.050 |
Gutenberg | +0.050 |
Vaugh | +0.048 |
Neg logit contributions | |
erent | -0.048 |
escal | -0.045 |
apo | -0.043 |
iste | -0.043 |
bang | -0.043 |
Token | sells |
Token ID | 16015 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Blessing | +0.249 |
WN | +0.242 |
advertisement | +0.237 |
Gutenberg | +0.236 |
Vaugh | +0.228 |
Neg logit contributions | |
erent | -0.248 |
escal | -0.231 |
apo | -0.224 |
iste | -0.223 |
bang | -0.221 |
Token | all |
Token ID | 477 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
Blessing | +0.555 |
WN | +0.538 |
advertisement | +0.529 |
Gutenberg | +0.527 |
Vaugh | +0.506 |
Neg logit contributions | |
erent | -0.556 |
escal | -0.519 |
apo | -0.503 |
iste | -0.497 |
bang | -0.490 |
Token | varieties |
Token ID | 20328 |
Feature activation | -2.19e-04 |
Pos logit contributions | |
Blessing | +0.162 |
WN | +0.158 |
Gutenberg | +0.156 |
advertisement | +0.155 |
Vaugh | +0.150 |
Neg logit contributions | |
erent | -0.124 |
escal | -0.114 |
apo | -0.109 |
iste | -0.109 |
bang | -0.107 |
Token | with |
Token ID | 351 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
erent | +0.000 |
escal | +0.000 |
apo | +0.000 |
iste | +0.000 |
bang | +0.000 |
Neg logit contributions | |
Blessing | -0.001 |
WN | -0.001 |
advertisement | -0.001 |
Gutenberg | -0.001 |
Vaugh | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
erent | +0.024 |
escal | +0.023 |
apo | +0.022 |
iste | +0.022 |
bang | +0.021 |
Neg logit contributions | |
Blessing | -0.028 |
WN | -0.027 |
Gutenberg | -0.027 |
advertisement | -0.027 |
Vaugh | -0.026 |
Token | intention |
Token ID | 6778 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Blessing | +0.016 |
WN | +0.016 |
Gutenberg | +0.016 |
advertisement | +0.016 |
Vaugh | +0.015 |
Neg logit contributions | |
erent | -0.016 |
escal | -0.015 |
apo | -0.014 |
iste | -0.014 |
bang | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Blessing | +0.356 |
WN | +0.345 |
Gutenberg | +0.336 |
advertisement | +0.335 |
Vaugh | +0.331 |
Neg logit contributions | |
erent | -0.328 |
escal | -0.304 |
bang | -0.293 |
apo | -0.292 |
iste | -0.291 |
Token | CG |
Token ID | 39816 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Blessing | +0.439 |
WN | +0.428 |
advertisement | +0.419 |
Gutenberg | +0.415 |
Vaugh | +0.403 |
Neg logit contributions | |
erent | -0.478 |
escal | -0.448 |
iste | -0.433 |
apo | -0.433 |
bang | -0.428 |
Token | section |
Token ID | 2665 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Blessing | +0.581 |
WN | +0.568 |
advertisement | +0.557 |
Gutenberg | +0.551 |
Vaugh | +0.539 |
Neg logit contributions | |
erent | -0.550 |
escal | -0.514 |
iste | -0.494 |
apo | -0.494 |
bang | -0.488 |
Token | ! |
Token ID | 0 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Blessing | +0.568 |
WN | +0.552 |
advertisement | +0.544 |
Gutenberg | +0.540 |
Vaugh | +0.522 |
Neg logit contributions | |
erent | -0.524 |
escal | -0.487 |
apo | -0.467 |
iste | -0.465 |
bang | -0.461 |
Token | ): |
Token ID | 2599 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Blessing | +0.360 |
WN | +0.350 |
advertisement | +0.342 |
Gutenberg | +0.340 |
Vaugh | +0.330 |
Neg logit contributions | |
erent | -0.386 |
escal | -0.362 |
apo | -0.348 |
iste | -0.348 |
bang | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Blessing | +0.290 |
WN | +0.282 |
advertisement | +0.276 |
Gutenberg | +0.276 |
Vaugh | +0.268 |
Neg logit contributions | |
erent | -0.266 |
escal | -0.248 |
apo | -0.238 |
iste | -0.238 |
bang | -0.236 |
Token |
|
Token ID | 198 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
Blessing | +0.247 |
WN | +0.241 |
advertisement | +0.238 |
Gutenberg | +0.231 |
Majesty | +0.217 |
Neg logit contributions | |
erent | -0.269 |
escal | -0.250 |
apo | -0.244 |
iste | -0.240 |
bang | -0.238 |
Token | _ |
Token ID | 62 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Blessing | +0.148 |
WN | +0.145 |
advertisement | +0.143 |
Gutenberg | +0.140 |
Vaugh | +0.136 |
Neg logit contributions | |
erent | -0.125 |
escal | -0.116 |
apo | -0.111 |
iste | -0.111 |
bang | -0.110 |
Token | P |
Token ID | 47 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Blessing | +0.530 |
WN | +0.518 |
advertisement | +0.509 |
Gutenberg | +0.507 |
Vaugh | +0.496 |
Neg logit contributions | |
erent | -0.345 |
escal | -0.316 |
apo | -0.300 |
iste | -0.300 |
bang | -0.298 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Blessing | +0.256 |
WN | +0.253 |
advertisement | +0.247 |
Gutenberg | +0.244 |
Vaugh | +0.229 |
Neg logit contributions | |
erent | -0.278 |
escal | -0.259 |
iste | -0.251 |
bang | -0.251 |
apo | -0.250 |
Token | Amount |
Token ID | 31264 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Blessing | +0.031 |
WN | +0.030 |
Gutenberg | +0.029 |
advertisement | +0.029 |
Vaugh | +0.028 |
Neg logit contributions | |
erent | -0.042 |
escal | -0.040 |
bang | -0.039 |
apo | -0.039 |
iste | -0.039 |
Token | (" |
Token ID | 5855 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Blessing | +0.033 |
WN | +0.032 |
advertisement | +0.032 |
Gutenberg | +0.032 |
Vaugh | +0.031 |
Neg logit contributions | |
erent | -0.031 |
escal | -0.029 |
apo | -0.028 |
iste | -0.028 |
bang | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Blessing | +0.264 |
WN | +0.258 |
advertisement | +0.254 |
Gutenberg | +0.252 |
Vaugh | +0.245 |
Neg logit contributions | |
erent | -0.199 |
escal | -0.184 |
apo | -0.176 |
iste | -0.176 |
bang | -0.173 |
Token | being |
Token ID | 852 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
erent | +0.099 |
escal | +0.091 |
apo | +0.088 |
iste | +0.088 |
bang | +0.087 |
Neg logit contributions | |
Blessing | -0.111 |
WN | -0.108 |
advertisement | -0.106 |
Gutenberg | -0.105 |
Vaugh | -0.103 |
Token | polite |
Token ID | 23507 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Blessing | +0.343 |
WN | +0.334 |
advertisement | +0.326 |
Gutenberg | +0.326 |
Vaugh | +0.317 |
Neg logit contributions | |
erent | -0.279 |
escal | -0.261 |
apo | -0.249 |
bang | -0.247 |
iste | -0.247 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
erent | +0.414 |
escal | +0.383 |
apo | +0.368 |
iste | +0.367 |
bang | +0.366 |
Neg logit contributions | |
Blessing | -0.496 |
WN | -0.484 |
advertisement | -0.474 |
Gutenberg | -0.472 |
Vaugh | -0.460 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
erent | +0.031 |
escal | +0.028 |
apo | +0.027 |
iste | +0.027 |
bang | +0.027 |
Neg logit contributions | |
Blessing | -0.033 |
WN | -0.032 |
advertisement | -0.031 |
Gutenberg | -0.031 |
Vaugh | -0.030 |
Token | � |
Token ID | 251 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
erent | +0.030 |
escal | +0.028 |
iste | +0.027 |
apo | +0.027 |
bang | +0.027 |
Neg logit contributions | |
Blessing | -0.021 |
WN | -0.020 |
advertisement | -0.020 |
Gutenberg | -0.019 |
Vaugh | -0.019 |
Token | U |
Token ID | 471 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
Blessing | +0.223 |
WN | +0.217 |
advertisement | +0.213 |
Gutenberg | +0.210 |
Vaugh | +0.205 |
Neg logit contributions | |
erent | -0.207 |
escal | -0.193 |
apo | -0.186 |
iste | -0.186 |
bang | -0.184 |
Token | em |
Token ID | 368 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
erent | +0.077 |
escal | +0.072 |
apo | +0.069 |
iste | +0.069 |
bang | +0.068 |
Neg logit contributions | |
Blessing | -0.090 |
WN | -0.088 |
advertisement | -0.086 |
Gutenberg | -0.086 |
Vaugh | -0.083 |
Token | atsu |
Token ID | 19231 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
erent | +0.272 |
escal | +0.251 |
iste | +0.241 |
apo | +0.241 |
bang | +0.240 |
Neg logit contributions | |
Blessing | -0.330 |
WN | -0.324 |
Gutenberg | -0.316 |
advertisement | -0.316 |
Vaugh | -0.304 |
Token | said |
Token ID | 531 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Blessing | +0.620 |
WN | +0.602 |
advertisement | +0.589 |
Gutenberg | +0.587 |
Vaugh | +0.571 |
Neg logit contributions | |
erent | -0.560 |
escal | -0.519 |
apo | -0.499 |
iste | -0.498 |
bang | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
erent | +0.228 |
escal | +0.210 |
apo | +0.201 |
iste | +0.201 |
bang | +0.200 |
Neg logit contributions | |
Blessing | -0.301 |
WN | -0.293 |
advertisement | -0.288 |
Gutenberg | -0.287 |
Vaugh | -0.280 |
Token | OB |
Token ID | 9864 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
erent | +0.076 |
escal | +0.071 |
apo | +0.069 |
bang | +0.069 |
iste | +0.069 |
Neg logit contributions | |
Blessing | -0.062 |
WN | -0.060 |
Gutenberg | -0.059 |
advertisement | -0.058 |
Vaugh | -0.057 |
Token | LE |
Token ID | 2538 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Blessing | +0.208 |
WN | +0.201 |
advertisement | +0.196 |
Gutenberg | +0.196 |
Vaugh | +0.190 |
Neg logit contributions | |
erent | -0.281 |
escal | -0.265 |
apo | -0.256 |
iste | -0.256 |
bang | -0.255 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Blessing | +0.309 |
WN | +0.299 |
Gutenberg | +0.295 |
advertisement | +0.295 |
Vaugh | +0.288 |
Neg logit contributions | |
erent | -0.275 |
escal | -0.255 |
apo | -0.245 |
iste | -0.244 |
bang | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Blessing | +0.302 |
WN | +0.295 |
advertisement | +0.291 |
Gutenberg | +0.284 |
Majesty | +0.267 |
Neg logit contributions | |
erent | -0.326 |
escal | -0.302 |
apo | -0.294 |
iste | -0.290 |
bang | -0.288 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Blessing | +0.173 |
WN | +0.170 |
advertisement | +0.167 |
Gutenberg | +0.164 |
Vaugh | +0.157 |
Neg logit contributions | |
erent | -0.188 |
escal | -0.174 |
iste | -0.169 |
apo | -0.168 |
bang | -0.167 |
Token | d |
Token ID | 67 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
Blessing | +0.259 |
WN | +0.249 |
advertisement | +0.245 |
Gutenberg | +0.240 |
Majesty | +0.222 |
Neg logit contributions | |
erent | -0.355 |
escal | -0.331 |
iste | -0.323 |
apo | -0.322 |
bang | -0.316 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
erent | +0.130 |
escal | +0.121 |
apo | +0.116 |
iste | +0.115 |
bang | +0.115 |
Neg logit contributions | |
Blessing | -0.158 |
WN | -0.154 |
advertisement | -0.151 |
Gutenberg | -0.151 |
Vaugh | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
erent | +0.087 |
escal | +0.078 |
apo | +0.075 |
iste | +0.075 |
bang | +0.073 |
Neg logit contributions | |
Blessing | -0.147 |
WN | -0.144 |
advertisement | -0.143 |
Gutenberg | -0.141 |
Majesty | -0.133 |
Token | Personnel |
Token ID | 41623 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
Blessing | +0.109 |
WN | +0.106 |
advertisement | +0.103 |
Gutenberg | +0.103 |
Vaugh | +0.099 |
Neg logit contributions | |
erent | -0.145 |
escal | -0.136 |
apo | -0.132 |
iste | -0.132 |
bang | -0.131 |
Token | admitting |
Token ID | 22688 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
erent | +0.163 |
escal | +0.152 |
apo | +0.146 |
iste | +0.146 |
bang | +0.145 |
Neg logit contributions | |
Blessing | -0.187 |
WN | -0.181 |
advertisement | -0.178 |
Gutenberg | -0.178 |
Vaugh | -0.172 |
Token | Scottish |
Token ID | 11905 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
Blessing | +0.007 |
WN | +0.006 |
advertisement | +0.006 |
Gutenberg | +0.006 |
Vaugh | +0.006 |
Neg logit contributions | |
erent | -0.006 |
escal | -0.006 |
apo | -0.006 |
iste | -0.006 |
bang | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
Blessing | +0.326 |
WN | +0.319 |
advertisement | +0.312 |
Gutenberg | +0.311 |
Vaugh | +0.302 |
Neg logit contributions | |
erent | -0.254 |
escal | -0.235 |
apo | -0.225 |
bang | -0.224 |
iste | -0.224 |
Token | I |
Token ID | 314 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Blessing | +0.092 |
WN | +0.089 |
advertisement | +0.087 |
Gutenberg | +0.087 |
Vaugh | +0.084 |
Neg logit contributions | |
erent | -0.095 |
escal | -0.088 |
apo | -0.086 |
iste | -0.085 |
bang | -0.085 |
Token | got |
Token ID | 1392 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
Blessing | +0.028 |
WN | +0.028 |
advertisement | +0.027 |
Gutenberg | +0.026 |
Vaugh | +0.025 |
Neg logit contributions | |
erent | -0.033 |
escal | -0.030 |
apo | -0.029 |
iste | -0.029 |
bang | -0.029 |
Token | into |
Token ID | 656 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
erent | +0.011 |
escal | +0.010 |
apo | +0.009 |
iste | +0.009 |
bang | +0.009 |
Neg logit contributions | |
Blessing | -0.012 |
WN | -0.011 |
advertisement | -0.011 |
Gutenberg | -0.011 |
Vaugh | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
Blessing | +0.159 |
WN | +0.154 |
advertisement | +0.152 |
Gutenberg | +0.151 |
Vaugh | +0.147 |
Neg logit contributions | |
erent | -0.140 |
escal | -0.131 |
apo | -0.126 |
iste | -0.125 |
bang | -0.124 |
Token | as |
Token ID | 355 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
Blessing | +0.125 |
WN | +0.120 |
advertisement | +0.120 |
Gutenberg | +0.118 |
Vaugh | +0.114 |
Neg logit contributions | |
erent | -0.112 |
escal | -0.104 |
apo | -0.100 |
iste | -0.098 |
bang | -0.098 |
Token | a |
Token ID | 257 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
erent | +0.038 |
escal | +0.035 |
apo | +0.034 |
iste | +0.034 |
bang | +0.034 |
Neg logit contributions | |
Blessing | -0.040 |
WN | -0.039 |
Gutenberg | -0.038 |
advertisement | -0.038 |
Vaugh | -0.037 |
Token | business |
Token ID | 1597 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
erent | +0.073 |
escal | +0.068 |
apo | +0.066 |
bang | +0.065 |
iste | +0.065 |
Neg logit contributions | |
Blessing | -0.083 |
WN | -0.080 |
advertisement | -0.078 |
Gutenberg | -0.078 |
Vaugh | -0.076 |
Token | opportunity |
Token ID | 3663 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Blessing | +0.119 |
WN | +0.115 |
advertisement | +0.114 |
Gutenberg | +0.112 |
Vaugh | +0.110 |
Neg logit contributions | |
erent | -0.100 |
escal | -0.093 |
apo | -0.090 |
bang | -0.089 |
iste | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
erent | +0.284 |
escal | +0.261 |
apo | +0.250 |
bang | +0.249 |
iste | +0.247 |
Neg logit contributions | |
Blessing | -0.401 |
WN | -0.391 |
advertisement | -0.386 |
Gutenberg | -0.384 |
Vaugh | -0.374 |
Token | But |
Token ID | 887 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
erent | +0.147 |
escal | +0.138 |
apo | +0.135 |
iste | +0.134 |
bang | +0.133 |
Neg logit contributions | |
Blessing | -0.103 |
WN | -0.099 |
advertisement | -0.097 |
Gutenberg | -0.096 |
Vaugh | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
erent | +0.133 |
escal | +0.124 |
apo | +0.119 |
iste | +0.119 |
bang | +0.119 |
Neg logit contributions | |
Blessing | -0.139 |
WN | -0.136 |
advertisement | -0.133 |
Gutenberg | -0.132 |
Vaugh | -0.129 |
Token | wing |
Token ID | 8539 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
erent | +0.193 |
escal | +0.179 |
apo | +0.171 |
iste | +0.171 |
bang | +0.170 |
Neg logit contributions | |
Blessing | -0.241 |
WN | -0.234 |
Gutenberg | -0.229 |
advertisement | -0.229 |
Vaugh | -0.224 |
Token | - |
Token ID | 12 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Blessing | +0.268 |
WN | +0.262 |
advertisement | +0.257 |
Gutenberg | +0.257 |
Vaugh | +0.251 |
Neg logit contributions | |
erent | -0.173 |
escal | -0.158 |
apo | -0.150 |
iste | -0.149 |
bang | -0.148 |
Token | fold |
Token ID | 11379 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Blessing | +0.075 |
WN | +0.073 |
advertisement | +0.072 |
Gutenberg | +0.072 |
Vaugh | +0.070 |
Neg logit contributions | |
erent | -0.059 |
escal | -0.054 |
apo | -0.052 |
iste | -0.052 |
bang | -0.051 |
Token | handle |
Token ID | 5412 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Blessing | +0.822 |
WN | +0.796 |
advertisement | +0.782 |
Gutenberg | +0.781 |
Vaugh | +0.757 |
Neg logit contributions | |
erent | -0.767 |
escal | -0.715 |
apo | -0.688 |
iste | -0.682 |
bang | -0.681 |
Token | sticking |
Token ID | 17274 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
Blessing | +0.462 |
WN | +0.448 |
advertisement | +0.441 |
Gutenberg | +0.439 |
Vaugh | +0.428 |
Neg logit contributions | |
erent | -0.400 |
escal | -0.372 |
apo | -0.358 |
iste | -0.353 |
bang | -0.349 |
Token | straight |
Token ID | 3892 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
erent | +0.191 |
escal | +0.180 |
apo | +0.172 |
iste | +0.168 |
bang | +0.166 |
Neg logit contributions | |
Blessing | -0.230 |
WN | -0.223 |
advertisement | -0.221 |
Gutenberg | -0.220 |
Vaugh | -0.213 |
Token | up |
Token ID | 510 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
erent | +0.048 |
escal | +0.045 |
apo | +0.043 |
iste | +0.042 |
bang | +0.042 |
Neg logit contributions | |
Blessing | -0.063 |
WN | -0.061 |
Gutenberg | -0.060 |
advertisement | -0.060 |
Vaugh | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Blessing | +0.070 |
WN | +0.067 |
Gutenberg | +0.067 |
advertisement | +0.067 |
Vaugh | +0.064 |
Neg logit contributions | |
erent | -0.060 |
escal | -0.056 |
apo | -0.054 |
iste | -0.053 |
bang | -0.052 |
Token | not |
Token ID | 407 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Blessing | +0.044 |
WN | +0.042 |
advertisement | +0.042 |
Gutenberg | +0.042 |
Vaugh | +0.040 |
Neg logit contributions | |
erent | -0.038 |
escal | -0.035 |
apo | -0.034 |
iste | -0.034 |
bang | -0.033 |
Token | st |
Token ID | 336 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
Blessing | +0.028 |
WN | +0.028 |
Gutenberg | +0.027 |
advertisement | +0.027 |
Vaugh | +0.026 |
Neg logit contributions | |
erent | -0.023 |
escal | -0.021 |
apo | -0.020 |
iste | -0.020 |
bang | -0.020 |
Token | Instead |
Token ID | 5455 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
erent | +0.064 |
escal | +0.060 |
apo | +0.058 |
iste | +0.058 |
bang | +0.058 |
Neg logit contributions | |
Blessing | -0.050 |
WN | -0.049 |
Gutenberg | -0.047 |
advertisement | -0.047 |
Vaugh | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
erent | +0.186 |
escal | +0.170 |
iste | +0.162 |
apo | +0.162 |
bang | +0.161 |
Neg logit contributions | |
Blessing | -0.266 |
WN | -0.259 |
advertisement | -0.255 |
Gutenberg | -0.254 |
Vaugh | -0.249 |
Token | it |
Token ID | 340 |
Feature activation | -4.34e-04 |
Pos logit contributions | |
Blessing | +0.051 |
WN | +0.050 |
Gutenberg | +0.049 |
advertisement | +0.048 |
Vaugh | +0.047 |
Neg logit contributions | |
erent | -0.054 |
escal | -0.051 |
apo | -0.049 |
iste | -0.048 |
bang | -0.048 |
Token | would |
Token ID | 561 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
erent | +0.001 |
escal | +0.001 |
apo | +0.001 |
bang | +0.001 |
iste | +0.001 |
Neg logit contributions | |
Blessing | -0.001 |
WN | -0.001 |
Gutenberg | -0.001 |
advertisement | -0.001 |
Vaugh | -0.001 |
Token | seem |
Token ID | 1283 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Blessing | +0.096 |
WN | +0.093 |
advertisement | +0.091 |
Gutenberg | +0.090 |
Vaugh | +0.088 |
Neg logit contributions | |
erent | -0.094 |
escal | -0.088 |
apo | -0.085 |
bang | -0.084 |
iste | -0.084 |
Token | that |
Token ID | 326 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
erent | +0.561 |
escal | +0.520 |
apo | +0.502 |
iste | +0.501 |
bang | +0.497 |
Neg logit contributions | |
Blessing | -0.600 |
WN | -0.584 |
advertisement | -0.574 |
Gutenberg | -0.570 |
Vaugh | -0.556 |
Token | feminists |
Token ID | 22742 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
erent | +0.141 |
escal | +0.133 |
apo | +0.128 |
bang | +0.128 |
iste | +0.127 |
Neg logit contributions | |
Blessing | -0.134 |
WN | -0.129 |
Gutenberg | -0.127 |
advertisement | -0.125 |
Vaugh | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Blessing | +0.035 |
WN | +0.034 |
advertisement | +0.034 |
Gutenberg | +0.034 |
Vaugh | +0.032 |
Neg logit contributions | |
erent | -0.029 |
escal | -0.028 |
apo | -0.026 |
iste | -0.026 |
bang | -0.026 |
Token | like |
Token ID | 588 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
erent | +0.029 |
escal | +0.027 |
apo | +0.026 |
bang | +0.025 |
iste | +0.025 |
Neg logit contributions | |
Blessing | -0.034 |
WN | -0.033 |
Gutenberg | -0.032 |
advertisement | -0.032 |
Vaugh | -0.031 |
Token | all |
Token ID | 477 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
erent | +0.105 |
escal | +0.098 |
apo | +0.095 |
bang | +0.094 |
iste | +0.094 |
Neg logit contributions | |
Blessing | -0.106 |
WN | -0.102 |
Gutenberg | -0.101 |
advertisement | -0.099 |
Vaugh | -0.097 |
Token | philosophers |
Token ID | 24858 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
Blessing | +0.226 |
WN | +0.220 |
Gutenberg | +0.215 |
advertisement | +0.214 |
Vaugh | +0.207 |
Neg logit contributions | |
erent | -0.223 |
escal | -0.210 |
apo | -0.201 |
bang | -0.200 |
iste | -0.199 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
erent | +0.333 |
escal | +0.309 |
apo | +0.300 |
iste | +0.297 |
bang | +0.294 |
Neg logit contributions | |
Blessing | -0.344 |
WN | -0.340 |
advertisement | -0.333 |
Gutenberg | -0.329 |
Vaugh | -0.312 |
Token | was |
Token ID | 373 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
erent | +0.033 |
escal | +0.031 |
apo | +0.030 |
iste | +0.030 |
bang | +0.030 |
Neg logit contributions | |
Blessing | -0.029 |
WN | -0.028 |
advertisement | -0.028 |
Gutenberg | -0.027 |
Vaugh | -0.027 |
Token | an |
Token ID | 281 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Blessing | +0.111 |
WN | +0.108 |
advertisement | +0.106 |
Gutenberg | +0.106 |
Vaugh | +0.103 |
Neg logit contributions | |
erent | -0.107 |
escal | -0.100 |
apo | -0.096 |
iste | -0.096 |
bang | -0.095 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Blessing | +0.080 |
WN | +0.078 |
Gutenberg | +0.077 |
advertisement | +0.076 |
Vaugh | +0.074 |
Neg logit contributions | |
erent | -0.073 |
escal | -0.067 |
apo | -0.065 |
iste | -0.065 |
bang | -0.064 |
Token | job |
Token ID | 1693 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Blessing | +0.558 |
WN | +0.538 |
advertisement | +0.533 |
Gutenberg | +0.531 |
Vaugh | +0.512 |
Neg logit contributions | |
erent | -0.479 |
escal | -0.446 |
apo | -0.425 |
iste | -0.422 |
bang | -0.422 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
erent | +0.886 |
escal | +0.820 |
apo | +0.785 |
iste | +0.784 |
bang | +0.779 |
Neg logit contributions | |
Blessing | -1.095 |
WN | -1.068 |
advertisement | -1.047 |
Gutenberg | -1.045 |
Vaugh | -1.019 |
Token | that |
Token ID | 326 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
erent | +0.054 |
escal | +0.051 |
apo | +0.049 |
iste | +0.049 |
bang | +0.048 |
Neg logit contributions | |
Blessing | -0.059 |
WN | -0.058 |
advertisement | -0.057 |
Gutenberg | -0.056 |
Vaugh | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Blessing | +0.078 |
WN | +0.076 |
Gutenberg | +0.075 |
advertisement | +0.074 |
Vaugh | +0.072 |
Neg logit contributions | |
erent | -0.074 |
escal | -0.069 |
bang | -0.066 |
iste | -0.066 |
apo | -0.066 |
Token | Sandy |
Token ID | 17581 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Blessing | +0.057 |
WN | +0.055 |
Gutenberg | +0.054 |
advertisement | +0.054 |
Vaugh | +0.053 |
Neg logit contributions | |
erent | -0.056 |
escal | -0.052 |
apo | -0.050 |
iste | -0.050 |
bang | -0.050 |
Token | Hook |
Token ID | 18531 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Blessing | +0.035 |
WN | +0.034 |
Gutenberg | +0.033 |
advertisement | +0.033 |
Vaugh | +0.033 |
Neg logit contributions | |
erent | -0.024 |
escal | -0.022 |
iste | -0.021 |
apo | -0.021 |
bang | -0.021 |
Token | shooting |
Token ID | 4395 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
erent | +0.688 |
escal | +0.640 |
apo | +0.615 |
iste | +0.613 |
bang | +0.611 |
Neg logit contributions | |
Blessing | -0.734 |
WN | -0.711 |
advertisement | -0.696 |
Gutenberg | -0.695 |
Vaugh | -0.674 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
Blessing | +0.549 |
WN | +0.534 |
advertisement | +0.526 |
Gutenberg | +0.523 |
Vaugh | +0.507 |
Neg logit contributions | |
erent | -0.407 |
escal | -0.374 |
iste | -0.359 |
apo | -0.358 |
bang | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
Blessing | +0.082 |
WN | +0.079 |
advertisement | +0.079 |
Gutenberg | +0.078 |
Vaugh | +0.076 |
Neg logit contributions | |
erent | -0.067 |
escal | -0.063 |
apo | -0.060 |
bang | -0.060 |
iste | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
Blessing | +0.141 |
WN | +0.138 |
advertisement | +0.135 |
Gutenberg | +0.133 |
Majesty | +0.124 |
Neg logit contributions | |
erent | -0.150 |
escal | -0.140 |
apo | -0.136 |
iste | -0.134 |
bang | -0.133 |
Token | Alexander |
Token ID | 38708 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Blessing | +0.122 |
WN | +0.121 |
advertisement | +0.119 |
Gutenberg | +0.116 |
Vaugh | +0.112 |
Neg logit contributions | |
erent | -0.134 |
escal | -0.125 |
iste | -0.121 |
apo | -0.120 |
bang | -0.119 |
Token | P |
Token ID | 350 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Blessing | +0.027 |
WN | +0.027 |
advertisement | +0.026 |
Gutenberg | +0.026 |
Vaugh | +0.025 |
Neg logit contributions | |
erent | -0.032 |
escal | -0.030 |
iste | -0.029 |
apo | -0.029 |
bang | -0.029 |
Token | eder |
Token ID | 5702 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Blessing | +0.357 |
WN | +0.351 |
advertisement | +0.343 |
Gutenberg | +0.343 |
Vaugh | +0.334 |
Neg logit contributions | |
erent | -0.260 |
escal | -0.240 |
bang | -0.229 |
apo | -0.229 |
iste | -0.228 |
Token | , |
Token ID | 11 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
erent | +0.788 |
escal | +0.732 |
iste | +0.709 |
apo | +0.707 |
bang | +0.700 |
Neg logit contributions | |
Blessing | -0.857 |
WN | -0.836 |
advertisement | -0.824 |
Gutenberg | -0.815 |
Vaugh | -0.796 |
Token | 57 |
Token ID | 7632 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Blessing | +0.150 |
WN | +0.145 |
advertisement | +0.142 |
Gutenberg | +0.142 |
Vaugh | +0.138 |
Neg logit contributions | |
erent | -0.151 |
escal | -0.142 |
apo | -0.137 |
iste | -0.136 |
bang | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Blessing | +0.278 |
WN | +0.272 |
advertisement | +0.268 |
Gutenberg | +0.267 |
Vaugh | +0.262 |
Neg logit contributions | |
erent | -0.174 |
escal | -0.159 |
apo | -0.151 |
iste | -0.151 |
bang | -0.150 |
Token | was |
Token ID | 373 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Blessing | +0.045 |
WN | +0.043 |
advertisement | +0.043 |
Gutenberg | +0.042 |
Vaugh | +0.041 |
Neg logit contributions | |
erent | -0.045 |
escal | -0.042 |
apo | -0.040 |
iste | -0.040 |
bang | -0.040 |
Token | found |
Token ID | 1043 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Blessing | +0.268 |
WN | +0.260 |
advertisement | +0.255 |
Gutenberg | +0.254 |
Vaugh | +0.247 |
Neg logit contributions | |
erent | -0.278 |
escal | -0.260 |
apo | -0.251 |
iste | -0.251 |
bang | -0.249 |
Token | child |
Token ID | 1200 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
erent | +0.008 |
escal | +0.008 |
apo | +0.007 |
bang | +0.007 |
iste | +0.007 |
Neg logit contributions | |
Blessing | -0.008 |
WN | -0.008 |
Gutenberg | -0.007 |
advertisement | -0.007 |
Vaugh | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
Blessing | +0.095 |
WN | +0.092 |
advertisement | +0.091 |
Gutenberg | +0.090 |
Vaugh | +0.088 |
Neg logit contributions | |
erent | -0.059 |
escal | -0.054 |
apo | -0.051 |
bang | -0.051 |
iste | -0.050 |
Token | " |
Token ID | 366 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
Blessing | +0.088 |
WN | +0.084 |
advertisement | +0.083 |
Gutenberg | +0.082 |
Vaugh | +0.080 |
Neg logit contributions | |
erent | -0.115 |
escal | -0.108 |
apo | -0.105 |
bang | -0.104 |
iste | -0.104 |
Token | You |
Token ID | 1639 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Blessing | +0.187 |
WN | +0.186 |
advertisement | +0.183 |
Gutenberg | +0.177 |
Vaugh | +0.170 |
Neg logit contributions | |
erent | -0.203 |
escal | -0.189 |
apo | -0.184 |
iste | -0.182 |
bang | -0.181 |
Token | might |
Token ID | 1244 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
Blessing | +0.131 |
WN | +0.127 |
advertisement | +0.124 |
Gutenberg | +0.123 |
Vaugh | +0.118 |
Neg logit contributions | |
erent | -0.130 |
escal | -0.120 |
apo | -0.118 |
iste | -0.116 |
bang | -0.115 |
Token | drive |
Token ID | 3708 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Blessing | +0.117 |
WN | +0.114 |
advertisement | +0.111 |
Gutenberg | +0.109 |
Vaugh | +0.106 |
Neg logit contributions | |
erent | -0.116 |
escal | -0.107 |
apo | -0.105 |
iste | -0.104 |
bang | -0.102 |
Token | fast |
Token ID | 3049 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
erent | +0.877 |
escal | +0.817 |
apo | +0.788 |
bang | +0.774 |
iste | +0.774 |
Neg logit contributions | |
Blessing | -1.013 |
WN | -0.980 |
Gutenberg | -0.965 |
advertisement | -0.960 |
Vaugh | -0.931 |
Token | but |
Token ID | 475 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Blessing | +0.195 |
WN | +0.191 |
advertisement | +0.187 |
Gutenberg | +0.186 |
Vaugh | +0.180 |
Neg logit contributions | |
erent | -0.166 |
escal | -0.154 |
apo | -0.149 |
bang | -0.146 |
iste | -0.146 |
Token | without |
Token ID | 1231 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Blessing | +0.176 |
WN | +0.170 |
Gutenberg | +0.168 |
advertisement | +0.168 |
Vaugh | +0.162 |
Neg logit contributions | |
erent | -0.148 |
escal | -0.138 |
apo | -0.133 |
iste | -0.132 |
bang | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
Blessing | +0.261 |
WN | +0.251 |
advertisement | +0.248 |
Gutenberg | +0.247 |
Vaugh | +0.239 |
Neg logit contributions | |
erent | -0.258 |
escal | -0.240 |
apo | -0.233 |
iste | -0.229 |
bang | -0.229 |
Token | racing |
Token ID | 11717 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Blessing | +0.028 |
WN | +0.026 |
advertisement | +0.026 |
Gutenberg | +0.026 |
Vaugh | +0.025 |
Neg logit contributions | |
erent | -0.024 |
escal | -0.022 |
apo | -0.022 |
iste | -0.021 |
bang | -0.021 |
Token | black |
Token ID | 2042 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Blessing | +0.152 |
WN | +0.147 |
advertisement | +0.145 |
Gutenberg | +0.145 |
Vaugh | +0.141 |
Neg logit contributions | |
erent | -0.116 |
escal | -0.106 |
apo | -0.102 |
iste | -0.101 |
bang | -0.100 |
Token | top |
Token ID | 1353 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Blessing | +0.827 |
WN | +0.802 |
Gutenberg | +0.783 |
advertisement | +0.783 |
Vaugh | +0.762 |
Neg logit contributions | |
erent | -0.743 |
escal | -0.689 |
apo | -0.664 |
iste | -0.660 |
bang | -0.654 |
Token | hat |
Token ID | 6877 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
Blessing | +0.259 |
WN | +0.254 |
advertisement | +0.250 |
Gutenberg | +0.249 |
Vaugh | +0.241 |
Neg logit contributions | |
erent | -0.183 |
escal | -0.168 |
apo | -0.161 |
iste | -0.159 |
bang | -0.158 |
Token | he |
Token ID | 339 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Blessing | +0.067 |
WN | +0.065 |
advertisement | +0.064 |
Gutenberg | +0.064 |
Vaugh | +0.062 |
Neg logit contributions | |
erent | -0.049 |
escal | -0.045 |
apo | -0.043 |
iste | -0.043 |
bang | -0.043 |
Token | always |
Token ID | 1464 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
Blessing | +0.115 |
WN | +0.113 |
advertisement | +0.109 |
Gutenberg | +0.107 |
Vaugh | +0.105 |
Neg logit contributions | |
erent | -0.130 |
escal | -0.120 |
iste | -0.116 |
apo | -0.116 |
bang | -0.114 |
Token | wore |
Token ID | 12408 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Blessing | +0.084 |
WN | +0.082 |
advertisement | +0.080 |
Gutenberg | +0.078 |
Vaugh | +0.076 |
Neg logit contributions | |
erent | -0.101 |
escal | -0.094 |
iste | -0.091 |
apo | -0.090 |
bang | -0.089 |
Token | to |
Token ID | 284 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
erent | +0.739 |
escal | +0.680 |
apo | +0.649 |
iste | +0.649 |
bang | +0.645 |
Neg logit contributions | |
Blessing | -1.036 |
WN | -1.010 |
Gutenberg | -0.992 |
advertisement | -0.991 |
Vaugh | -0.969 |
Token | events |
Token ID | 2995 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Blessing | +0.082 |
WN | +0.080 |
advertisement | +0.078 |
Gutenberg | +0.078 |
Vaugh | +0.077 |
Neg logit contributions | |
erent | -0.060 |
escal | -0.055 |
iste | -0.053 |
apo | -0.052 |
bang | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
Blessing | +0.041 |
WN | +0.040 |
advertisement | +0.040 |
Gutenberg | +0.039 |
Vaugh | +0.038 |
Neg logit contributions | |
erent | -0.032 |
escal | -0.029 |
apo | -0.028 |
iste | -0.028 |
bang | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
Blessing | +0.119 |
WN | +0.116 |
advertisement | +0.113 |
Gutenberg | +0.112 |
Vaugh | +0.109 |
Neg logit contributions | |
erent | -0.142 |
escal | -0.132 |
apo | -0.128 |
iste | -0.128 |
bang | -0.127 |
Token | described |
Token ID | 3417 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Blessing | +0.221 |
WN | +0.214 |
advertisement | +0.210 |
Gutenberg | +0.208 |
Vaugh | +0.203 |
Neg logit contributions | |
erent | -0.235 |
escal | -0.220 |
apo | -0.212 |
iste | -0.211 |
bang | -0.210 |
Token | University |
Token ID | 2059 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Blessing | +0.050 |
WN | +0.048 |
advertisement | +0.047 |
Gutenberg | +0.047 |
Vaugh | +0.046 |
Neg logit contributions | |
erent | -0.052 |
escal | -0.048 |
iste | -0.046 |
apo | -0.046 |
bang | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
Blessing | +0.030 |
WN | +0.029 |
advertisement | +0.028 |
Gutenberg | +0.028 |
Vaugh | +0.027 |
Neg logit contributions | |
erent | -0.026 |
escal | -0.024 |
apo | -0.023 |
iste | -0.023 |
bang | -0.023 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Blessing | +0.122 |
WN | +0.118 |
Gutenberg | +0.116 |
advertisement | +0.114 |
Vaugh | +0.111 |
Neg logit contributions | |
erent | -0.172 |
escal | -0.162 |
apo | -0.157 |
iste | -0.156 |
bang | -0.156 |
Token | � |
Token ID | 447 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
Blessing | +0.104 |
WN | +0.102 |
Gutenberg | +0.100 |
advertisement | +0.100 |
Vaugh | +0.097 |
Neg logit contributions | |
erent | -0.067 |
escal | -0.061 |
apo | -0.058 |
iste | -0.058 |
bang | -0.058 |
Token | � |
Token ID | 247 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
erent | +0.246 |
escal | +0.233 |
apo | +0.225 |
iste | +0.225 |
bang | +0.224 |
Neg logit contributions | |
Blessing | -0.166 |
WN | -0.160 |
advertisement | -0.156 |
Gutenberg | -0.156 |
Vaugh | -0.150 |
Token | i |
Token ID | 72 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
erent | +0.165 |
escal | +0.154 |
apo | +0.147 |
iste | +0.147 |
bang | +0.147 |
Neg logit contributions | |
Blessing | -0.169 |
WN | -0.165 |
Gutenberg | -0.161 |
advertisement | -0.161 |
Vaugh | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
erent | +0.826 |
escal | +0.762 |
apo | +0.728 |
iste | +0.727 |
bang | +0.722 |
Neg logit contributions | |
Blessing | -1.118 |
WN | -1.091 |
advertisement | -1.071 |
Gutenberg | -1.068 |
Vaugh | -1.043 |
Token | there |
Token ID | 612 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
erent | +0.112 |
escal | +0.104 |
iste | +0.100 |
apo | +0.100 |
bang | +0.100 |
Neg logit contributions | |
Blessing | -0.112 |
WN | -0.109 |
Gutenberg | -0.107 |
advertisement | -0.107 |
Vaugh | -0.103 |
Token | may |
Token ID | 743 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Blessing | +0.007 |
WN | +0.007 |
advertisement | +0.007 |
Gutenberg | +0.007 |
Vaugh | +0.006 |
Neg logit contributions | |
erent | -0.007 |
escal | -0.007 |
iste | -0.007 |
apo | -0.007 |
bang | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
Blessing | +0.048 |
WN | +0.047 |
advertisement | +0.046 |
Gutenberg | +0.045 |
Vaugh | +0.044 |
Neg logit contributions | |
erent | -0.052 |
escal | -0.049 |
apo | -0.047 |
iste | -0.047 |
bang | -0.047 |
Token | modest |
Token ID | 12949 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
erent | +0.018 |
escal | +0.017 |
apo | +0.016 |
iste | +0.016 |
bang | +0.016 |
Neg logit contributions | |
Blessing | -0.020 |
WN | -0.019 |
Gutenberg | -0.019 |
advertisement | -0.019 |
Vaugh | -0.018 |
Token | CEO |
Token ID | 6123 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Blessing | +0.036 |
WN | +0.035 |
Gutenberg | +0.034 |
advertisement | +0.034 |
Vaugh | +0.033 |
Neg logit contributions | |
erent | -0.045 |
escal | -0.043 |
apo | -0.042 |
iste | -0.041 |
bang | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Blessing | +0.451 |
WN | +0.436 |
Gutenberg | +0.426 |
advertisement | +0.424 |
Vaugh | +0.412 |
Neg logit contributions | |
erent | -0.498 |
escal | -0.468 |
apo | -0.451 |
iste | -0.448 |
bang | -0.447 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Blessing | +0.168 |
WN | +0.162 |
Gutenberg | +0.159 |
advertisement | +0.158 |
Vaugh | +0.153 |
Neg logit contributions | |
erent | -0.186 |
escal | -0.175 |
apo | -0.168 |
iste | -0.168 |
bang | -0.167 |
Token | Climate |
Token ID | 13963 |
Feature activation | -8.29e-03 |
Pos logit contributions | |
erent | +0.029 |
escal | +0.028 |
apo | +0.027 |
iste | +0.027 |
bang | +0.026 |
Neg logit contributions | |
Blessing | -0.026 |
WN | -0.025 |
Gutenberg | -0.024 |
advertisement | -0.024 |
Vaugh | -0.024 |
Token | Works |
Token ID | 23044 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
erent | +0.020 |
escal | +0.019 |
apo | +0.018 |
iste | +0.018 |
bang | +0.018 |
Neg logit contributions | |
Blessing | -0.020 |
WN | -0.019 |
advertisement | -0.019 |
Gutenberg | -0.019 |
Vaugh | -0.018 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
erent | +0.440 |
escal | +0.409 |
apo | +0.393 |
iste | +0.393 |
bang | +0.390 |
Neg logit contributions | |
Blessing | -0.441 |
WN | -0.428 |
advertisement | -0.420 |
Gutenberg | -0.418 |
Vaugh | -0.405 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
erent | +0.918 |
escal | +0.859 |
apo | +0.829 |
iste | +0.823 |
bang | +0.820 |
Neg logit contributions | |
Blessing | -0.872 |
WN | -0.845 |
Gutenberg | -0.825 |
advertisement | -0.823 |
Vaugh | -0.798 |
Token | - |
Token ID | 12 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
erent | +0.116 |
escal | +0.107 |
apo | +0.103 |
iste | +0.103 |
bang | +0.102 |
Neg logit contributions | |
Blessing | -0.146 |
WN | -0.143 |
advertisement | -0.140 |
Gutenberg | -0.139 |
Vaugh | -0.136 |
Token | 2011 |
Token ID | 9804 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
erent | +0.073 |
escal | +0.067 |
iste | +0.064 |
apo | +0.064 |
bang | +0.062 |
Neg logit contributions | |
Blessing | -0.106 |
WN | -0.104 |
advertisement | -0.103 |
Gutenberg | -0.101 |
Vaugh | -0.098 |
Token | ), |
Token ID | 828 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
erent | +0.089 |
escal | +0.082 |
apo | +0.078 |
iste | +0.078 |
bang | +0.077 |
Neg logit contributions | |
Blessing | -0.133 |
WN | -0.129 |
advertisement | -0.127 |
Gutenberg | -0.127 |
Vaugh | -0.124 |
Token | Larry |
Token ID | 13633 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
erent | +0.171 |
escal | +0.161 |
apo | +0.155 |
iste | +0.155 |
bang | +0.154 |
Neg logit contributions | |
Blessing | -0.146 |
WN | -0.141 |
advertisement | -0.138 |
Gutenberg | -0.138 |
Vaugh | -0.134 |