Token | leader |
Token ID | 3554 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
�� | +0.648 |
esty | +0.646 |
Dickinson | +0.646 |
Lund | +0.643 |
allic | +0.642 |
Neg logit contributions | |
sent | -0.556 |
kins | -0.548 |
.# | -0.540 |
SEE | -0.538 |
\\ | -0.532 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
sent | +0.185 |
kins | +0.181 |
.# | +0.180 |
SEE | +0.178 |
\\ | +0.177 |
Neg logit contributions | |
�� | -0.224 |
esty | -0.223 |
Dickinson | -0.221 |
allic | -0.221 |
Lund | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
�� | +0.198 |
esty | +0.197 |
Dickinson | +0.196 |
allic | +0.195 |
Lund | +0.194 |
Neg logit contributions | |
sent | -0.163 |
kins | -0.160 |
.# | -0.159 |
SEE | -0.157 |
\\ | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
�� | +0.372 |
esty | +0.364 |
Dickinson | +0.361 |
allic | +0.360 |
Lund | +0.359 |
Neg logit contributions | |
sent | -0.283 |
kins | -0.277 |
.# | -0.276 |
\\ | -0.272 |
SEE | -0.271 |
Token | Mus |
Token ID | 10694 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
�� | +0.276 |
esty | +0.275 |
Dickinson | +0.273 |
allic | +0.273 |
Lund | +0.272 |
Neg logit contributions | |
sent | -0.166 |
kins | -0.163 |
.# | -0.161 |
SEE | -0.158 |
\\ | -0.158 |
Token | ically |
Token ID | 1146 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
sent | +0.157 |
kins | +0.155 |
.# | +0.154 |
SEE | +0.153 |
\\ | +0.152 |
Neg logit contributions | |
�� | -0.104 |
esty | -0.102 |
Dickinson | -0.102 |
Lund | -0.101 |
allic | -0.101 |
Token | speaking |
Token ID | 5486 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Lund | +2.368 |
Dickinson | +2.362 |
esty | +2.340 |
allic | +2.320 |
�� | +2.313 |
Neg logit contributions | |
sent | -2.296 |
kins | -2.266 |
.# | -2.215 |
\\ | -2.196 |
SEE | -2.191 |
Token | everyone |
Token ID | 2506 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
sent | +0.198 |
kins | +0.195 |
.# | +0.192 |
SEE | +0.190 |
\\ | +0.190 |
Neg logit contributions | |
�� | -0.217 |
esty | -0.216 |
Dickinson | -0.215 |
Lund | -0.214 |
allic | -0.214 |
Token | in |
Token ID | 287 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
sent | +0.048 |
kins | +0.047 |
.# | +0.047 |
\\ | +0.047 |
SEE | +0.046 |
Neg logit contributions | |
�� | -0.058 |
esty | -0.056 |
allic | -0.056 |
Dickinson | -0.056 |
Lund | -0.055 |
Token | G |
Token ID | 402 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
�� | +0.495 |
esty | +0.491 |
Dickinson | +0.491 |
Lund | +0.489 |
allic | +0.489 |
Neg logit contributions | |
sent | -0.457 |
kins | -0.450 |
.# | -0.447 |
SEE | -0.440 |
\\ | -0.439 |
Token | WAR |
Token ID | 16279 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
�� | +0.431 |
Dickinson | +0.422 |
esty | +0.421 |
Lund | +0.416 |
allic | +0.415 |
Neg logit contributions | |
sent | -0.326 |
kins | -0.319 |
.# | -0.316 |
SEE | -0.313 |
\\ | -0.312 |
Token | er |
Token ID | 263 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
esty | +0.791 |
Dickinson | +0.754 |
allic | +0.752 |
�� | +0.749 |
abbit | +0.744 |
Neg logit contributions | |
sent | -1.099 |
kins | -1.088 |
SEE | -1.087 |
.# | -1.080 |
\\ | -1.065 |
Token | ator |
Token ID | 1352 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
sent | +0.019 |
kins | +0.019 |
SEE | +0.019 |
.# | +0.019 |
Limit | +0.019 |
Neg logit contributions | |
esty | -0.019 |
allic | -0.019 |
Lund | -0.019 |
Dickinson | -0.019 |
abbit | -0.018 |
Token | Gabriel |
Token ID | 17371 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
�� | +0.357 |
esty | +0.356 |
Dickinson | +0.355 |
Lund | +0.353 |
allic | +0.352 |
Neg logit contributions | |
sent | -0.282 |
kins | -0.276 |
.# | -0.273 |
SEE | -0.271 |
\\ | -0.270 |
Token | Lerner |
Token ID | 49750 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
sent | +0.092 |
kins | +0.091 |
.# | +0.090 |
\\ | +0.089 |
SEE | +0.089 |
Neg logit contributions | |
�� | -0.086 |
esty | -0.084 |
Dickinson | -0.083 |
allic | -0.082 |
abbit | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
�� | +0.134 |
esty | +0.132 |
allic | +0.132 |
Dickinson | +0.132 |
Lund | +0.131 |
Neg logit contributions | |
sent | -0.121 |
kins | -0.120 |
.# | -0.119 |
\\ | -0.117 |
SEE | -0.117 |
Token | metro |
Token ID | 24536 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
�� | +0.256 |
esty | +0.252 |
allic | +0.250 |
Dickinson | +0.249 |
abbit | +0.248 |
Neg logit contributions | |
sent | -0.272 |
kins | -0.268 |
.# | -0.267 |
\\ | -0.263 |
SEE | -0.262 |
Token | editor |
Token ID | 5464 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Dickinson | +2.266 |
esty | +2.251 |
Lund | +2.247 |
allic | +2.247 |
�� | +2.214 |
Neg logit contributions | |
sent | -2.221 |
kins | -2.188 |
.# | -2.164 |
SEE | -2.155 |
\\ | -2.146 |
Token | of |
Token ID | 286 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
esty | +1.044 |
Dickinson | +1.042 |
�� | +1.037 |
Lund | +1.035 |
allic | +1.029 |
Neg logit contributions | |
sent | -1.032 |
kins | -1.012 |
.# | -1.003 |
SEE | -0.998 |
\\ | -0.993 |
Token | La |
Token ID | 4689 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
�� | +0.223 |
esty | +0.221 |
allic | +0.219 |
Dickinson | +0.219 |
Lund | +0.218 |
Neg logit contributions | |
sent | -0.197 |
kins | -0.194 |
.# | -0.192 |
SEE | -0.190 |
\\ | -0.190 |
Token | Opinion |
Token ID | 29525 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
�� | +0.112 |
esty | +0.111 |
Dickinson | +0.111 |
allic | +0.111 |
Lund | +0.110 |
Neg logit contributions | |
sent | -0.085 |
kins | -0.083 |
.# | -0.083 |
SEE | -0.081 |
\\ | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
�� | +1.276 |
Dickinson | +1.276 |
esty | +1.275 |
Lund | +1.267 |
allic | +1.265 |
Neg logit contributions | |
sent | -1.077 |
kins | -1.060 |
.# | -1.047 |
\\ | -1.034 |
SEE | -1.033 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sent | +0.066 |
kins | +0.065 |
.# | +0.064 |
SEE | +0.063 |
\\ | +0.063 |
Neg logit contributions | |
�� | -0.094 |
esty | -0.094 |
Dickinson | -0.093 |
Lund | -0.093 |
allic | -0.093 |
Token | land |
Token ID | 1956 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
sent | +0.011 |
kins | +0.010 |
.# | +0.010 |
SEE | +0.010 |
\\ | +0.010 |
Neg logit contributions | |
�� | -0.010 |
esty | -0.010 |
Dickinson | -0.010 |
allic | -0.010 |
Lund | -0.010 |
Token | as |
Token ID | 355 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
�� | +0.297 |
esty | +0.296 |
Dickinson | +0.295 |
Lund | +0.294 |
allic | +0.294 |
Neg logit contributions | |
sent | -0.233 |
kins | -0.229 |
.# | -0.226 |
SEE | -0.225 |
\\ | -0.223 |
Token | many |
Token ID | 867 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
�� | +0.114 |
esty | +0.112 |
Dickinson | +0.112 |
allic | +0.111 |
abbit | +0.111 |
Neg logit contributions | |
sent | -0.103 |
kins | -0.101 |
.# | -0.100 |
\\ | -0.099 |
SEE | -0.099 |
Token | C |
Token ID | 327 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
�� | +0.223 |
esty | +0.222 |
Dickinson | +0.221 |
allic | +0.220 |
Lund | +0.220 |
Neg logit contributions | |
sent | -0.205 |
kins | -0.201 |
.# | -0.200 |
SEE | -0.197 |
\\ | -0.197 |
Token | Ms |
Token ID | 10128 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
�� | +0.062 |
esty | +0.062 |
Dickinson | +0.061 |
allic | +0.061 |
Lund | +0.061 |
Neg logit contributions | |
sent | -0.020 |
kins | -0.020 |
.# | -0.019 |
SEE | -0.019 |
\\ | -0.019 |
Token | prior |
Token ID | 3161 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
esty | +2.288 |
Lund | +2.266 |
Dickinson | +2.261 |
allic | +2.248 |
abbit | +2.231 |
Neg logit contributions | |
sent | -1.994 |
.# | -1.958 |
kins | -1.944 |
SEE | -1.934 |
Tab | -1.917 |
Token | to |
Token ID | 284 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
�� | +0.313 |
esty | +0.312 |
Dickinson | +0.309 |
allic | +0.308 |
Lund | +0.308 |
Neg logit contributions | |
sent | -0.295 |
kins | -0.291 |
.# | -0.289 |
SEE | -0.285 |
\\ | -0.284 |
Token | Des |
Token ID | 2935 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
sent | +0.016 |
kins | +0.016 |
.# | +0.015 |
SEE | +0.015 |
\\ | +0.015 |
Neg logit contributions | |
�� | -0.018 |
esty | -0.018 |
Dickinson | -0.017 |
allic | -0.017 |
Lund | -0.017 |
Token | hm |
Token ID | 23940 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
�� | +0.533 |
esty | +0.527 |
Dickinson | +0.526 |
allic | +0.523 |
Lund | +0.522 |
Neg logit contributions | |
sent | -0.296 |
kins | -0.290 |
.# | -0.287 |
\\ | -0.281 |
SEE | -0.281 |
Token | uk |
Token ID | 2724 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
sent | +0.228 |
kins | +0.227 |
.# | +0.223 |
\\ | +0.220 |
SEE | +0.218 |
Neg logit contributions | |
�� | -0.299 |
Dickinson | -0.293 |
esty | -0.291 |
Lund | -0.290 |
allic | -0.288 |
Token | an |
Token ID | 281 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
�� | +0.000 |
esty | +0.000 |
Dickinson | +0.000 |
allic | +0.000 |
Lund | +0.000 |
Neg logit contributions | |
sent | -0.000 |
kins | -0.000 |
.# | -0.000 |
\\ | -0.000 |
SEE | -0.000 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
�� | +0.290 |
esty | +0.287 |
Dickinson | +0.285 |
allic | +0.283 |
Lund | +0.282 |
Neg logit contributions | |
sent | -0.227 |
kins | -0.221 |
.# | -0.221 |
\\ | -0.218 |
SEE | -0.217 |
Token | : |
Token ID | 1058 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
�� | +0.670 |
esty | +0.666 |
Dickinson | +0.663 |
allic | +0.661 |
Lund | +0.659 |
Neg logit contributions | |
sent | -0.622 |
kins | -0.612 |
.# | -0.607 |
SEE | -0.600 |
\\ | -0.599 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
�� | +0.371 |
esty | +0.367 |
Dickinson | +0.365 |
allic | +0.364 |
Lund | +0.362 |
Neg logit contributions | |
sent | -0.320 |
kins | -0.315 |
.# | -0.312 |
SEE | -0.308 |
\\ | -0.306 |
Token |
|
Token ID | 198 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
�� | +0.874 |
esty | +0.863 |
Dickinson | +0.858 |
allic | +0.855 |
Lund | +0.853 |
Neg logit contributions | |
sent | -0.694 |
kins | -0.681 |
.# | -0.676 |
\\ | -0.666 |
SEE | -0.666 |
Token | impl |
Token ID | 23928 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
�� | +0.544 |
esty | +0.544 |
allic | +0.541 |
Dickinson | +0.538 |
abbit | +0.535 |
Neg logit contributions | |
sent | -0.460 |
kins | -0.454 |
.# | -0.448 |
SEE | -0.443 |
\\ | -0.441 |
Token | < |
Token ID | 1279 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Dickinson | +2.119 |
esty | +2.118 |
�� | +2.115 |
Lund | +2.109 |
allic | +2.094 |
Neg logit contributions | |
sent | -2.026 |
kins | -1.995 |
.# | -1.967 |
SEE | -1.965 |
\\ | -1.932 |
Token | T |
Token ID | 309 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
�� | +0.351 |
esty | +0.350 |
Dickinson | +0.348 |
allic | +0.347 |
Lund | +0.346 |
Neg logit contributions | |
sent | -0.223 |
kins | -0.219 |
.# | -0.217 |
SEE | -0.213 |
\\ | -0.212 |
Token | > |
Token ID | 1875 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
esty | +0.223 |
Dickinson | +0.223 |
�� | +0.222 |
allic | +0.221 |
Lund | +0.221 |
Neg logit contributions | |
sent | -0.138 |
kins | -0.136 |
.# | -0.134 |
\\ | -0.131 |
SEE | -0.131 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +0.247 |
esty | +0.244 |
Dickinson | +0.243 |
allic | +0.242 |
Lund | +0.242 |
Neg logit contributions | |
sent | -0.141 |
kins | -0.138 |
.# | -0.137 |
\\ | -0.135 |
SEE | -0.135 |
Token | < |
Token ID | 1279 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
�� | +0.651 |
esty | +0.648 |
Dickinson | +0.645 |
allic | +0.643 |
Lund | +0.640 |
Neg logit contributions | |
sent | -0.565 |
kins | -0.556 |
.# | -0.551 |
SEE | -0.543 |
\\ | -0.543 |
Token | fair |
Token ID | 3148 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
sent | +0.187 |
kins | +0.184 |
.# | +0.183 |
SEE | +0.180 |
\\ | +0.180 |
Neg logit contributions | |
�� | -0.205 |
esty | -0.203 |
Dickinson | -0.202 |
allic | -0.201 |
Lund | -0.200 |
Token | enough |
Token ID | 1576 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
�� | +0.638 |
esty | +0.638 |
Dickinson | +0.632 |
Lund | +0.630 |
allic | +0.629 |
Neg logit contributions | |
sent | -0.575 |
kins | -0.565 |
.# | -0.560 |
SEE | -0.557 |
\\ | -0.553 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
�� | +0.362 |
esty | +0.361 |
Dickinson | +0.359 |
Lund | +0.358 |
allic | +0.357 |
Neg logit contributions | |
sent | -0.319 |
kins | -0.314 |
.# | -0.310 |
SEE | -0.308 |
\\ | -0.306 |
Token | if |
Token ID | 611 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
sent | +0.195 |
kins | +0.191 |
.# | +0.190 |
\\ | +0.188 |
SEE | +0.187 |
Neg logit contributions | |
�� | -0.211 |
esty | -0.209 |
Dickinson | -0.208 |
allic | -0.208 |
Lund | -0.207 |
Token | de |
Token ID | 390 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
sent | +0.124 |
kins | +0.122 |
.# | +0.121 |
\\ | +0.120 |
SEE | +0.120 |
Neg logit contributions | |
�� | -0.128 |
esty | -0.127 |
Dickinson | -0.126 |
allic | -0.126 |
Lund | -0.125 |
Token | vious |
Token ID | 1442 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
sent | +0.354 |
kins | +0.348 |
.# | +0.345 |
\\ | +0.341 |
SEE | +0.341 |
Neg logit contributions | |
�� | -0.397 |
esty | -0.393 |
Dickinson | -0.392 |
allic | -0.390 |
Lund | -0.388 |
Token | ) |
Token ID | 8 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
esty | +2.131 |
Lund | +2.112 |
Dickinson | +2.096 |
�� | +2.094 |
allic | +2.093 |
Neg logit contributions | |
sent | -1.905 |
kins | -1.889 |
SEE | -1.855 |
.# | -1.841 |
\\ | -1.820 |
Token | CAT |
Token ID | 38348 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
sent | +0.103 |
kins | +0.101 |
.# | +0.100 |
SEE | +0.099 |
\\ | +0.098 |
Neg logit contributions | |
�� | -0.122 |
esty | -0.122 |
Dickinson | -0.121 |
Lund | -0.121 |
allic | -0.121 |
Token | F |
Token ID | 37 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
�� | +1.105 |
esty | +1.101 |
allic | +1.091 |
Lund | +1.091 |
Dickinson | +1.090 |
Neg logit contributions | |
sent | -0.813 |
kins | -0.793 |
.# | -0.783 |
\\ | -0.772 |
SEE | -0.770 |
Token | ISH |
Token ID | 18422 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
esty | +0.708 |
�� | +0.707 |
Dickinson | +0.696 |
abbit | +0.693 |
allic | +0.693 |
Neg logit contributions | |
sent | -0.671 |
kins | -0.656 |
.# | -0.646 |
\\ | -0.641 |
Tab | -0.637 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
sent | +0.003 |
kins | +0.003 |
.# | +0.003 |
SEE | +0.003 |
\\ | +0.003 |
Neg logit contributions | |
�� | -0.004 |
esty | -0.004 |
Dickinson | -0.004 |
Lund | -0.004 |
allic | -0.004 |
Token | f |
Token ID | 69 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
�� | +0.840 |
esty | +0.831 |
Dickinson | +0.828 |
allic | +0.824 |
Lund | +0.822 |
Neg logit contributions | |
sent | -0.738 |
kins | -0.725 |
.# | -0.719 |
\\ | -0.709 |
SEE | -0.709 |
Token | ); |
Token ID | 1776 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
�� | +0.200 |
esty | +0.197 |
Dickinson | +0.196 |
allic | +0.195 |
Lund | +0.194 |
Neg logit contributions | |
sent | -0.188 |
kins | -0.184 |
.# | -0.184 |
\\ | -0.181 |
SEE | -0.180 |
Token | RAW |
Token ID | 33782 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
�� | +1.211 |
esty | +1.200 |
Dickinson | +1.194 |
Lund | +1.193 |
allic | +1.185 |
Neg logit contributions | |
sent | -1.051 |
kins | -1.034 |
.# | -1.010 |
SEE | -0.999 |
Tab | -0.994 |
Token | _ |
Token ID | 62 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
�� | +0.141 |
esty | +0.138 |
Dickinson | +0.137 |
allic | +0.137 |
Lund | +0.137 |
Neg logit contributions | |
sent | -0.073 |
kins | -0.070 |
.# | -0.070 |
\\ | -0.069 |
SEE | -0.069 |
Token | ASS |
Token ID | 10705 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
esty | +0.904 |
�� | +0.902 |
allic | +0.900 |
Lund | +0.895 |
Dickinson | +0.894 |
Neg logit contributions | |
sent | -0.577 |
kins | -0.571 |
.# | -0.560 |
Limit | -0.548 |
\\ | -0.546 |
Token | ERT |
Token ID | 17395 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
esty | +1.124 |
�� | +1.122 |
Dickinson | +1.118 |
allic | +1.116 |
Lund | +1.114 |
Neg logit contributions | |
sent | -0.480 |
kins | -0.473 |
.# | -0.457 |
SEE | -0.450 |
\\ | -0.448 |
Token | ( |
Token ID | 7 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
esty | +2.870 |
Dickinson | +2.868 |
Lund | +2.862 |
allic | +2.859 |
abbit | +2.845 |
Neg logit contributions | |
sent | -1.087 |
kins | -1.079 |
.# | -1.026 |
SEE | -1.007 |
Limit | -0.997 |
Token | it |
Token ID | 270 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
�� | +0.481 |
Dickinson | +0.468 |
esty | +0.464 |
Lund | +0.464 |
allic | +0.461 |
Neg logit contributions | |
sent | -0.582 |
kins | -0.572 |
.# | -0.569 |
\\ | -0.565 |
SEE | -0.560 |
Token | -> |
Token ID | 3784 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
�� | +0.551 |
esty | +0.546 |
Dickinson | +0.543 |
allic | +0.541 |
Lund | +0.541 |
Neg logit contributions | |
sent | -0.191 |
kins | -0.185 |
.# | -0.183 |
\\ | -0.179 |
SEE | -0.178 |
Token | f |
Token ID | 69 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
�� | +0.128 |
esty | +0.127 |
Dickinson | +0.127 |
allic | +0.126 |
Lund | +0.126 |
Neg logit contributions | |
sent | -0.162 |
kins | -0.159 |
.# | -0.158 |
SEE | -0.157 |
\\ | -0.156 |
Token | () |
Token ID | 3419 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
�� | +0.366 |
esty | +0.365 |
Dickinson | +0.362 |
allic | +0.362 |
Lund | +0.360 |
Neg logit contributions | |
sent | -0.265 |
kins | -0.260 |
.# | -0.258 |
SEE | -0.254 |
\\ | -0.254 |
Token | di |
Token ID | 10989 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
esty | +1.859 |
�� | +1.846 |
allic | +1.844 |
Dickinson | +1.838 |
Lund | +1.834 |
Neg logit contributions | |
sent | -1.431 |
kins | -1.408 |
.# | -1.405 |
SEE | -1.393 |
\\ | -1.382 |
Token | |
Token ID | 3907 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
sent | +0.030 |
kins | +0.029 |
.# | +0.029 |
SEE | +0.029 |
\\ | +0.028 |
Neg logit contributions | |
�� | -0.034 |
esty | -0.034 |
Dickinson | -0.034 |
allic | -0.034 |
Lund | -0.034 |
Token | um |
Token ID | 388 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
esty | +2.325 |
allic | +2.310 |
�� | +2.306 |
Lund | +2.287 |
Dickinson | +2.283 |
Neg logit contributions | |
sent | -0.923 |
kins | -0.917 |
.# | -0.908 |
SEE | -0.905 |
\\ | -0.897 |
Token | and |
Token ID | 290 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
�� | +0.277 |
esty | +0.275 |
Dickinson | +0.274 |
allic | +0.273 |
Lund | +0.272 |
Neg logit contributions | |
sent | -0.226 |
kins | -0.222 |
.# | -0.221 |
SEE | -0.218 |
\\ | -0.217 |
Token | al |
Token ID | 435 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
�� | +0.020 |
esty | +0.020 |
Dickinson | +0.019 |
allic | +0.019 |
Lund | +0.019 |
Neg logit contributions | |
sent | -0.018 |
kins | -0.018 |
.# | -0.017 |
SEE | -0.017 |
\\ | -0.017 |
Token | |
Token ID | 3907 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
esty | +0.231 |
�� | +0.231 |
Dickinson | +0.229 |
allic | +0.229 |
Lund | +0.228 |
Neg logit contributions | |
sent | -0.204 |
kins | -0.200 |
.# | -0.199 |
SEE | -0.197 |
\\ | -0.195 |
Token | l |
Token ID | 75 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
esty | +2.085 |
�� | +2.075 |
allic | +2.042 |
Lund | +2.038 |
abbit | +2.033 |
Neg logit contributions | |
sent | -1.855 |
.# | -1.827 |
kins | -1.825 |
SEE | -1.814 |
\\ | -1.800 |
Token | owed |
Token ID | 6972 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
esty | +1.148 |
�� | +1.140 |
allic | +1.130 |
Dickinson | +1.125 |
Lund | +1.125 |
Neg logit contributions | |
sent | -1.230 |
kins | -1.212 |
.# | -1.204 |
SEE | -1.198 |
Limit | -1.186 |
Token | only |
Token ID | 691 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
�� | +0.399 |
esty | +0.398 |
Dickinson | +0.396 |
Lund | +0.394 |
allic | +0.393 |
Neg logit contributions | |
sent | -0.361 |
kins | -0.356 |
.# | -0.353 |
SEE | -0.349 |
\\ | -0.347 |
Token | a |
Token ID | 257 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
�� | +0.201 |
esty | +0.200 |
Dickinson | +0.199 |
Lund | +0.198 |
allic | +0.198 |
Neg logit contributions | |
sent | -0.182 |
kins | -0.179 |
.# | -0.177 |
SEE | -0.176 |
\\ | -0.175 |
Token | brief |
Token ID | 4506 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
�� | +0.014 |
esty | +0.014 |
Dickinson | +0.014 |
allic | +0.014 |
Lund | +0.014 |
Neg logit contributions | |
sent | -0.013 |
kins | -0.013 |
.# | -0.013 |
SEE | -0.012 |
\\ | -0.012 |
Token | count |
Token ID | 9127 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
�� | +0.506 |
esty | +0.506 |
allic | +0.500 |
Dickinson | +0.500 |
Lund | +0.498 |
Neg logit contributions | |
sent | -0.397 |
kins | -0.390 |
.# | -0.386 |
SEE | -0.380 |
\\ | -0.379 |
Token | )); |
Token ID | 18125 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
�� | +0.620 |
esty | +0.620 |
Dickinson | +0.616 |
allic | +0.615 |
Lund | +0.612 |
Neg logit contributions | |
sent | -0.325 |
kins | -0.316 |
.# | -0.313 |
SEE | -0.309 |
\\ | -0.306 |
Token | RAW |
Token ID | 33782 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
�� | +0.766 |
esty | +0.763 |
Dickinson | +0.759 |
Lund | +0.757 |
allic | +0.754 |
Neg logit contributions | |
sent | -0.628 |
kins | -0.618 |
.# | -0.607 |
SEE | -0.600 |
\\ | -0.596 |
Token | _ |
Token ID | 62 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
sent | +0.014 |
.# | +0.014 |
kins | +0.014 |
\\ | +0.013 |
SEE | +0.013 |
Neg logit contributions | |
�� | -0.028 |
esty | -0.027 |
Dickinson | -0.027 |
allic | -0.027 |
Lund | -0.027 |
Token | ASS |
Token ID | 10705 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
�� | +0.786 |
esty | +0.785 |
allic | +0.780 |
abbit | +0.775 |
Lund | +0.773 |
Neg logit contributions | |
sent | -0.504 |
kins | -0.500 |
.# | -0.491 |
Limit | -0.480 |
\\ | -0.479 |
Token | ERT |
Token ID | 17395 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
�� | +0.981 |
esty | +0.981 |
Dickinson | +0.977 |
allic | +0.974 |
Lund | +0.973 |
Neg logit contributions | |
sent | -0.413 |
kins | -0.406 |
.# | -0.395 |
SEE | -0.388 |
\\ | -0.386 |
Token | ( |
Token ID | 7 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
�� | +2.746 |
esty | +2.739 |
Lund | +2.716 |
Dickinson | +2.708 |
abbit | +2.706 |
Neg logit contributions | |
sent | -1.149 |
kins | -1.149 |
.# | -1.090 |
Limit | -1.060 |
SEE | -1.053 |
Token | it |
Token ID | 270 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
�� | +0.406 |
esty | +0.405 |
allic | +0.399 |
Dickinson | +0.398 |
Lund | +0.396 |
Neg logit contributions | |
sent | -0.516 |
kins | -0.510 |
.# | -0.506 |
SEE | -0.500 |
\\ | -0.498 |
Token | -> |
Token ID | 3784 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
�� | +0.638 |
esty | +0.631 |
Dickinson | +0.627 |
Lund | +0.625 |
allic | +0.625 |
Neg logit contributions | |
sent | -0.219 |
kins | -0.212 |
.# | -0.211 |
\\ | -0.206 |
SEE | -0.204 |
Token | i |
Token ID | 72 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
�� | +0.124 |
esty | +0.123 |
Dickinson | +0.123 |
allic | +0.122 |
Lund | +0.122 |
Neg logit contributions | |
sent | -0.113 |
kins | -0.111 |
.# | -0.111 |
SEE | -0.109 |
\\ | -0.109 |
Token | () |
Token ID | 3419 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
�� | +1.395 |
esty | +1.392 |
allic | +1.386 |
Lund | +1.378 |
Dickinson | +1.375 |
Neg logit contributions | |
sent | -0.807 |
kins | -0.786 |
.# | -0.770 |
SEE | -0.764 |
\\ | -0.754 |
Token | prime |
Token ID | 35505 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
�� | +0.363 |
esty | +0.360 |
Dickinson | +0.358 |
allic | +0.357 |
Lund | +0.356 |
Neg logit contributions | |
sent | -0.317 |
kins | -0.312 |
.# | -0.309 |
SEE | -0.305 |
\\ | -0.305 |
Token | - |
Token ID | 12 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
�� | +0.667 |
esty | +0.665 |
Dickinson | +0.662 |
allic | +0.658 |
Lund | +0.658 |
Neg logit contributions | |
sent | -0.576 |
kins | -0.569 |
.# | -0.563 |
SEE | -0.556 |
\\ | -0.554 |
Token | time |
Token ID | 2435 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
esty | +0.224 |
�� | +0.223 |
allic | +0.221 |
Dickinson | +0.221 |
Lund | +0.220 |
Neg logit contributions | |
sent | -0.212 |
kins | -0.211 |
.# | -0.209 |
SEE | -0.206 |
\\ | -0.206 |
Token | video |
Token ID | 2008 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
sent | +0.656 |
kins | +0.642 |
.# | +0.640 |
\\ | +0.631 |
SEE | +0.630 |
Neg logit contributions | |
�� | -0.777 |
esty | -0.764 |
allic | -0.760 |
Dickinson | -0.758 |
Lund | -0.753 |
Token | mes |
Token ID | 18842 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
sent | +0.188 |
kins | +0.184 |
.# | +0.183 |
SEE | +0.180 |
\\ | +0.180 |
Neg logit contributions | |
�� | -0.220 |
esty | -0.218 |
Dickinson | -0.216 |
allic | -0.216 |
Lund | -0.215 |
Token | |
Token ID | 3907 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
�� | +0.253 |
esty | +0.250 |
Dickinson | +0.250 |
allic | +0.248 |
Lund | +0.248 |
Neg logit contributions | |
sent | -0.209 |
kins | -0.205 |
.# | -0.203 |
\\ | -0.201 |
SEE | -0.201 |
Token | s |
Token ID | 82 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
�� | +1.930 |
esty | +1.917 |
Dickinson | +1.904 |
allic | +1.898 |
Lund | +1.892 |
Neg logit contributions | |
sent | -2.008 |
kins | -1.978 |
.# | -1.964 |
SEE | -1.943 |
\\ | -1.940 |
Token | age |
Token ID | 496 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
�� | +0.804 |
Dickinson | +0.795 |
esty | +0.794 |
Lund | +0.789 |
allic | +0.788 |
Neg logit contributions | |
sent | -0.445 |
kins | -0.432 |
.# | -0.427 |
\\ | -0.421 |
SEE | -0.417 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
�� | +0.400 |
esty | +0.398 |
Dickinson | +0.396 |
allic | +0.394 |
Lund | +0.394 |
Neg logit contributions | |
sent | -0.316 |
kins | -0.311 |
.# | -0.307 |
SEE | -0.304 |
\\ | -0.303 |
Token | This |
Token ID | 770 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
�� | +0.107 |
esty | +0.106 |
Dickinson | +0.106 |
Lund | +0.105 |
allic | +0.105 |
Neg logit contributions | |
sent | -0.084 |
kins | -0.082 |
.# | -0.082 |
SEE | -0.081 |
\\ | -0.080 |
Token | led |
Token ID | 2957 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
�� | +0.501 |
esty | +0.498 |
Dickinson | +0.495 |
Lund | +0.493 |
allic | +0.493 |
Neg logit contributions | |
sent | -0.474 |
kins | -0.467 |
.# | -0.463 |
SEE | -0.458 |
\\ | -0.457 |
Token | ing |
Token ID | 278 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
esty | +2.257 |
�� | +2.248 |
Lund | +2.226 |
Dickinson | +2.226 |
allic | +2.225 |
Neg logit contributions | |
sent | -1.410 |
.# | -1.386 |
kins | -1.385 |
SEE | -1.365 |
\\ | -1.353 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
sent | +0.218 |
kins | +0.215 |
.# | +0.213 |
SEE | +0.211 |
\\ | +0.211 |
Neg logit contributions | |
�� | -0.217 |
esty | -0.214 |
Dickinson | -0.212 |
allic | -0.212 |
Lund | -0.211 |
Token | Carter |
Token ID | 10831 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
sent | +0.703 |
kins | +0.693 |
.# | +0.688 |
SEE | +0.679 |
\\ | +0.679 |
Neg logit contributions | |
�� | -0.727 |
esty | -0.720 |
Dickinson | -0.715 |
allic | -0.713 |
Lund | -0.710 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
�� | +0.137 |
esty | +0.136 |
Dickinson | +0.135 |
allic | +0.135 |
Lund | +0.134 |
Neg logit contributions | |
sent | -0.115 |
kins | -0.113 |
.# | -0.112 |
SEE | -0.111 |
\\ | -0.111 |
Token | Al |
Token ID | 978 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
�� | +0.316 |
Dickinson | +0.314 |
esty | +0.314 |
Lund | +0.313 |
allic | +0.312 |
Neg logit contributions | |
sent | -0.258 |
kins | -0.254 |
.# | -0.251 |
SEE | -0.248 |
\\ | -0.247 |
Token | |
Token ID | 3907 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
esty | +0.314 |
�� | +0.311 |
Lund | +0.310 |
Dickinson | +0.310 |
allic | +0.308 |
Neg logit contributions | |
sent | -0.293 |
kins | -0.288 |
.# | -0.286 |
SEE | -0.284 |
\\ | -0.281 |
Token | though |
Token ID | 2016 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
esty | +2.060 |
�� | +2.054 |
allic | +2.024 |
Dickinson | +2.020 |
Lund | +2.019 |
Neg logit contributions | |
sent | -1.843 |
kins | -1.810 |
.# | -1.809 |
SEE | -1.799 |
\\ | -1.782 |
Token | he |
Token ID | 339 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
sent | +0.269 |
kins | +0.265 |
.# | +0.263 |
\\ | +0.260 |
SEE | +0.260 |
Neg logit contributions | |
�� | -0.282 |
esty | -0.279 |
Dickinson | -0.278 |
allic | -0.277 |
Lund | -0.275 |
Token | left |
Token ID | 1364 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
�� | +0.252 |
esty | +0.250 |
Dickinson | +0.249 |
allic | +0.248 |
Lund | +0.247 |
Neg logit contributions | |
sent | -0.235 |
kins | -0.231 |
.# | -0.229 |
\\ | -0.226 |
SEE | -0.226 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
�� | +0.546 |
esty | +0.543 |
Dickinson | +0.540 |
allic | +0.538 |
Lund | +0.538 |
Neg logit contributions | |
sent | -0.427 |
kins | -0.420 |
.# | -0.416 |
SEE | -0.411 |
\\ | -0.410 |
Token | White |
Token ID | 2635 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
�� | +0.047 |
esty | +0.047 |
Dickinson | +0.047 |
allic | +0.047 |
Lund | +0.046 |
Neg logit contributions | |
sent | -0.042 |
kins | -0.041 |
.# | -0.041 |
\\ | -0.040 |
SEE | -0.040 |
Token | Act |
Token ID | 2191 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
sent | +0.081 |
kins | +0.080 |
.# | +0.079 |
SEE | +0.078 |
\\ | +0.077 |
Neg logit contributions | |
�� | -0.092 |
esty | -0.092 |
Dickinson | -0.092 |
Lund | -0.091 |
allic | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
�� | +0.209 |
esty | +0.208 |
Dickinson | +0.207 |
Lund | +0.206 |
allic | +0.206 |
Neg logit contributions | |
sent | -0.196 |
kins | -0.194 |
.# | -0.191 |
SEE | -0.189 |
\\ | -0.188 |
Token | there |
Token ID | 612 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +0.109 |
esty | +0.108 |
Dickinson | +0.108 |
allic | +0.107 |
Lund | +0.107 |
Neg logit contributions | |
sent | -0.092 |
kins | -0.091 |
.# | -0.090 |
SEE | -0.089 |
\\ | -0.089 |
Token | are |
Token ID | 389 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
sent | +0.080 |
kins | +0.079 |
.# | +0.078 |
\\ | +0.077 |
SEE | +0.077 |
Neg logit contributions | |
�� | -0.086 |
esty | -0.085 |
Dickinson | -0.084 |
allic | -0.084 |
Lund | -0.084 |
Token | 223 |
Token ID | 30299 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
�� | +0.292 |
esty | +0.289 |
Dickinson | +0.288 |
allic | +0.287 |
Lund | +0.286 |
Neg logit contributions | |
sent | -0.269 |
kins | -0.265 |
.# | -0.263 |
SEE | -0.260 |
\\ | -0.260 |
Token | Sections |
Token ID | 37703 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
�� | +0.125 |
esty | +0.124 |
Dickinson | +0.123 |
allic | +0.123 |
Lund | +0.123 |
Neg logit contributions | |
sent | -0.111 |
kins | -0.109 |
.# | -0.108 |
SEE | -0.107 |
\\ | -0.107 |
Token | out |
Token ID | 503 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
�� | +2.109 |
esty | +2.107 |
Dickinson | +2.100 |
Lund | +2.099 |
allic | +2.093 |
Neg logit contributions | |
sent | -1.733 |
kins | -1.706 |
SEE | -1.666 |
.# | -1.665 |
\\ | -1.648 |
Token | of |
Token ID | 286 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
�� | +0.061 |
esty | +0.061 |
Dickinson | +0.061 |
Lund | +0.061 |
allic | +0.060 |
Neg logit contributions | |
sent | -0.045 |
kins | -0.045 |
.# | -0.044 |
SEE | -0.043 |
\\ | -0.043 |
Token | which |
Token ID | 543 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
�� | +0.137 |
esty | +0.136 |
Dickinson | +0.136 |
allic | +0.135 |
Lund | +0.135 |
Neg logit contributions | |
sent | -0.109 |
kins | -0.107 |
.# | -0.106 |
SEE | -0.105 |
\\ | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +0.242 |
esty | +0.239 |
Dickinson | +0.238 |
allic | +0.237 |
Lund | +0.236 |
Neg logit contributions | |
sent | -0.190 |
kins | -0.186 |
.# | -0.186 |
\\ | -0.183 |
SEE | -0.183 |
Token | Bill |
Token ID | 3941 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
�� | +0.133 |
esty | +0.132 |
Dickinson | +0.131 |
allic | +0.131 |
Lund | +0.130 |
Neg logit contributions | |
sent | -0.114 |
kins | -0.112 |
.# | -0.111 |
SEE | -0.110 |
\\ | -0.110 |
Token | T |
Token ID | 309 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
�� | +0.728 |
esty | +0.727 |
Dickinson | +0.724 |
allic | +0.721 |
Lund | +0.720 |
Neg logit contributions | |
sent | -0.376 |
kins | -0.374 |
.# | -0.366 |
SEE | -0.357 |
\\ | -0.353 |
Token | > |
Token ID | 1875 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Dickinson | +0.467 |
esty | +0.467 |
�� | +0.466 |
allic | +0.464 |
Lund | +0.464 |
Neg logit contributions | |
sent | -0.287 |
kins | -0.281 |
.# | -0.278 |
SEE | -0.272 |
\\ | -0.271 |
Token | { |
Token ID | 1391 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
�� | +0.323 |
esty | +0.322 |
Dickinson | +0.321 |
allic | +0.320 |
Lund | +0.320 |
Neg logit contributions | |
sent | -0.134 |
kins | -0.130 |
.# | -0.128 |
SEE | -0.126 |
\\ | -0.125 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
esty | +0.186 |
�� | +0.186 |
Dickinson | +0.185 |
Lund | +0.185 |
allic | +0.184 |
Neg logit contributions | |
sent | -0.117 |
kins | -0.115 |
.# | -0.113 |
SEE | -0.112 |
\\ | -0.111 |
Token | } |
Token ID | 1782 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
�� | +0.167 |
esty | +0.166 |
Dickinson | +0.165 |
allic | +0.165 |
Lund | +0.165 |
Neg logit contributions | |
sent | -0.114 |
kins | -0.112 |
.# | -0.111 |
SEE | -0.109 |
\\ | -0.109 |
Token | impl |
Token ID | 4114 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
sent | +0.177 |
kins | +0.174 |
.# | +0.173 |
SEE | +0.171 |
\\ | +0.170 |
Neg logit contributions | |
�� | -0.193 |
esty | -0.192 |
Dickinson | -0.191 |
allic | -0.190 |
Lund | -0.190 |
Token | < |
Token ID | 1279 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Dickinson | +2.156 |
Lund | +2.145 |
esty | +2.142 |
�� | +2.135 |
allic | +2.132 |
Neg logit contributions | |
sent | -1.696 |
kins | -1.661 |
SEE | -1.647 |
.# | -1.627 |
Tab | -1.595 |
Token | T |
Token ID | 309 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
�� | +0.443 |
esty | +0.442 |
Dickinson | +0.441 |
allic | +0.440 |
Lund | +0.439 |
Neg logit contributions | |
sent | -0.232 |
kins | -0.229 |
.# | -0.224 |
SEE | -0.221 |
\\ | -0.218 |
Token | > |
Token ID | 1875 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
esty | +0.289 |
Dickinson | +0.289 |
�� | +0.289 |
allic | +0.288 |
Lund | +0.287 |
Neg logit contributions | |
sent | -0.184 |
kins | -0.181 |
.# | -0.179 |
\\ | -0.175 |
SEE | -0.175 |
Token | Own |
Token ID | 11744 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
�� | +0.105 |
esty | +0.105 |
Dickinson | +0.104 |
allic | +0.104 |
Lund | +0.104 |
Neg logit contributions | |
sent | -0.081 |
kins | -0.079 |
.# | -0.079 |
SEE | -0.078 |
\\ | -0.077 |
Token | ed |
Token ID | 276 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
�� | +0.395 |
esty | +0.394 |
Dickinson | +0.392 |
allic | +0.391 |
Lund | +0.390 |
Neg logit contributions | |
sent | -0.259 |
kins | -0.254 |
.# | -0.252 |
SEE | -0.248 |
\\ | -0.247 |
Token | f |
Token ID | 69 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
�� | +0.823 |
esty | +0.813 |
Dickinson | +0.810 |
allic | +0.806 |
Lund | +0.805 |
Neg logit contributions | |
sent | -0.717 |
kins | -0.704 |
.# | -0.698 |
\\ | -0.689 |
SEE | -0.688 |
Token | ); |
Token ID | 1776 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
�� | +0.242 |
esty | +0.238 |
Dickinson | +0.236 |
allic | +0.235 |
Lund | +0.235 |
Neg logit contributions | |
sent | -0.223 |
kins | -0.218 |
.# | -0.218 |
\\ | -0.215 |
SEE | -0.214 |
Token | RAW |
Token ID | 33782 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
�� | +1.171 |
esty | +1.161 |
Dickinson | +1.155 |
Lund | +1.154 |
allic | +1.148 |
Neg logit contributions | |
sent | -1.011 |
kins | -0.994 |
.# | -0.973 |
SEE | -0.961 |
Tab | -0.957 |
Token | _ |
Token ID | 62 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
�� | +0.065 |
esty | +0.064 |
Dickinson | +0.063 |
allic | +0.063 |
Lund | +0.063 |
Neg logit contributions | |
sent | -0.033 |
.# | -0.032 |
kins | -0.032 |
\\ | -0.032 |
SEE | -0.032 |
Token | ASS |
Token ID | 10705 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
esty | +0.837 |
�� | +0.836 |
allic | +0.834 |
Dickinson | +0.829 |
Lund | +0.829 |
Neg logit contributions | |
sent | -0.531 |
kins | -0.525 |
.# | -0.515 |
Limit | -0.505 |
\\ | -0.503 |
Token | ERT |
Token ID | 17395 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
esty | +0.997 |
�� | +0.996 |
Dickinson | +0.992 |
allic | +0.990 |
Lund | +0.988 |
Neg logit contributions | |
sent | -0.424 |
kins | -0.417 |
.# | -0.404 |
SEE | -0.397 |
\\ | -0.396 |
Token | ( |
Token ID | 7 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
esty | +2.733 |
Dickinson | +2.719 |
Lund | +2.717 |
allic | +2.711 |
abbit | +2.708 |
Neg logit contributions | |
sent | -1.086 |
kins | -1.080 |
.# | -1.026 |
SEE | -1.003 |
Limit | -0.997 |
Token | it |
Token ID | 270 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
�� | +0.397 |
Dickinson | +0.389 |
esty | +0.387 |
Lund | +0.385 |
allic | +0.383 |
Neg logit contributions | |
sent | -0.490 |
kins | -0.483 |
.# | -0.480 |
\\ | -0.476 |
SEE | -0.473 |
Token | -> |
Token ID | 3784 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +0.362 |
esty | +0.358 |
Dickinson | +0.356 |
Lund | +0.354 |
allic | +0.354 |
Neg logit contributions | |
sent | -0.123 |
kins | -0.120 |
.# | -0.119 |
\\ | -0.116 |
SEE | -0.115 |
Token | vec |
Token ID | 35138 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
�� | +0.109 |
esty | +0.108 |
Dickinson | +0.107 |
allic | +0.107 |
Lund | +0.106 |
Neg logit contributions | |
sent | -0.139 |
kins | -0.137 |
.# | -0.137 |
SEE | -0.135 |
\\ | -0.135 |
Token | () |
Token ID | 3419 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
�� | +0.384 |
esty | +0.376 |
Dickinson | +0.374 |
allic | +0.371 |
Lund | +0.370 |
Neg logit contributions | |
sent | -0.180 |
kins | -0.176 |
.# | -0.175 |
\\ | -0.172 |
SEE | -0.170 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
sent | +0.005 |
kins | +0.005 |
.# | +0.005 |
SEE | +0.005 |
\\ | +0.005 |
Neg logit contributions | |
�� | -0.007 |
esty | -0.007 |
Dickinson | -0.007 |
allic | -0.007 |
Lund | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
sent | +0.123 |
kins | +0.121 |
.# | +0.121 |
\\ | +0.119 |
SEE | +0.118 |
Neg logit contributions | |
�� | -0.170 |
esty | -0.164 |
Dickinson | -0.163 |
allic | -0.162 |
abbit | -0.162 |
Token | Clearly |
Token ID | 30638 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
sent | +0.123 |
kins | +0.120 |
.# | +0.119 |
SEE | +0.118 |
\\ | +0.117 |
Neg logit contributions | |
�� | -0.203 |
esty | -0.201 |
Dickinson | -0.200 |
allic | -0.199 |
Lund | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
esty | +0.874 |
�� | +0.870 |
Dickinson | +0.869 |
Lund | +0.869 |
allic | +0.862 |
Neg logit contributions | |
sent | -0.808 |
kins | -0.792 |
.# | -0.779 |
SEE | -0.775 |
\\ | -0.773 |
Token | any |
Token ID | 597 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
�� | +0.068 |
esty | +0.067 |
Dickinson | +0.067 |
allic | +0.067 |
Lund | +0.066 |
Neg logit contributions | |
sent | -0.058 |
kins | -0.057 |
.# | -0.057 |
SEE | -0.056 |
\\ | -0.056 |
Token | sort |
Token ID | 3297 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
sent | +0.008 |
kins | +0.008 |
.# | +0.008 |
SEE | +0.008 |
\\ | +0.008 |
Neg logit contributions | |
�� | -0.009 |
esty | -0.009 |
Dickinson | -0.009 |
allic | -0.009 |
Lund | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
esty | +2.218 |
�� | +2.211 |
Dickinson | +2.202 |
allic | +2.198 |
Lund | +2.192 |
Neg logit contributions | |
sent | -1.614 |
kins | -1.586 |
.# | -1.569 |
SEE | -1.556 |
\\ | -1.545 |
Token | outdoor |
Token ID | 15162 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
sent | +0.300 |
.# | +0.295 |
kins | +0.295 |
\\ | +0.290 |
SEE | +0.289 |
Neg logit contributions | |
�� | -0.332 |
esty | -0.322 |
allic | -0.322 |
abbit | -0.320 |
Dickinson | -0.320 |
Token | setting |
Token ID | 4634 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
�� | +0.389 |
esty | +0.382 |
Dickinson | +0.380 |
allic | +0.379 |
Lund | +0.377 |
Neg logit contributions | |
sent | -0.377 |
kins | -0.371 |
.# | -0.369 |
\\ | -0.364 |
SEE | -0.364 |
Token | is |
Token ID | 318 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
�� | +0.858 |
esty | +0.847 |
Dickinson | +0.842 |
allic | +0.840 |
Lund | +0.836 |
Neg logit contributions | |
sent | -0.762 |
kins | -0.750 |
.# | -0.745 |
\\ | -0.735 |
SEE | -0.734 |
Token | going |
Token ID | 1016 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
�� | +0.262 |
esty | +0.256 |
Dickinson | +0.254 |
allic | +0.253 |
Lund | +0.252 |
Neg logit contributions | |
sent | -0.259 |
kins | -0.255 |
.# | -0.255 |
\\ | -0.252 |
SEE | -0.250 |
Token | � |
Token ID | 251 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
sent | +0.065 |
.# | +0.064 |
kins | +0.064 |
\\ | +0.063 |
SEE | +0.062 |
Neg logit contributions | |
�� | -0.082 |
allic | -0.082 |
esty | -0.081 |
Dickinson | -0.081 |
abbit | -0.081 |
Token | she |
Token ID | 673 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
sent | +0.075 |
kins | +0.073 |
.# | +0.073 |
SEE | +0.072 |
\\ | +0.072 |
Neg logit contributions | |
�� | -0.096 |
esty | -0.095 |
Dickinson | -0.095 |
allic | -0.094 |
Lund | -0.094 |
Token | said |
Token ID | 531 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
sent | +0.107 |
kins | +0.105 |
.# | +0.104 |
\\ | +0.103 |
SEE | +0.102 |
Neg logit contributions | |
�� | -0.116 |
esty | -0.112 |
allic | -0.112 |
abbit | -0.111 |
Dickinson | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
�� | +0.136 |
esty | +0.136 |
Dickinson | +0.135 |
allic | +0.134 |
Lund | +0.134 |
Neg logit contributions | |
sent | -0.112 |
kins | -0.110 |
.# | -0.109 |
SEE | -0.108 |
\\ | -0.108 |
Token | before |
Token ID | 878 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
sent | +0.044 |
kins | +0.044 |
.# | +0.043 |
SEE | +0.043 |
\\ | +0.043 |
Neg logit contributions | |
�� | -0.047 |
esty | -0.047 |
Dickinson | -0.047 |
allic | -0.046 |
Lund | -0.046 |
Token | clicking |
Token ID | 12264 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
sent | +0.081 |
kins | +0.080 |
.# | +0.079 |
SEE | +0.078 |
\\ | +0.078 |
Neg logit contributions | |
�� | -0.082 |
allic | -0.080 |
esty | -0.080 |
abbit | -0.080 |
Dickinson | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
esty | +1.997 |
Dickinson | +1.987 |
Lund | +1.981 |
�� | +1.973 |
allic | +1.968 |
Neg logit contributions | |
sent | -1.815 |
kins | -1.786 |
SEE | -1.764 |
.# | -1.762 |
\\ | -1.755 |
Token | shutter |
Token ID | 31168 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
sent | +0.071 |
kins | +0.070 |
.# | +0.070 |
SEE | +0.069 |
\\ | +0.069 |
Neg logit contributions | |
�� | -0.046 |
esty | -0.046 |
Dickinson | -0.045 |
allic | -0.045 |
Lund | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
�� | +0.775 |
esty | +0.772 |
Dickinson | +0.768 |
allic | +0.765 |
Lund | +0.764 |
Neg logit contributions | |
sent | -0.550 |
kins | -0.540 |
.# | -0.534 |
SEE | -0.528 |
\\ | -0.527 |
Token | The |
Token ID | 383 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
sent | +0.116 |
kins | +0.114 |
.# | +0.112 |
SEE | +0.111 |
\\ | +0.111 |
Neg logit contributions | |
�� | -0.151 |
esty | -0.150 |
Dickinson | -0.150 |
Lund | -0.149 |
allic | -0.149 |
Token | man |
Token ID | 582 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
sent | +0.082 |
kins | +0.081 |
.# | +0.081 |
SEE | +0.079 |
\\ | +0.079 |
Neg logit contributions | |
�� | -0.082 |
esty | -0.081 |
allic | -0.080 |
Dickinson | -0.080 |
Lund | -0.079 |
Token | ; |
Token ID | 26 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
�� | +0.525 |
esty | +0.522 |
Dickinson | +0.519 |
allic | +0.518 |
Lund | +0.516 |
Neg logit contributions | |
sent | -0.469 |
kins | -0.461 |
.# | -0.457 |
SEE | -0.452 |
\\ | -0.450 |
Token | } |
Token ID | 1782 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
�� | +1.123 |
esty | +1.118 |
Dickinson | +1.113 |
Lund | +1.110 |
allic | +1.106 |
Neg logit contributions | |
sent | -0.870 |
kins | -0.856 |
.# | -0.844 |
SEE | -0.832 |
\\ | -0.829 |
Token | RAW |
Token ID | 33782 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
�� | +0.527 |
esty | +0.525 |
Dickinson | +0.522 |
Lund | +0.520 |
allic | +0.519 |
Neg logit contributions | |
sent | -0.424 |
kins | -0.417 |
.# | -0.412 |
SEE | -0.407 |
\\ | -0.405 |
Token | _ |
Token ID | 62 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
�� | +0.135 |
esty | +0.133 |
Dickinson | +0.132 |
allic | +0.132 |
Lund | +0.132 |
Neg logit contributions | |
sent | -0.069 |
.# | -0.067 |
kins | -0.067 |
\\ | -0.066 |
SEE | -0.066 |
Token | ASS |
Token ID | 10705 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +1.023 |
esty | +1.022 |
allic | +1.016 |
Dickinson | +1.013 |
Lund | +1.011 |
Neg logit contributions | |
sent | -0.642 |
kins | -0.633 |
.# | -0.623 |
\\ | -0.609 |
Limit | -0.606 |
Token | ERT |
Token ID | 17395 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
�� | +1.109 |
esty | +1.107 |
Dickinson | +1.103 |
allic | +1.100 |
Lund | +1.098 |
Neg logit contributions | |
sent | -0.462 |
kins | -0.452 |
.# | -0.441 |
SEE | -0.433 |
\\ | -0.432 |
Token | ( |
Token ID | 7 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
�� | +2.665 |
esty | +2.663 |
Lund | +2.650 |
Dickinson | +2.632 |
abbit | +2.629 |
Neg logit contributions | |
sent | -1.118 |
kins | -1.106 |
.# | -1.056 |
SEE | -1.019 |
\\ | -1.011 |
Token | count |
Token ID | 9127 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
�� | +0.492 |
esty | +0.490 |
Dickinson | +0.485 |
allic | +0.484 |
Lund | +0.483 |
Neg logit contributions | |
sent | -0.490 |
kins | -0.483 |
.# | -0.479 |
SEE | -0.472 |
\\ | -0.471 |
Token | == |
Token ID | 6624 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
�� | +0.366 |
esty | +0.364 |
Dickinson | +0.362 |
allic | +0.360 |
Lund | +0.359 |
Neg logit contributions | |
sent | -0.336 |
kins | -0.331 |
.# | -0.328 |
SEE | -0.324 |
\\ | -0.323 |
Token | 100 |
Token ID | 1802 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
�� | +0.605 |
esty | +0.603 |
Dickinson | +0.599 |
Lund | +0.596 |
allic | +0.595 |
Neg logit contributions | |
sent | -0.553 |
kins | -0.544 |
.# | -0.539 |
SEE | -0.532 |
\\ | -0.531 |
Token | 000 |
Token ID | 830 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
�� | +0.169 |
esty | +0.168 |
Dickinson | +0.167 |
allic | +0.167 |
Lund | +0.166 |
Neg logit contributions | |
sent | -0.166 |
kins | -0.163 |
.# | -0.161 |
SEE | -0.160 |
\\ | -0.159 |
Token | a |
Token ID | 64 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
esty | +1.335 |
�� | +1.333 |
Dickinson | +1.323 |
allic | +1.321 |
Lund | +1.311 |
Neg logit contributions | |
sent | -1.210 |
kins | -1.201 |
.# | -1.187 |
SEE | -1.172 |
Limit | -1.161 |
Token | > |
Token ID | 1875 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
�� | +0.290 |
esty | +0.289 |
Dickinson | +0.288 |
allic | +0.287 |
Lund | +0.286 |
Neg logit contributions | |
sent | -0.187 |
kins | -0.183 |
.# | -0.181 |
SEE | -0.178 |
\\ | -0.177 |
Token | { |
Token ID | 1391 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
�� | +0.275 |
esty | +0.273 |
Dickinson | +0.272 |
allic | +0.272 |
Lund | +0.271 |
Neg logit contributions | |
sent | -0.109 |
kins | -0.106 |
.# | -0.104 |
SEE | -0.102 |
\\ | -0.102 |
Token | ... |
Token ID | 2644 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
�� | +0.336 |
esty | +0.336 |
Lund | +0.335 |
Dickinson | +0.334 |
allic | +0.333 |
Neg logit contributions | |
sent | -0.144 |
kins | -0.141 |
.# | -0.137 |
SEE | -0.136 |
\\ | -0.134 |
Token | } |
Token ID | 1782 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
�� | +0.345 |
esty | +0.343 |
Dickinson | +0.341 |
Lund | +0.341 |
allic | +0.340 |
Neg logit contributions | |
sent | -0.243 |
kins | -0.239 |
.# | -0.236 |
SEE | -0.233 |
\\ | -0.232 |
Token | impl |
Token ID | 4114 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
�� | +0.044 |
esty | +0.044 |
Dickinson | +0.043 |
allic | +0.043 |
Lund | +0.043 |
Neg logit contributions | |
sent | -0.056 |
kins | -0.056 |
.# | -0.055 |
SEE | -0.055 |
\\ | -0.055 |
Token | < |
Token ID | 1279 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Lund | +1.820 |
�� | +1.815 |
esty | +1.815 |
Dickinson | +1.814 |
allic | +1.791 |
Neg logit contributions | |
sent | -1.931 |
kins | -1.900 |
.# | -1.887 |
SEE | -1.866 |
\\ | -1.847 |
Token | ' |
Token ID | 705 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
�� | +0.647 |
esty | +0.645 |
Dickinson | +0.641 |
allic | +0.639 |
Lund | +0.638 |
Neg logit contributions | |
sent | -0.414 |
kins | -0.408 |
.# | -0.401 |
SEE | -0.394 |
\\ | -0.391 |
Token | a |
Token ID | 64 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
esty | +1.083 |
�� | +1.078 |
Dickinson | +1.073 |
allic | +1.073 |
Lund | +1.063 |
Neg logit contributions | |
sent | -1.010 |
kins | -0.997 |
.# | -0.983 |
SEE | -0.969 |
Limit | -0.965 |
Token | , |
Token ID | 837 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
esty | +0.180 |
�� | +0.180 |
Dickinson | +0.179 |
Lund | +0.179 |
allic | +0.179 |
Neg logit contributions | |
sent | -0.138 |
kins | -0.136 |
.# | -0.133 |
SEE | -0.131 |
\\ | -0.131 |
Token | T |
Token ID | 309 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
�� | +0.185 |
esty | +0.184 |
Dickinson | +0.183 |
Lund | +0.183 |
allic | +0.182 |
Neg logit contributions | |
sent | -0.111 |
kins | -0.110 |
.# | -0.108 |
SEE | -0.106 |
\\ | -0.105 |
Token | en |
Token ID | 268 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
esty | +1.795 |
allic | +1.758 |
�� | +1.756 |
Dickinson | +1.754 |
abbit | +1.747 |
Neg logit contributions | |
sent | -1.814 |
kins | -1.795 |
.# | -1.787 |
SEE | -1.779 |
\\ | -1.764 |
Token | |
Token ID | 3907 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
sent | +0.298 |
kins | +0.293 |
.# | +0.290 |
\\ | +0.287 |
SEE | +0.285 |
Neg logit contributions | |
�� | -0.367 |
Dickinson | -0.361 |
esty | -0.361 |
allic | -0.360 |
Lund | -0.357 |
Token | t |
Token ID | 83 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
esty | +2.216 |
�� | +2.186 |
allic | +2.170 |
abbit | +2.158 |
Lund | +2.158 |
Neg logit contributions | |
sent | -1.212 |
kins | -1.210 |
.# | -1.208 |
SEE | -1.190 |
\\ | -1.185 |
Token | ial |
Token ID | 498 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
�� | +0.123 |
Dickinson | +0.121 |
esty | +0.120 |
Lund | +0.119 |
allic | +0.118 |
Neg logit contributions | |
sent | -0.329 |
kins | -0.325 |
.# | -0.323 |
\\ | -0.321 |
SEE | -0.320 |
Token | cam |
Token ID | 12172 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
esty | +1.131 |
Dickinson | +1.127 |
�� | +1.126 |
Lund | +1.124 |
allic | +1.116 |
Neg logit contributions | |
sent | -0.991 |
kins | -0.977 |
.# | -0.964 |
SEE | -0.957 |
\\ | -0.949 |
Token | |
Token ID | 3907 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
�� | +0.438 |
esty | +0.431 |
Dickinson | +0.429 |
allic | +0.428 |
Lund | +0.427 |
Neg logit contributions | |
sent | -0.355 |
kins | -0.348 |
.# | -0.346 |
\\ | -0.342 |
SEE | -0.340 |
Token | p |
Token ID | 79 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
�� | +1.977 |
esty | +1.948 |
Dickinson | +1.942 |
allic | +1.935 |
Lund | +1.931 |
Neg logit contributions | |
sent | -1.806 |
kins | -1.775 |
.# | -1.756 |
\\ | -1.732 |
SEE | -1.732 |
Token | aign |
Token ID | 1784 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
esty | +0.336 |
�� | +0.334 |
allic | +0.333 |
Dickinson | +0.333 |
Lund | +0.331 |
Neg logit contributions | |
sent | -0.334 |
kins | -0.328 |
.# | -0.327 |
SEE | -0.324 |
\\ | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
�� | +0.556 |
esty | +0.556 |
Dickinson | +0.552 |
Lund | +0.550 |
allic | +0.550 |
Neg logit contributions | |
sent | -0.441 |
kins | -0.435 |
.# | -0.429 |
SEE | -0.427 |
\\ | -0.425 |
Token |
|
Token ID | 198 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
sent | +0.054 |
kins | +0.053 |
.# | +0.052 |
SEE | +0.051 |
\\ | +0.051 |
Neg logit contributions | |
�� | -0.067 |
esty | -0.066 |
Dickinson | -0.066 |
Lund | -0.066 |
allic | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
�� | +0.039 |
esty | +0.038 |
Dickinson | +0.037 |
allic | +0.037 |
abbit | +0.037 |
Neg logit contributions | |
sent | -0.028 |
kins | -0.028 |
.# | -0.028 |
\\ | -0.027 |
SEE | -0.027 |
Token | here |
Token ID | 994 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
�� | +0.245 |
esty | +0.241 |
allic | +0.239 |
Dickinson | +0.239 |
Lund | +0.237 |
Neg logit contributions | |
sent | -0.209 |
kins | -0.205 |
.# | -0.204 |
\\ | -0.201 |
SEE | -0.201 |
Token | : |
Token ID | 25 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
�� | +0.284 |
esty | +0.281 |
Dickinson | +0.280 |
allic | +0.279 |
Lund | +0.278 |
Neg logit contributions | |
sent | -0.199 |
kins | -0.195 |
.# | -0.194 |
SEE | -0.191 |
\\ | -0.190 |
Token | ( |
Token ID | 357 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
�� | +0.360 |
esty | +0.358 |
Dickinson | +0.356 |
allic | +0.355 |
Lund | +0.354 |
Neg logit contributions | |
sent | -0.282 |
kins | -0.277 |
.# | -0.275 |
SEE | -0.271 |
\\ | -0.271 |
Token | https |
Token ID | 3740 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
�� | +0.268 |
esty | +0.266 |
Dickinson | +0.265 |
allic | +0.264 |
Lund | +0.263 |
Neg logit contributions | |
sent | -0.214 |
kins | -0.210 |
.# | -0.209 |
SEE | -0.206 |
\\ | -0.206 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
�� | +0.635 |
esty | +0.628 |
Dickinson | +0.625 |
Lund | +0.623 |
allic | +0.623 |
Neg logit contributions | |
sent | -0.231 |
kins | -0.224 |
.# | -0.222 |
\\ | -0.216 |
SEE | -0.215 |
Token | www |
Token ID | 2503 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
�� | +0.851 |
esty | +0.850 |
allic | +0.843 |
Dickinson | +0.843 |
Lund | +0.839 |
Neg logit contributions | |
sent | -0.611 |
kins | -0.601 |
.# | -0.597 |
SEE | -0.590 |
\\ | -0.587 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
esty | +2.198 |
allic | +2.196 |
Dickinson | +2.190 |
Lund | +2.179 |
abbit | +2.170 |
Neg logit contributions | |
sent | -1.501 |
kins | -1.476 |
SEE | -1.454 |
.# | -1.445 |
Limit | -1.434 |
Token | cor |
Token ID | 10215 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
�� | +0.770 |
esty | +0.762 |
Dickinson | +0.759 |
allic | +0.754 |
Lund | +0.753 |
Neg logit contributions | |
sent | -0.741 |
kins | -0.728 |
.# | -0.722 |
SEE | -0.713 |
\\ | -0.713 |
Token | vette |
Token ID | 33573 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
�� | +0.048 |
esty | +0.047 |
Dickinson | +0.047 |
allic | +0.047 |
Lund | +0.047 |
Neg logit contributions | |
sent | -0.042 |
kins | -0.041 |
.# | -0.041 |
SEE | -0.041 |
\\ | -0.041 |
Token | forum |
Token ID | 27302 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
�� | +0.619 |
esty | +0.617 |
Dickinson | +0.613 |
allic | +0.613 |
Lund | +0.609 |
Neg logit contributions | |
sent | -0.521 |
kins | -0.512 |
.# | -0.509 |
SEE | -0.503 |
\\ | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
esty | +1.248 |
allic | +1.240 |
�� | +1.235 |
Dickinson | +1.233 |
abbit | +1.232 |
Neg logit contributions | |
sent | -0.848 |
kins | -0.833 |
SEE | -0.826 |
.# | -0.821 |
Limit | -0.817 |
Token | ón |
Token ID | 18840 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
sent | +0.625 |
.# | +0.616 |
kins | +0.609 |
\\ | +0.606 |
SEE | +0.602 |
Neg logit contributions | |
�� | -0.694 |
Dickinson | -0.675 |
esty | -0.666 |
allic | -0.661 |
abbit | -0.661 |
Token | Un |
Token ID | 791 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
sent | +0.328 |
.# | +0.321 |
kins | +0.320 |
\\ | +0.317 |
SEE | +0.316 |
Neg logit contributions | |
�� | -0.393 |
esty | -0.384 |
Dickinson | -0.383 |
allic | -0.381 |
abbit | -0.381 |
Token | ilateral |
Token ID | 14796 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
sent | +0.376 |
kins | +0.369 |
.# | +0.366 |
SEE | +0.362 |
\\ | +0.361 |
Neg logit contributions | |
�� | -0.452 |
Dickinson | -0.444 |
esty | -0.443 |
allic | -0.440 |
Lund | -0.440 |
Token | de |
Token ID | 390 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
sent | +0.215 |
kins | +0.211 |
.# | +0.210 |
SEE | +0.207 |
\\ | +0.207 |
Neg logit contributions | |
�� | -0.266 |
esty | -0.264 |
Dickinson | -0.263 |
allic | -0.262 |
Lund | -0.261 |
Token | Ind |
Token ID | 1423 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
sent | +0.313 |
kins | +0.306 |
.# | +0.305 |
\\ | +0.301 |
SEE | +0.300 |
Neg logit contributions | |
�� | -0.438 |
esty | -0.431 |
Dickinson | -0.429 |
allic | -0.428 |
abbit | -0.426 |
Token | epend |
Token ID | 2690 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
esty | +0.805 |
�� | +0.801 |
allic | +0.797 |
Dickinson | +0.795 |
Lund | +0.791 |
Neg logit contributions | |
sent | -0.734 |
kins | -0.725 |
.# | -0.717 |
SEE | -0.710 |
\\ | -0.706 |
Token | encia |
Token ID | 29634 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
esty | +2.025 |
allic | +1.989 |
abbit | +1.974 |
Lund | +1.967 |
Dickinson | +1.962 |
Neg logit contributions | |
sent | -1.687 |
kins | -1.681 |
SEE | -1.664 |
.# | -1.655 |
\\ | -1.643 |
Token | ) |
Token ID | 8 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
sent | +0.169 |
kins | +0.165 |
.# | +0.165 |
\\ | +0.163 |
SEE | +0.163 |
Neg logit contributions | |
�� | -0.189 |
esty | -0.185 |
Dickinson | -0.185 |
allic | -0.184 |
abbit | -0.183 |
Token | could |
Token ID | 714 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
�� | +0.136 |
esty | +0.135 |
Dickinson | +0.134 |
allic | +0.134 |
Lund | +0.133 |
Neg logit contributions | |
sent | -0.124 |
kins | -0.123 |
.# | -0.122 |
SEE | -0.120 |
\\ | -0.120 |
Token | be |
Token ID | 307 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
sent | +0.341 |
kins | +0.335 |
.# | +0.333 |
SEE | +0.329 |
\\ | +0.328 |
Neg logit contributions | |
�� | -0.367 |
esty | -0.363 |
Dickinson | -0.362 |
allic | -0.360 |
Lund | -0.359 |
Token | re |
Token ID | 302 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
�� | +0.154 |
esty | +0.151 |
allic | +0.150 |
Dickinson | +0.150 |
Lund | +0.149 |
Neg logit contributions | |
sent | -0.158 |
kins | -0.154 |
.# | -0.154 |
\\ | -0.152 |
SEE | -0.152 |
Token | "] |
Token ID | 8973 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
�� | +0.294 |
Dickinson | +0.293 |
Lund | +0.293 |
esty | +0.292 |
allic | +0.291 |
Neg logit contributions | |
sent | -0.206 |
kins | -0.201 |
.# | -0.199 |
SEE | -0.196 |
\\ | -0.194 |
Token | [ |
Token ID | 685 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
kins | +0.111 |
sent | +0.111 |
.# | +0.108 |
SEE | +0.104 |
Tab | +0.103 |
Neg logit contributions | |
Lund | -0.206 |
allic | -0.206 |
Dickinson | -0.206 |
esty | -0.205 |
�� | -0.205 |
Token | Site |
Token ID | 29123 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
sent | +0.213 |
kins | +0.206 |
.# | +0.201 |
SEE | +0.195 |
\\ | +0.194 |
Neg logit contributions | |
�� | -0.655 |
esty | -0.654 |
Dickinson | -0.652 |
allic | -0.652 |
Lund | -0.650 |
Token | " |
Token ID | 366 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
sent | +0.362 |
.# | +0.353 |
kins | +0.351 |
Newsletter | +0.346 |
SEE | +0.344 |
Neg logit contributions | |
Lund | -0.420 |
Dickinson | -0.415 |
abbit | -0.414 |
esty | -0.410 |
allic | -0.410 |
Token | W |
Token ID | 54 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
esty | +0.133 |
allic | +0.133 |
�� | +0.133 |
Dickinson | +0.133 |
Lund | +0.133 |
Neg logit contributions | |
sent | -0.081 |
kins | -0.080 |
.# | -0.078 |
SEE | -0.077 |
Limit | -0.077 |
Token | ijk |
Token ID | 45961 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
sent | +0.039 |
kins | +0.039 |
.# | +0.038 |
SEE | +0.038 |
\\ | +0.038 |
Neg logit contributions | |
�� | -0.044 |
Dickinson | -0.043 |
esty | -0.043 |
allic | -0.043 |
Lund | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
sent | +2.166 |
kins | +2.160 |
.# | +2.157 |
\\ | +2.125 |
SEE | +2.117 |
Neg logit contributions | |
�� | -2.153 |
Dickinson | -2.114 |
allic | -2.100 |
esty | -2.093 |
abbit | -2.075 |
Token | an |
Token ID | 272 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
sent | +0.547 |
kins | +0.544 |
.# | +0.534 |
\\ | +0.530 |
SEE | +0.526 |
Neg logit contributions | |
�� | -0.508 |
Dickinson | -0.493 |
esty | -0.492 |
allic | -0.486 |
abbit | -0.486 |
Token | Z |
Token ID | 1168 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
sent | +0.290 |
kins | +0.285 |
.# | +0.282 |
\\ | +0.278 |
SEE | +0.277 |
Neg logit contributions | |
�� | -0.499 |
esty | -0.495 |
Dickinson | -0.494 |
allic | -0.491 |
abbit | -0.489 |
Token | ee |
Token ID | 1453 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
sent | +0.549 |
.# | +0.530 |
kins | +0.526 |
\\ | +0.519 |
Tab | +0.516 |
Neg logit contributions | |
�� | -0.877 |
Dickinson | -0.860 |
Lund | -0.841 |
allic | -0.832 |
abbit | -0.828 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sent | +0.505 |
kins | +0.497 |
.# | +0.492 |
SEE | +0.486 |
\\ | +0.486 |
Neg logit contributions | |
�� | -0.644 |
esty | -0.637 |
Dickinson | -0.633 |
allic | -0.631 |
abbit | -0.627 |
Token | - |
Token ID | 12 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
�� | +0.184 |
esty | +0.182 |
Dickinson | +0.181 |
allic | +0.181 |
Lund | +0.180 |
Neg logit contributions | |
sent | -0.149 |
kins | -0.146 |
.# | -0.145 |
SEE | -0.143 |
\\ | -0.143 |
Token | vers |
Token ID | 690 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
sent | +0.225 |
kins | +0.222 |
.# | +0.221 |
SEE | +0.218 |
\\ | +0.217 |
Neg logit contributions | |
�� | -0.257 |
esty | -0.257 |
Dickinson | -0.254 |
allic | -0.254 |
Lund | -0.253 |
Token | us |
Token ID | 385 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
sent | +0.322 |
kins | +0.314 |
.# | +0.311 |
SEE | +0.306 |
\\ | +0.305 |
Neg logit contributions | |
�� | -0.642 |
esty | -0.639 |
Dickinson | -0.635 |
allic | -0.634 |
Lund | -0.633 |
Token | - |
Token ID | 12 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
sent | +0.487 |
kins | +0.479 |
.# | +0.474 |
SEE | +0.470 |
\\ | +0.469 |
Neg logit contributions | |
esty | -0.540 |
�� | -0.539 |
Dickinson | -0.535 |
allic | -0.534 |
Lund | -0.532 |
Token | sw |
Token ID | 2032 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
sent | +0.255 |
kins | +0.251 |
.# | +0.249 |
SEE | +0.246 |
\\ | +0.246 |
Neg logit contributions | |
�� | -0.289 |
esty | -0.287 |
Dickinson | -0.286 |
allic | -0.285 |
Lund | -0.284 |
Token | orn |
Token ID | 1211 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
sent | +0.732 |
kins | +0.720 |
.# | +0.709 |
\\ | +0.702 |
SEE | +0.698 |
Neg logit contributions | |
�� | -0.737 |
Dickinson | -0.726 |
Lund | -0.719 |
esty | -0.716 |
allic | -0.711 |
Token | - |
Token ID | 12 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
sent | +1.838 |
kins | +1.806 |
.# | +1.795 |
\\ | +1.755 |
SEE | +1.752 |
Neg logit contributions | |
�� | -2.420 |
Dickinson | -2.341 |
allic | -2.333 |
esty | -2.325 |
Lund | -2.321 |
Token | en |
Token ID | 268 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
sent | +0.427 |
kins | +0.420 |
.# | +0.416 |
SEE | +0.411 |
\\ | +0.410 |
Neg logit contributions | |
�� | -0.469 |
esty | -0.465 |
Dickinson | -0.463 |
allic | -0.461 |
Lund | -0.460 |
Token | m |
Token ID | 76 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
sent | +1.346 |
kins | +1.331 |
.# | +1.305 |
\\ | +1.294 |
SEE | +1.279 |
Neg logit contributions | |
�� | -1.483 |
Dickinson | -1.453 |
allic | -1.448 |
Lund | -1.440 |
esty | -1.432 |
Token | ity |
Token ID | 414 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
sent | +0.765 |
kins | +0.759 |
.# | +0.754 |
\\ | +0.745 |
SEE | +0.738 |
Neg logit contributions | |
�� | -0.607 |
Dickinson | -0.603 |
Lund | -0.599 |
esty | -0.593 |
allic | -0.590 |
Token | approach |
Token ID | 3164 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
esty | +0.390 |
�� | +0.389 |
Dickinson | +0.387 |
allic | +0.386 |
Lund | +0.385 |
Neg logit contributions | |
sent | -0.316 |
kins | -0.312 |
.# | -0.308 |
SEE | -0.305 |
\\ | -0.304 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
sent | +0.414 |
kins | +0.406 |
.# | +0.403 |
SEE | +0.396 |
\\ | +0.396 |
Neg logit contributions | |
�� | -0.614 |
esty | -0.607 |
Dickinson | -0.605 |
allic | -0.603 |
Lund | -0.601 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
�� | +0.269 |
esty | +0.267 |
Dickinson | +0.267 |
Lund | +0.266 |
allic | +0.265 |
Neg logit contributions | |
sent | -0.211 |
kins | -0.207 |
.# | -0.205 |
SEE | -0.202 |
\\ | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
�� | +0.327 |
esty | +0.319 |
Dickinson | +0.315 |
allic | +0.314 |
Lund | +0.313 |
Neg logit contributions | |
sent | -0.243 |
kins | -0.238 |
.# | -0.237 |
\\ | -0.234 |
SEE | -0.232 |
Token | NASA |
Token ID | 29998 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
�� | +0.187 |
esty | +0.187 |
Dickinson | +0.186 |
allic | +0.185 |
Lund | +0.185 |
Neg logit contributions | |
sent | -0.119 |
kins | -0.117 |
.# | -0.115 |
SEE | -0.114 |
\\ | -0.113 |
Token | Earth |
Token ID | 3668 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
esty | +0.714 |
�� | +0.711 |
Lund | +0.709 |
Dickinson | +0.709 |
allic | +0.705 |
Neg logit contributions | |
sent | -0.787 |
kins | -0.776 |
.# | -0.772 |
SEE | -0.767 |
\\ | -0.760 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
esty | +0.519 |
�� | +0.518 |
Dickinson | +0.516 |
Lund | +0.513 |
allic | +0.513 |
Neg logit contributions | |
sent | -0.454 |
kins | -0.447 |
.# | -0.443 |
SEE | -0.438 |
\\ | -0.435 |
Token | images |
Token ID | 4263 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
sent | +1.954 |
kins | +1.911 |
\\ | +1.894 |
.# | +1.893 |
Limit | +1.870 |
Neg logit contributions | |
�� | -2.333 |
esty | -2.258 |
allic | -2.242 |
Dickinson | -2.222 |
abbit | -2.190 |
Token | by |
Token ID | 416 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
�� | +0.392 |
esty | +0.388 |
allic | +0.386 |
Dickinson | +0.385 |
abbit | +0.382 |
Neg logit contributions | |
sent | -0.247 |
kins | -0.242 |
.# | -0.240 |
\\ | -0.236 |
SEE | -0.234 |
Token | Jesse |
Token ID | 18033 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
�� | +0.266 |
esty | +0.258 |
allic | +0.257 |
abbit | +0.256 |
Dickinson | +0.253 |
Neg logit contributions | |
sent | -0.265 |
kins | -0.262 |
\\ | -0.262 |
.# | -0.258 |
Limit | -0.257 |
Token | Allen |
Token ID | 9659 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
sent | +0.725 |
kins | +0.715 |
.# | +0.712 |
\\ | +0.706 |
SEE | +0.705 |
Neg logit contributions | |
�� | -0.503 |
esty | -0.503 |
allic | -0.493 |
abbit | -0.491 |
Dickinson | -0.488 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
�� | +0.462 |
esty | +0.462 |
Dickinson | +0.460 |
Lund | +0.459 |
allic | +0.457 |
Neg logit contributions | |
sent | -0.387 |
kins | -0.377 |
.# | -0.373 |
SEE | -0.370 |
\\ | -0.367 |
Token | ways |
Token ID | 2842 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
sent | +0.120 |
kins | +0.118 |
.# | +0.116 |
SEE | +0.115 |
\\ | +0.114 |
Neg logit contributions | |
�� | -0.169 |
esty | -0.166 |
allic | -0.165 |
Dickinson | -0.164 |
abbit | -0.164 |
Token | that |
Token ID | 326 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
�� | +0.182 |
esty | +0.179 |
allic | +0.178 |
Dickinson | +0.177 |
Lund | +0.176 |
Neg logit contributions | |
sent | -0.174 |
kins | -0.172 |
.# | -0.170 |
SEE | -0.168 |
\\ | -0.167 |
Token | aren |
Token ID | 3588 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
�� | +0.013 |
esty | +0.013 |
allic | +0.013 |
Dickinson | +0.013 |
Lund | +0.013 |
Neg logit contributions | |
sent | -0.012 |
kins | -0.012 |
.# | -0.012 |
SEE | -0.012 |
\\ | -0.012 |
Token | 't |
Token ID | 470 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
sent | +0.001 |
kins | +0.001 |
.# | +0.001 |
\\ | +0.001 |
SEE | +0.001 |
Neg logit contributions | |
�� | -0.001 |
esty | -0.001 |
Dickinson | -0.001 |
allic | -0.001 |
Lund | -0.001 |
Token | comm |
Token ID | 725 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
sent | +0.002 |
kins | +0.002 |
.# | +0.002 |
SEE | +0.002 |
\\ | +0.002 |
Neg logit contributions | |
�� | -0.002 |
esty | -0.002 |
Dickinson | -0.002 |
allic | -0.002 |
Lund | -0.002 |
Token | ens |
Token ID | 641 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
�� | +0.378 |
esty | +0.375 |
Dickinson | +0.373 |
allic | +0.372 |
Lund | +0.371 |
Neg logit contributions | |
sent | -0.281 |
kins | -0.276 |
.# | -0.273 |
SEE | -0.270 |
\\ | -0.269 |
Token | urate |
Token ID | 15537 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
sent | +2.046 |
kins | +1.999 |
.# | +1.967 |
\\ | +1.955 |
SEE | +1.947 |
Neg logit contributions | |
�� | -2.085 |
Dickinson | -2.052 |
esty | -2.023 |
Lund | -2.022 |
abbit | -2.003 |
Token | with |
Token ID | 351 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
sent | +0.256 |
kins | +0.251 |
.# | +0.248 |
SEE | +0.246 |
\\ | +0.246 |
Neg logit contributions | |
�� | -0.344 |
esty | -0.343 |
Dickinson | -0.341 |
allic | -0.340 |
Lund | -0.339 |
Token | their |
Token ID | 511 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
sent | +0.213 |
kins | +0.210 |
.# | +0.208 |
SEE | +0.205 |
\\ | +0.205 |
Neg logit contributions | |
�� | -0.270 |
esty | -0.268 |
Dickinson | -0.266 |
allic | -0.265 |
Lund | -0.264 |
Token | past |
Token ID | 1613 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
sent | +0.076 |
kins | +0.075 |
.# | +0.075 |
SEE | +0.074 |
\\ | +0.073 |
Neg logit contributions | |
�� | -0.089 |
esty | -0.088 |
Dickinson | -0.088 |
allic | -0.088 |
Lund | -0.087 |
Token | performances |
Token ID | 13289 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�� | +0.288 |
esty | +0.285 |
Dickinson | +0.283 |
allic | +0.282 |
Lund | +0.281 |
Neg logit contributions | |
sent | -0.283 |
kins | -0.279 |
.# | -0.277 |
SEE | -0.273 |
\\ | -0.273 |
Token | excessively |
Token ID | 40437 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
sent | +0.303 |
kins | +0.298 |
.# | +0.295 |
SEE | +0.292 |
\\ | +0.291 |
Neg logit contributions | |
�� | -0.372 |
esty | -0.369 |
Dickinson | -0.366 |
allic | -0.366 |
Lund | -0.364 |
Token | sensitive |
Token ID | 8564 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Dickinson | +0.460 |
esty | +0.459 |
�� | +0.459 |
Lund | +0.454 |
allic | +0.454 |
Neg logit contributions | |
sent | -0.434 |
kins | -0.427 |
.# | -0.424 |
SEE | -0.418 |
\\ | -0.418 |
Token | to |
Token ID | 284 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
esty | +0.093 |
�� | +0.092 |
Dickinson | +0.092 |
Lund | +0.092 |
allic | +0.091 |
Neg logit contributions | |
sent | -0.078 |
kins | -0.077 |
.# | -0.076 |
SEE | -0.075 |
\\ | -0.075 |
Token | perceived |
Token ID | 11067 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
�� | +0.089 |
esty | +0.089 |
Dickinson | +0.089 |
allic | +0.088 |
Lund | +0.088 |
Neg logit contributions | |
sent | -0.081 |
kins | -0.080 |
.# | -0.079 |
SEE | -0.079 |
\\ | -0.078 |
Token | sl |
Token ID | 1017 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
sent | +0.171 |
kins | +0.168 |
.# | +0.167 |
SEE | +0.165 |
\\ | +0.165 |
Neg logit contributions | |
�� | -0.177 |
esty | -0.175 |
Dickinson | -0.174 |
allic | -0.174 |
Lund | -0.173 |
Token | ights |
Token ID | 2337 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
esty | +0.209 |
Dickinson | +0.208 |
�� | +0.207 |
allic | +0.207 |
abbit | +0.206 |
Neg logit contributions | |
sent | -0.150 |
kins | -0.146 |
.# | -0.145 |
SEE | -0.145 |
\\ | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
sent | +1.622 |
kins | +1.593 |
.# | +1.588 |
\\ | +1.546 |
SEE | +1.543 |
Neg logit contributions | |
�� | -2.306 |
allic | -2.259 |
Dickinson | -2.255 |
esty | -2.252 |
Lund | -2.238 |
Token |
|
Token ID | 198 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Dickinson | +0.165 |
esty | +0.165 |
Lund | +0.165 |
�� | +0.164 |
allic | +0.164 |
Neg logit contributions | |
sent | -0.138 |
kins | -0.136 |
.# | -0.134 |
SEE | -0.132 |
\\ | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
�� | +0.299 |
esty | +0.292 |
Dickinson | +0.289 |
allic | +0.288 |
Lund | +0.287 |
Neg logit contributions | |
sent | -0.224 |
kins | -0.220 |
.# | -0.219 |
\\ | -0.216 |
SEE | -0.215 |
Token | Three |
Token ID | 12510 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
�� | +0.238 |
esty | +0.238 |
Dickinson | +0.236 |
allic | +0.236 |
Lund | +0.235 |
Neg logit contributions | |
sent | -0.145 |
kins | -0.143 |
.# | -0.141 |
\\ | -0.138 |
SEE | -0.138 |
Token | months |
Token ID | 1933 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
�� | +0.284 |
esty | +0.282 |
Dickinson | +0.280 |
allic | +0.279 |
Lund | +0.278 |
Neg logit contributions | |
sent | -0.258 |
kins | -0.254 |
.# | -0.252 |
SEE | -0.249 |
\\ | -0.248 |
Token | power |
Token ID | 6477 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
sent | +0.123 |
kins | +0.121 |
.# | +0.120 |
SEE | +0.118 |
\\ | +0.118 |
Neg logit contributions | |
�� | -0.136 |
esty | -0.135 |
Dickinson | -0.134 |
allic | -0.134 |
Lund | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
�� | +0.141 |
esty | +0.140 |
Dickinson | +0.138 |
allic | +0.138 |
Lund | +0.138 |
Neg logit contributions | |
sent | -0.107 |
kins | -0.106 |
.# | -0.105 |
SEE | -0.103 |
\\ | -0.103 |
Token | 4 |
Token ID | 604 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
sent | +0.031 |
kins | +0.030 |
.# | +0.030 |
SEE | +0.030 |
\\ | +0.030 |
Neg logit contributions | |
�� | -0.038 |
esty | -0.038 |
Dickinson | -0.037 |
allic | -0.037 |
Lund | -0.037 |
Token | 34 |
Token ID | 2682 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
sent | +0.034 |
kins | +0.034 |
.# | +0.034 |
SEE | +0.033 |
\\ | +0.033 |
Neg logit contributions | |
�� | -0.048 |
esty | -0.047 |
Dickinson | -0.047 |
allic | -0.047 |
Lund | -0.047 |
Token | - |
Token ID | 12 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
�� | +0.101 |
esty | +0.101 |
Dickinson | +0.100 |
allic | +0.100 |
Lund | +0.100 |
Neg logit contributions | |
sent | -0.089 |
kins | -0.088 |
.# | -0.087 |
SEE | -0.086 |
\\ | -0.086 |
Token | lb |
Token ID | 23160 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
sent | +0.006 |
kins | +0.006 |
.# | +0.006 |
SEE | +0.006 |
\\ | +0.005 |
Neg logit contributions | |
�� | -0.004 |
esty | -0.004 |
Dickinson | -0.004 |
allic | -0.004 |
Lund | -0.004 |
Token | .- |
Token ID | 7874 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
sent | +1.446 |
.# | +1.423 |
kins | +1.417 |
SEE | +1.387 |
\\ | +1.385 |
Neg logit contributions | |
�� | -2.448 |
esty | -2.411 |
Dickinson | -2.408 |
allic | -2.389 |
Lund | -2.388 |
Token | ft |
Token ID | 701 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
sent | +0.156 |
kins | +0.153 |
.# | +0.152 |
SEE | +0.149 |
\\ | +0.148 |
Neg logit contributions | |
esty | -0.258 |
allic | -0.257 |
Lund | -0.256 |
Dickinson | -0.255 |
�� | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
sent | +0.638 |
kins | +0.624 |
.# | +0.615 |
SEE | +0.607 |
\\ | +0.606 |
Neg logit contributions | |
�� | -1.104 |
esty | -1.099 |
Dickinson | -1.095 |
allic | -1.091 |
Lund | -1.090 |
Token | 6 |
Token ID | 718 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
sent | +0.037 |
kins | +0.037 |
.# | +0.036 |
SEE | +0.036 |
\\ | +0.036 |
Neg logit contributions | |
�� | -0.045 |
esty | -0.044 |
Dickinson | -0.044 |
allic | -0.044 |
Lund | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
sent | +0.497 |
kins | +0.489 |
.# | +0.484 |
SEE | +0.478 |
\\ | +0.478 |
Neg logit contributions | |
�� | -0.637 |
esty | -0.629 |
Dickinson | -0.628 |
allic | -0.626 |
Lund | -0.623 |
Token | less |
Token ID | 1203 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
�� | +0.040 |
esty | +0.040 |
Dickinson | +0.040 |
allic | +0.040 |
Lund | +0.040 |
Neg logit contributions | |
sent | -0.030 |
kins | -0.030 |
.# | -0.029 |
SEE | -0.029 |
\\ | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
sent | +0.309 |
kins | +0.305 |
.# | +0.304 |
\\ | +0.300 |
SEE | +0.298 |
Neg logit contributions | |
�� | -0.330 |
esty | -0.326 |
Dickinson | -0.322 |
allic | -0.322 |
Lund | -0.320 |
Token | hook |
Token ID | 8011 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
sent | +0.425 |
kins | +0.419 |
.# | +0.416 |
\\ | +0.411 |
SEE | +0.411 |
Neg logit contributions | |
�� | -0.412 |
esty | -0.407 |
Dickinson | -0.404 |
allic | -0.403 |
Lund | -0.401 |
Token | n |
Token ID | 77 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
sent | +0.105 |
kins | +0.103 |
.# | +0.102 |
SEE | +0.101 |
\\ | +0.101 |
Neg logit contributions | |
�� | -0.126 |
esty | -0.124 |
Dickinson | -0.124 |
allic | -0.123 |
Lund | -0.123 |
Token | osed |
Token ID | 1335 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
sent | +0.430 |
kins | +0.423 |
.# | +0.420 |
SEE | +0.416 |
\\ | +0.415 |
Neg logit contributions | |
�� | -0.439 |
esty | -0.437 |
Dickinson | -0.434 |
allic | -0.433 |
Lund | -0.431 |
Token | Jew |
Token ID | 3370 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
sent | +0.427 |
kins | +0.421 |
.# | +0.419 |
\\ | +0.414 |
SEE | +0.413 |
Neg logit contributions | |
�� | -0.470 |
esty | -0.463 |
Dickinson | -0.459 |
allic | -0.458 |
Lund | -0.456 |
Token | � |
Token ID | 447 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
sent | +1.678 |
kins | +1.672 |
.# | +1.667 |
\\ | +1.632 |
SEE | +1.619 |
Neg logit contributions | |
�� | -2.195 |
esty | -2.143 |
Dickinson | -2.137 |
allic | -2.125 |
Lund | -2.116 |
Token | � |
Token ID | 251 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
sent | +0.173 |
kins | +0.170 |
.# | +0.168 |
SEE | +0.166 |
\\ | +0.166 |
Neg logit contributions | |
�� | -0.230 |
esty | -0.228 |
Dickinson | -0.226 |
allic | -0.226 |
Lund | -0.225 |
Token | from |
Token ID | 422 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
sent | +0.193 |
kins | +0.190 |
.# | +0.188 |
SEE | +0.186 |
\\ | +0.185 |
Neg logit contributions | |
�� | -0.236 |
esty | -0.235 |
Dickinson | -0.234 |
allic | -0.233 |
Lund | -0.233 |
Token | a |
Token ID | 257 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
sent | +0.560 |
kins | +0.553 |
.# | +0.549 |
\\ | +0.541 |
SEE | +0.539 |
Neg logit contributions | |
�� | -0.586 |
esty | -0.579 |
Dickinson | -0.574 |
allic | -0.573 |
Lund | -0.570 |
Token | user |
Token ID | 2836 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
sent | +0.241 |
kins | +0.238 |
.# | +0.236 |
\\ | +0.232 |
SEE | +0.232 |
Neg logit contributions | |
�� | -0.248 |
esty | -0.246 |
Dickinson | -0.243 |
allic | -0.243 |
Lund | -0.242 |
Token | gymn |
Token ID | 38581 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
�� | +0.010 |
esty | +0.010 |
Dickinson | +0.010 |
allic | +0.010 |
Lund | +0.010 |
Neg logit contributions | |
sent | -0.010 |
kins | -0.010 |
.# | -0.010 |
SEE | -0.010 |
\\ | -0.010 |
Token | astics |
Token ID | 24232 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
sent | +0.026 |
kins | +0.026 |
.# | +0.026 |
\\ | +0.025 |
SEE | +0.025 |
Neg logit contributions | |
�� | -0.025 |
esty | -0.024 |
Dickinson | -0.024 |
allic | -0.024 |
Lund | -0.024 |
Token | routine |
Token ID | 8027 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
�� | +0.494 |
esty | +0.492 |
Dickinson | +0.490 |
Lund | +0.488 |
allic | +0.487 |
Neg logit contributions | |
sent | -0.479 |
kins | -0.471 |
.# | -0.467 |
SEE | -0.464 |
\\ | -0.462 |
Token | for |
Token ID | 329 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
sent | +0.383 |
kins | +0.376 |
.# | +0.374 |
\\ | +0.367 |
SEE | +0.367 |
Neg logit contributions | |
�� | -0.519 |
esty | -0.514 |
Dickinson | -0.511 |
allic | -0.510 |
Lund | -0.508 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
sent | +0.490 |
kins | +0.482 |
.# | +0.479 |
SEE | +0.473 |
\\ | +0.472 |
Neg logit contributions | |
�� | -0.503 |
esty | -0.497 |
Dickinson | -0.493 |
allic | -0.493 |
Lund | -0.489 |
Token | speaker |
Token ID | 10834 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
sent | +0.393 |
kins | +0.387 |
.# | +0.384 |
\\ | +0.379 |
SEE | +0.378 |
Neg logit contributions | |
�� | -0.415 |
esty | -0.410 |
allic | -0.407 |
Dickinson | -0.406 |
Lund | -0.402 |
Token | � |
Token ID | 447 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
sent | +1.577 |
.# | +1.564 |
kins | +1.544 |
\\ | +1.521 |
SEE | +1.516 |
Neg logit contributions | |
�� | -2.282 |
esty | -2.238 |
allic | -2.225 |
Dickinson | -2.223 |
Lund | -2.210 |
Token | � |
Token ID | 247 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
sent | +0.312 |
kins | +0.307 |
.# | +0.303 |
SEE | +0.300 |
\\ | +0.300 |
Neg logit contributions | |
�� | -0.391 |
esty | -0.387 |
Dickinson | -0.385 |
allic | -0.383 |
Lund | -0.383 |
Token | s |
Token ID | 82 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
sent | +0.463 |
kins | +0.454 |
.# | +0.451 |
SEE | +0.445 |
\\ | +0.444 |
Neg logit contributions | |
�� | -0.610 |
esty | -0.605 |
Dickinson | -0.603 |
allic | -0.600 |
Lund | -0.599 |
Token | tongue |
Token ID | 11880 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
sent | +0.015 |
kins | +0.015 |
.# | +0.015 |
SEE | +0.015 |
\\ | +0.015 |
Neg logit contributions | |
�� | -0.021 |
esty | -0.020 |
Dickinson | -0.020 |
allic | -0.020 |
Lund | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
�� | +0.024 |
esty | +0.024 |
Dickinson | +0.024 |
allic | +0.024 |
Lund | +0.024 |
Neg logit contributions | |
sent | -0.018 |
kins | -0.018 |
.# | -0.018 |
SEE | -0.017 |
\\ | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
sent | +0.018 |
kins | +0.018 |
.# | +0.018 |
\\ | +0.017 |
SEE | +0.017 |
Neg logit contributions | |
�� | -0.015 |
Dickinson | -0.015 |
esty | -0.015 |
allic | -0.015 |
Lund | -0.015 |
Token | staff |
Token ID | 3085 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
�� | +0.109 |
esty | +0.108 |
Dickinson | +0.107 |
allic | +0.107 |
Lund | +0.107 |
Neg logit contributions | |
sent | -0.090 |
kins | -0.089 |
.# | -0.088 |
SEE | -0.087 |
\\ | -0.086 |
Token | |
Token ID | 22020 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
�� | +0.263 |
esty | +0.261 |
Dickinson | +0.260 |
allic | +0.259 |
Lund | +0.258 |
Neg logit contributions | |
sent | -0.245 |
kins | -0.241 |
.# | -0.239 |
SEE | -0.236 |
\\ | -0.236 |
Token | in |
Token ID | 259 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
esty | +1.518 |
�� | +1.505 |
allic | +1.502 |
Lund | +1.497 |
Dickinson | +1.495 |
Neg logit contributions | |
sent | -1.245 |
kins | -1.235 |
.# | -1.233 |
\\ | -1.214 |
SEE | -1.210 |
Token | comp |
Token ID | 5589 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
�� | +0.006 |
esty | +0.006 |
Dickinson | +0.006 |
allic | +0.006 |
Lund | +0.006 |
Neg logit contributions | |
sent | -0.006 |
kins | -0.006 |
.# | -0.006 |
SEE | -0.006 |
\\ | -0.006 |
Token | et |
Token ID | 316 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
sent | +0.543 |
kins | +0.533 |
.# | +0.527 |
\\ | +0.519 |
SEE | +0.518 |
Neg logit contributions | |
�� | -0.676 |
Dickinson | -0.667 |
esty | -0.666 |
Lund | -0.662 |
allic | -0.660 |
Token | ent |
Token ID | 298 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
sent | +1.847 |
.# | +1.787 |
kins | +1.783 |
\\ | +1.761 |
SEE | +1.756 |
Neg logit contributions | |
�� | -1.875 |
Dickinson | -1.818 |
esty | -1.799 |
allic | -1.794 |
Lund | -1.793 |
Token | or |
Token ID | 393 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
sent | +1.039 |
kins | +1.019 |
.# | +1.014 |
SEE | +0.995 |
\\ | +0.992 |
Neg logit contributions | |
�� | -1.486 |
esty | -1.465 |
Dickinson | -1.462 |
allic | -1.459 |
Lund | -1.451 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
sent | +0.068 |
kins | +0.067 |
.# | +0.066 |
SEE | +0.065 |
\\ | +0.065 |
Neg logit contributions | |
�� | -0.065 |
esty | -0.064 |
Dickinson | -0.064 |
allic | -0.064 |
Lund | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
esty | +0.950 |
�� | +0.938 |
Dickinson | +0.933 |
Lund | +0.932 |
allic | +0.929 |
Neg logit contributions | |
sent | -0.726 |
kins | -0.717 |
.# | -0.706 |
\\ | -0.701 |
SEE | -0.700 |
Token |
|
Token ID | 198 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
sent | +0.049 |
kins | +0.048 |
.# | +0.047 |
SEE | +0.047 |
\\ | +0.047 |
Neg logit contributions | |
�� | -0.060 |
esty | -0.059 |
Dickinson | -0.059 |
allic | -0.059 |
Lund | -0.059 |
Token | fees |
Token ID | 6642 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
�� | +0.584 |
esty | +0.572 |
Dickinson | +0.568 |
allic | +0.567 |
Lund | +0.564 |
Neg logit contributions | |
sent | -0.579 |
kins | -0.572 |
.# | -0.568 |
\\ | -0.562 |
SEE | -0.560 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
�� | +0.817 |
esty | +0.810 |
Dickinson | +0.805 |
allic | +0.803 |
Lund | +0.801 |
Neg logit contributions | |
sent | -0.677 |
kins | -0.666 |
.# | -0.660 |
SEE | -0.652 |
\\ | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
�� | +0.227 |
esty | +0.224 |
Dickinson | +0.222 |
allic | +0.222 |
Lund | +0.221 |
Neg logit contributions | |
sent | -0.216 |
kins | -0.212 |
.# | -0.211 |
\\ | -0.208 |
SEE | -0.208 |
Token | re |
Token ID | 302 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
�� | +0.207 |
esty | +0.203 |
allic | +0.203 |
Dickinson | +0.202 |
Lund | +0.201 |
Neg logit contributions | |
sent | -0.192 |
kins | -0.189 |
.# | -0.188 |
\\ | -0.186 |
SEE | -0.185 |
Token | - |
Token ID | 12 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
�� | +0.173 |
esty | +0.172 |
Dickinson | +0.171 |
allic | +0.171 |
Lund | +0.170 |
Neg logit contributions | |
sent | -0.177 |
kins | -0.175 |
.# | -0.174 |
SEE | -0.172 |
\\ | -0.171 |
Token | fin |
Token ID | 15643 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
sent | +0.640 |
kins | +0.622 |
.# | +0.615 |
\\ | +0.613 |
SEE | +0.609 |
Neg logit contributions | |
�� | -0.674 |
Dickinson | -0.660 |
esty | -0.656 |
Lund | -0.654 |
allic | -0.651 |
Token | ancing |
Token ID | 5077 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
sent | +1.796 |
kins | +1.730 |
.# | +1.708 |
\\ | +1.698 |
Limit | +1.683 |
Neg logit contributions | |
�� | -1.922 |
Dickinson | -1.808 |
abbit | -1.791 |
allic | -1.787 |
Lund | -1.785 |
Token | fees |
Token ID | 6642 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
sent | +0.018 |
kins | +0.017 |
.# | +0.017 |
\\ | +0.017 |
SEE | +0.017 |
Neg logit contributions | |
�� | -0.025 |
esty | -0.025 |
allic | -0.025 |
Dickinson | -0.025 |
Lund | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
�� | +0.540 |
esty | +0.537 |
Dickinson | +0.534 |
allic | +0.532 |
Lund | +0.531 |
Neg logit contributions | |
sent | -0.459 |
kins | -0.452 |
.# | -0.448 |
SEE | -0.442 |
\\ | -0.442 |
Token | the |
Token ID | 262 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
�� | +0.014 |
esty | +0.014 |
Dickinson | +0.014 |
allic | +0.014 |
Lund | +0.014 |
Neg logit contributions | |
sent | -0.013 |
kins | -0.013 |
.# | -0.013 |
SEE | -0.012 |
\\ | -0.012 |
Token | pl |
Token ID | 458 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
�� | +0.063 |
esty | +0.062 |
allic | +0.062 |
Dickinson | +0.062 |
Lund | +0.062 |
Neg logit contributions | |
sent | -0.060 |
kins | -0.059 |
.# | -0.058 |
\\ | -0.058 |
SEE | -0.057 |
Token | ometer |
Token ID | 15635 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
esty | +0.853 |
allic | +0.851 |
Lund | +0.847 |
Dickinson | +0.841 |
�� | +0.841 |
Neg logit contributions | |
sent | -0.536 |
kins | -0.528 |
.# | -0.526 |
SEE | -0.517 |
Tab | -0.511 |
Token | Grav |
Token ID | 32599 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
sent | +0.147 |
kins | +0.145 |
.# | +0.144 |
Limit | +0.141 |
\\ | +0.141 |
Neg logit contributions | |
�� | -0.585 |
esty | -0.574 |
Dickinson | -0.569 |
allic | -0.568 |
abbit | -0.566 |
Token | itational |
Token ID | 22181 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
sent | +1.189 |
kins | +1.169 |
.# | +1.162 |
SEE | +1.149 |
\\ | +1.147 |
Neg logit contributions | |
�� | -1.185 |
esty | -1.173 |
Dickinson | -1.167 |
allic | -1.162 |
Lund | -1.159 |
Token | - |
Token ID | 12 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
sent | +1.273 |
kins | +1.252 |
.# | +1.249 |
\\ | +1.234 |
SEE | +1.233 |
Neg logit contributions | |
�� | -1.564 |
esty | -1.545 |
allic | -1.522 |
Dickinson | -1.514 |
abbit | -1.511 |
Token | wave |
Token ID | 19204 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
Lund | +0.067 |
allic | +0.067 |
Dickinson | +0.066 |
abbit | +0.066 |
esty | +0.066 |
Neg logit contributions | |
sent | -0.031 |
kins | -0.031 |
.# | -0.030 |
\\ | -0.029 |
SEE | -0.029 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
sent | +0.428 |
kins | +0.418 |
.# | +0.413 |
SEE | +0.408 |
\\ | +0.407 |
Neg logit contributions | |
Dickinson | -0.493 |
esty | -0.490 |
Lund | -0.489 |
allic | -0.488 |
�� | -0.487 |
Token | ( |
Token ID | 357 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
sent | +1.455 |
kins | +1.434 |
.# | +1.424 |
\\ | +1.409 |
Limit | +1.402 |
Neg logit contributions | |
�� | -2.167 |
esty | -2.110 |
allic | -2.097 |
Dickinson | -2.082 |
abbit | -2.073 |
Token | L |
Token ID | 43 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
sent | +0.125 |
kins | +0.124 |
.# | +0.123 |
SEE | +0.122 |
\\ | +0.121 |
Neg logit contributions | |
�� | -0.098 |
esty | -0.096 |
Dickinson | -0.096 |
allic | -0.095 |
Lund | -0.094 |
Token | IG |
Token ID | 3528 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
�� | +0.327 |
esty | +0.325 |
Dickinson | +0.323 |
allic | +0.322 |
Lund | +0.322 |
Neg logit contributions | |
sent | -0.234 |
kins | -0.230 |
.# | -0.228 |
SEE | -0.225 |
\\ | -0.224 |
Token | O |
Token ID | 46 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
sent | +0.546 |
.# | +0.539 |
kins | +0.532 |
SEE | +0.530 |
\\ | +0.522 |
Neg logit contributions | |
�� | -0.915 |
esty | -0.899 |
Dickinson | -0.894 |
allic | -0.893 |
abbit | -0.884 |
Token | ) |
Token ID | 8 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
sent | +0.265 |
kins | +0.262 |
.# | +0.260 |
SEE | +0.258 |
\\ | +0.257 |
Neg logit contributions | |
�� | -0.218 |
esty | -0.214 |
Dickinson | -0.213 |
allic | -0.212 |
Lund | -0.211 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
sent | +0.226 |
kins | +0.222 |
.# | +0.220 |
SEE | +0.218 |
\\ | +0.217 |
Neg logit contributions | |
�� | -0.265 |
esty | -0.263 |
Dickinson | -0.262 |
allic | -0.261 |
Lund | -0.260 |
Token | gu |
Token ID | 5162 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
sent | +0.295 |
kins | +0.281 |
.# | +0.276 |
SEE | +0.268 |
\\ | +0.265 |
Neg logit contributions | |
�� | -1.350 |
esty | -1.347 |
Dickinson | -1.341 |
allic | -1.339 |
Lund | -1.336 |
Token | in |
Token ID | 259 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
sent | +0.155 |
kins | +0.152 |
.# | +0.149 |
\\ | +0.148 |
SEE | +0.145 |
Neg logit contributions | |
�� | -0.228 |
esty | -0.220 |
Dickinson | -0.220 |
Lund | -0.219 |
allic | -0.219 |
Token | The |
Token ID | 383 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
Dickinson | +0.057 |
esty | +0.057 |
�� | +0.057 |
Lund | +0.056 |
allic | +0.056 |
Neg logit contributions | |
sent | -0.045 |
kins | -0.044 |
.# | -0.044 |
SEE | -0.043 |
\\ | -0.043 |
Token | at |
Token ID | 265 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
sent | +0.038 |
kins | +0.037 |
.# | +0.037 |
SEE | +0.037 |
\\ | +0.037 |
Neg logit contributions | |
�� | -0.030 |
esty | -0.030 |
Dickinson | -0.030 |
Lund | -0.029 |
allic | -0.029 |
Token | res |
Token ID | 411 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
esty | +0.222 |
�� | +0.222 |
Dickinson | +0.221 |
allic | +0.220 |
Lund | +0.220 |
Neg logit contributions | |
sent | -0.100 |
kins | -0.096 |
.# | -0.095 |
SEE | -0.094 |
\\ | -0.093 |
Token | Inc |
Token ID | 3457 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
sent | +1.581 |
kins | +1.556 |
.# | +1.543 |
SEE | +1.521 |
\\ | +1.518 |
Neg logit contributions | |
�� | -2.023 |
esty | -2.002 |
Dickinson | -1.986 |
allic | -1.986 |
Lund | -1.975 |
Token | ., |
Token ID | 1539 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
sent | +0.325 |
kins | +0.318 |
SEE | +0.311 |
.# | +0.310 |
\\ | +0.309 |
Neg logit contributions | |
esty | -0.535 |
�� | -0.533 |
Dickinson | -0.531 |
Lund | -0.530 |
allic | -0.529 |
Token | � |
Token ID | 564 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
Dickinson | +0.241 |
Lund | +0.239 |
esty | +0.239 |
�� | +0.238 |
allic | +0.236 |
Neg logit contributions | |
sent | -0.205 |
kins | -0.202 |
.# | -0.200 |
SEE | -0.198 |
\\ | -0.197 |
Token | � |
Token ID | 250 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
�� | +0.042 |
esty | +0.042 |
Dickinson | +0.042 |
allic | +0.041 |
Lund | +0.041 |
Neg logit contributions | |
sent | -0.045 |
kins | -0.044 |
.# | -0.044 |
\\ | -0.043 |
SEE | -0.043 |
Token | working |
Token ID | 16090 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
esty | +0.035 |
Dickinson | +0.035 |
Lund | +0.035 |
allic | +0.035 |
�� | +0.035 |
Neg logit contributions | |
sent | -0.026 |
kins | -0.025 |
.# | -0.025 |
SEE | -0.025 |
\\ | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
�� | +0.354 |
esty | +0.351 |
Dickinson | +0.350 |
allic | +0.348 |
Lund | +0.348 |
Neg logit contributions | |
sent | -0.299 |
kins | -0.294 |
.# | -0.291 |
SEE | -0.288 |
\\ | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
sent | +0.183 |
.# | +0.179 |
kins | +0.178 |
\\ | +0.176 |
SEE | +0.174 |
Neg logit contributions | |
�� | -0.256 |
esty | -0.247 |
Dickinson | -0.244 |
allic | -0.243 |
abbit | -0.243 |
Token | Bay |
Token ID | 15262 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
sent | +0.180 |
kins | +0.177 |
.# | +0.175 |
SEE | +0.173 |
\\ | +0.173 |
Neg logit contributions | |
�� | -0.260 |
esty | -0.259 |
Dickinson | -0.258 |
allic | -0.257 |
Lund | -0.256 |
Token | ern |
Token ID | 1142 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
�� | +0.320 |
esty | +0.317 |
Dickinson | +0.314 |
allic | +0.312 |
Lund | +0.310 |
Neg logit contributions | |
sent | -1.005 |
kins | -0.995 |
.# | -0.990 |
SEE | -0.984 |
\\ | -0.982 |
Token | Munich |
Token ID | 22418 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
�� | +0.310 |
esty | +0.307 |
Dickinson | +0.305 |
allic | +0.303 |
Lund | +0.302 |
Neg logit contributions | |
sent | -0.382 |
kins | -0.377 |
.# | -0.374 |
SEE | -0.370 |
\\ | -0.370 |
Token | Jun |
Token ID | 7653 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
sent | +0.218 |
kins | +0.215 |
.# | +0.213 |
SEE | +0.210 |
\\ | +0.210 |
Neg logit contributions | |
�� | -0.259 |
esty | -0.257 |
Dickinson | -0.255 |
allic | -0.254 |
Lund | -0.253 |
Token | iors |
Token ID | 12706 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
sent | +1.670 |
kins | +1.623 |
.# | +1.610 |
SEE | +1.584 |
Limit | +1.577 |
Neg logit contributions | |
�� | -1.920 |
Dickinson | -1.917 |
allic | -1.902 |
esty | -1.888 |
abbit | -1.887 |
Token | [ |
Token ID | 58 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
sent | +0.394 |
kins | +0.388 |
.# | +0.385 |
SEE | +0.380 |
\\ | +0.379 |
Neg logit contributions | |
�� | -0.459 |
esty | -0.455 |
Dickinson | -0.451 |
allic | -0.451 |
Lund | -0.447 |
Token | 92 |
Token ID | 5892 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
sent | +0.621 |
kins | +0.611 |
.# | +0.605 |
SEE | +0.597 |
\\ | +0.596 |
Neg logit contributions | |
�� | -0.815 |
esty | -0.810 |
Dickinson | -0.806 |
allic | -0.804 |
Lund | -0.802 |
Token | ][ |
Token ID | 7131 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
sent | +0.676 |
kins | +0.666 |
.# | +0.661 |
SEE | +0.655 |
\\ | +0.653 |
Neg logit contributions | |
�� | -0.580 |
esty | -0.575 |
Dickinson | -0.571 |
allic | -0.569 |
Lund | -0.568 |
Token | 93 |
Token ID | 6052 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
sent | +0.560 |
kins | +0.556 |
.# | +0.549 |
SEE | +0.541 |
\\ | +0.540 |
Neg logit contributions | |
esty | -0.705 |
�� | -0.705 |
allic | -0.703 |
Dickinson | -0.698 |
Lund | -0.697 |
Token | Property |
Token ID | 21746 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
sent | +0.266 |
kins | +0.261 |
.# | +0.257 |
SEE | +0.251 |
\\ | +0.250 |
Neg logit contributions | |
esty | -0.552 |
�� | -0.550 |
Dickinson | -0.549 |
allic | -0.547 |
Lund | -0.546 |
Token | B |
Token ID | 347 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sent | +0.650 |
kins | +0.638 |
.# | +0.631 |
SEE | +0.623 |
\\ | +0.621 |
Neg logit contributions | |
�� | -0.959 |
esty | -0.954 |
Dickinson | -0.949 |
allic | -0.946 |
Lund | -0.945 |
Token | ounds |
Token ID | 3733 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
sent | +0.684 |
kins | +0.671 |
.# | +0.666 |
SEE | +0.656 |
\\ | +0.654 |
Neg logit contributions | |
�� | -0.875 |
esty | -0.872 |
Dickinson | -0.866 |
allic | -0.865 |
Lund | -0.862 |
Token | | |
Token ID | 930 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
sent | +0.639 |
kins | +0.626 |
.# | +0.620 |
SEE | +0.612 |
\\ | +0.610 |
Neg logit contributions | |
�� | -0.870 |
esty | -0.865 |
Dickinson | -0.860 |
allic | -0.858 |
Lund | -0.856 |
Token | Select |
Token ID | 9683 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
sent | +0.398 |
kins | +0.392 |
.# | +0.387 |
SEE | +0.383 |
\\ | +0.380 |
Neg logit contributions | |
�� | -0.498 |
esty | -0.497 |
Dickinson | -0.495 |
Lund | -0.494 |
allic | -0.493 |
Token | Width |
Token ID | 38807 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
sent | +0.049 |
kins | +0.048 |
.# | +0.047 |
SEE | +0.047 |
\\ | +0.047 |
Neg logit contributions | |
�� | -0.063 |
esty | -0.063 |
Dickinson | -0.063 |
allic | -0.062 |
Lund | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
sent | +1.674 |
kins | +1.649 |
.# | +1.639 |
\\ | +1.619 |
SEE | +1.618 |
Neg logit contributions | |
�� | -1.914 |
esty | -1.891 |
Dickinson | -1.886 |
allic | -1.878 |
Lund | -1.870 |
Token | Height |
Token ID | 23106 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
sent | +0.212 |
kins | +0.207 |
.# | +0.204 |
SEE | +0.200 |
\\ | +0.198 |
Neg logit contributions | |
�� | -0.473 |
esty | -0.473 |
allic | -0.469 |
Dickinson | -0.469 |
Lund | -0.469 |
Token | Write |
Token ID | 19430 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
sent | +0.469 |
kins | +0.461 |
.# | +0.456 |
SEE | +0.450 |
\\ | +0.449 |
Neg logit contributions | |
�� | -0.624 |
esty | -0.621 |
Dickinson | -0.618 |
allic | -0.616 |
Lund | -0.615 |
Token | - |
Token ID | 12 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
sent | +1.052 |
kins | +1.035 |
.# | +1.024 |
SEE | +1.010 |
\\ | +1.004 |
Neg logit contributions | |
�� | -1.161 |
esty | -1.159 |
Dickinson | -1.150 |
allic | -1.145 |
Lund | -1.145 |
Token | Ver |
Token ID | 13414 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
sent | +0.170 |
kins | +0.169 |
.# | +0.167 |
SEE | +0.162 |
\\ | +0.162 |
Neg logit contributions | |
esty | -0.223 |
�� | -0.222 |
allic | -0.222 |
Dickinson | -0.221 |
Lund | -0.220 |
Token | gen |
Token ID | 5235 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
sent | +0.450 |
kins | +0.444 |
.# | +0.437 |
SEE | +0.432 |
\\ | +0.432 |
Neg logit contributions | |
�� | -0.408 |
esty | -0.402 |
Dickinson | -0.397 |
abbit | -0.395 |
allic | -0.395 |
Token | y |
Token ID | 88 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
Lund | +0.558 |
esty | +0.555 |
Dickinson | +0.552 |
allic | +0.550 |
�� | +0.547 |
Neg logit contributions | |
sent | -0.254 |
kins | -0.251 |
.# | -0.249 |
SEE | -0.244 |
\\ | -0.242 |
Token | K |
Token ID | 509 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
�� | +0.013 |
esty | +0.012 |
allic | +0.012 |
Dickinson | +0.012 |
abbit | +0.012 |
Neg logit contributions | |
sent | -0.010 |
kins | -0.010 |
.# | -0.010 |
\\ | -0.009 |
SEE | -0.009 |
Token | uz |
Token ID | 10277 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
sent | +0.079 |
kins | +0.078 |
.# | +0.077 |
SEE | +0.075 |
\\ | +0.075 |
Neg logit contributions | |
�� | -0.148 |
Dickinson | -0.146 |
esty | -0.145 |
allic | -0.145 |
Lund | -0.144 |
Token | net |
Token ID | 3262 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
sent | +0.588 |
kins | +0.572 |
.# | +0.556 |
\\ | +0.547 |
SEE | +0.546 |
Neg logit contributions | |
�� | -0.873 |
Dickinson | -0.865 |
esty | -0.857 |
allic | -0.851 |
abbit | -0.850 |
Token | sov |
Token ID | 47272 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
�� | +0.629 |
Dickinson | +0.621 |
esty | +0.621 |
allic | +0.618 |
Lund | +0.614 |
Neg logit contributions | |
sent | -0.406 |
kins | -0.399 |
.# | -0.393 |
SEE | -0.386 |
\\ | -0.385 |
Token | pass |
Token ID | 1208 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
sent | +1.710 |
.# | +1.691 |
kins | +1.673 |
\\ | +1.638 |
SEE | +1.624 |
Neg logit contributions | |
�� | -1.928 |
esty | -1.857 |
Dickinson | -1.838 |
abbit | -1.833 |
allic | -1.827 |
Token | , |
Token ID | 11 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
sent | +0.204 |
kins | +0.201 |
.# | +0.200 |
\\ | +0.196 |
SEE | +0.195 |
Neg logit contributions | |
�� | -0.256 |
esty | -0.252 |
Dickinson | -0.250 |
allic | -0.250 |
Lund | -0.249 |
Token | before |
Token ID | 878 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
�� | +0.061 |
esty | +0.061 |
Dickinson | +0.060 |
allic | +0.060 |
Lund | +0.060 |
Neg logit contributions | |
sent | -0.050 |
kins | -0.050 |
.# | -0.049 |
SEE | -0.049 |
\\ | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
sent | +0.088 |
kins | +0.087 |
.# | +0.086 |
SEE | +0.085 |
\\ | +0.085 |
Neg logit contributions | |
�� | -0.088 |
esty | -0.087 |
allic | -0.087 |
Dickinson | -0.086 |
abbit | -0.086 |
Token | Great |
Token ID | 3878 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
�� | +0.142 |
esty | +0.139 |
allic | +0.138 |
Dickinson | +0.137 |
abbit | +0.136 |
Neg logit contributions | |
sent | -0.141 |
kins | -0.139 |
.# | -0.138 |
\\ | -0.136 |
SEE | -0.135 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
sent | +0.538 |
kins | +0.529 |
.# | +0.524 |
SEE | +0.518 |
\\ | +0.516 |
Neg logit contributions | |
�� | -0.715 |
esty | -0.713 |
Dickinson | -0.711 |
allic | -0.707 |
Lund | -0.705 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sent | +0.011 |
kins | +0.011 |
.# | +0.011 |
\\ | +0.011 |
SEE | +0.011 |
Neg logit contributions | |
�� | -0.013 |
esty | -0.012 |
Dickinson | -0.012 |
allic | -0.012 |
Lund | -0.012 |
Token | subscribe |
Token ID | 12383 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
sent | +0.623 |
kins | +0.611 |
.# | +0.606 |
\\ | +0.598 |
Limit | +0.593 |
Neg logit contributions | |
�� | -0.811 |
esty | -0.785 |
Lund | -0.778 |
allic | -0.776 |
Dickinson | -0.775 |
Token | to |
Token ID | 284 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
sent | +0.440 |
kins | +0.431 |
.# | +0.431 |
\\ | +0.423 |
SEE | +0.420 |
Neg logit contributions | |
�� | -0.527 |
esty | -0.518 |
Dickinson | -0.511 |
allic | -0.510 |
Lund | -0.507 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sent | +0.415 |
.# | +0.411 |
kins | +0.406 |
\\ | +0.397 |
SEE | +0.390 |
Neg logit contributions | |
�� | -0.786 |
esty | -0.758 |
abbit | -0.742 |
allic | -0.742 |
Dickinson | -0.741 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
sent | +0.291 |
kins | +0.277 |
.# | +0.272 |
\\ | +0.266 |
Limit | +0.265 |
Neg logit contributions | |
�� | -1.142 |
esty | -1.130 |
Dickinson | -1.109 |
abbit | -1.109 |
allic | -1.108 |
Token | Up |
Token ID | 3205 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
sent | +1.162 |
Limit | +1.157 |
.# | +1.127 |
kins | +1.123 |
\\ | +1.112 |
Neg logit contributions | |
�� | -2.550 |
esty | -2.461 |
abbit | -2.367 |
Dickinson | -2.365 |
allic | -2.355 |
Token | You |
Token ID | 921 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sent | +0.850 |
kins | +0.832 |
.# | +0.831 |
Limit | +0.827 |
\\ | +0.825 |
Neg logit contributions | |
�� | -1.107 |
esty | -1.082 |
allic | -1.049 |
abbit | -1.045 |
Dickinson | -1.045 |
Token | will |
Token ID | 481 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
sent | +0.635 |
kins | +0.627 |
.# | +0.616 |
\\ | +0.612 |
Limit | +0.606 |
Neg logit contributions | |
�� | -0.819 |
esty | -0.784 |
Lund | -0.780 |
Dickinson | -0.778 |
allic | -0.776 |
Token | receive |
Token ID | 3328 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
sent | +0.284 |
kins | +0.274 |
.# | +0.272 |
\\ | +0.266 |
SEE | +0.260 |
Neg logit contributions | |
�� | -0.781 |
esty | -0.766 |
Lund | -0.755 |
Dickinson | -0.755 |
allic | -0.755 |
Token | emails |
Token ID | 7237 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
sent | +1.310 |
kins | +1.276 |
.# | +1.268 |
\\ | +1.254 |
SEE | +1.251 |
Neg logit contributions | |
�� | -1.402 |
esty | -1.321 |
Dickinson | -1.308 |
allic | -1.293 |
Lund | -1.283 |
Token | would |
Token ID | 561 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.083 |
esty | +0.082 |
Dickinson | +0.082 |
allic | +0.081 |
Lund | +0.081 |
Neg logit contributions | |
sent | -0.067 |
kins | -0.066 |
.# | -0.065 |
\\ | -0.064 |
SEE | -0.064 |
Token | like |
Token ID | 588 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
sent | +0.071 |
kins | +0.070 |
.# | +0.069 |
\\ | +0.068 |
SEE | +0.068 |
Neg logit contributions | |
�� | -0.092 |
esty | -0.091 |
Dickinson | -0.091 |
allic | -0.090 |
Lund | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
sent | +0.117 |
kins | +0.115 |
.# | +0.114 |
SEE | +0.113 |
\\ | +0.113 |
Neg logit contributions | |
�� | -0.123 |
esty | -0.123 |
Dickinson | -0.122 |
Lund | -0.121 |
allic | -0.121 |
Token | hi |
Token ID | 23105 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
sent | +0.154 |
kins | +0.150 |
.# | +0.150 |
SEE | +0.148 |
\\ | +0.147 |
Neg logit contributions | |
�� | -0.193 |
esty | -0.192 |
Dickinson | -0.191 |
Lund | -0.190 |
allic | -0.190 |
Token | - |
Token ID | 12 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
sent | +0.285 |
kins | +0.279 |
.# | +0.278 |
SEE | +0.275 |
\\ | +0.274 |
Neg logit contributions | |
esty | -0.316 |
�� | -0.316 |
allic | -0.315 |
Dickinson | -0.313 |
Lund | -0.312 |
Token | res |
Token ID | 411 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
sent | +0.250 |
kins | +0.242 |
.# | +0.239 |
SEE | +0.234 |
\\ | +0.234 |
Neg logit contributions | |
�� | -0.595 |
esty | -0.591 |
Dickinson | -0.589 |
Lund | -0.586 |
allic | -0.586 |
Token | version |
Token ID | 2196 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
sent | +1.589 |
kins | +1.579 |
.# | +1.557 |
\\ | +1.537 |
SEE | +1.531 |
Neg logit contributions | |
�� | -1.958 |
esty | -1.924 |
Dickinson | -1.918 |
allic | -1.910 |
abbit | -1.897 |
Token | of |
Token ID | 286 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
sent | +0.232 |
kins | +0.227 |
.# | +0.225 |
SEE | +0.222 |
\\ | +0.221 |
Neg logit contributions | |
�� | -0.310 |
esty | -0.309 |
Dickinson | -0.307 |
Lund | -0.306 |
allic | -0.306 |
Token | your |
Token ID | 534 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
sent | +0.177 |
kins | +0.174 |
.# | +0.173 |
SEE | +0.171 |
\\ | +0.170 |
Neg logit contributions | |
�� | -0.225 |
esty | -0.224 |
Dickinson | -0.223 |
allic | -0.222 |
Lund | -0.222 |
Token | image |
Token ID | 2939 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
sent | +0.119 |
kins | +0.116 |
.# | +0.115 |
SEE | +0.114 |
\\ | +0.114 |
Neg logit contributions | |
�� | -0.169 |
esty | -0.168 |
Dickinson | -0.167 |
allic | -0.166 |
Lund | -0.166 |
Token | please |
Token ID | 3387 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
esty | +0.133 |
�� | +0.133 |
Dickinson | +0.132 |
Lund | +0.132 |
allic | +0.131 |
Neg logit contributions | |
sent | -0.114 |
kins | -0.112 |
.# | -0.111 |
SEE | -0.110 |
\\ | -0.109 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
sent | +0.429 |
kins | +0.421 |
.# | +0.420 |
\\ | +0.411 |
SEE | +0.410 |
Neg logit contributions | |
�� | -0.561 |
esty | -0.552 |
allic | -0.549 |
Dickinson | -0.548 |
Lund | -0.544 |
Token | , |
Token ID | 11 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
sent | +0.072 |
kins | +0.071 |
.# | +0.070 |
SEE | +0.069 |
\\ | +0.069 |
Neg logit contributions | |
�� | -0.108 |
esty | -0.108 |
Dickinson | -0.107 |
allic | -0.107 |
Lund | -0.107 |
Token | " |
Token ID | 366 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
sent | +0.022 |
kins | +0.021 |
.# | +0.021 |
\\ | +0.021 |
SEE | +0.021 |
Neg logit contributions | |
�� | -0.027 |
esty | -0.026 |
Dickinson | -0.026 |
allic | -0.026 |
abbit | -0.026 |
Token | Final |
Token ID | 19006 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
�� | +0.099 |
esty | +0.098 |
Dickinson | +0.097 |
allic | +0.097 |
Lund | +0.097 |
Neg logit contributions | |
sent | -0.072 |
kins | -0.071 |
.# | -0.070 |
SEE | -0.069 |
\\ | -0.069 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
sent | +1.030 |
kins | +1.016 |
.# | +1.013 |
Limit | +1.003 |
\\ | +1.001 |
Neg logit contributions | |
�� | -0.736 |
esty | -0.728 |
allic | -0.724 |
Dickinson | -0.721 |
Lund | -0.716 |
Token | XV |
Token ID | 29922 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
sent | +0.915 |
kins | +0.904 |
.# | +0.897 |
\\ | +0.885 |
SEE | +0.882 |
Neg logit contributions | |
�� | -1.137 |
esty | -1.125 |
allic | -1.116 |
Dickinson | -1.116 |
Lund | -1.109 |
Token | " |
Token ID | 1 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
sent | +1.440 |
kins | +1.414 |
.# | +1.409 |
\\ | +1.384 |
SEE | +1.380 |
Neg logit contributions | |
�� | -2.098 |
esty | -2.073 |
Dickinson | -2.064 |
allic | -2.063 |
Lund | -2.046 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
�� | +0.024 |
esty | +0.024 |
Dickinson | +0.024 |
Lund | +0.024 |
allic | +0.024 |
Neg logit contributions | |
sent | -0.018 |
kins | -0.018 |
.# | -0.018 |
SEE | -0.018 |
\\ | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
sent | +0.361 |
kins | +0.354 |
.# | +0.351 |
SEE | +0.346 |
\\ | +0.345 |
Neg logit contributions | |
�� | -0.495 |
esty | -0.492 |
Dickinson | -0.490 |
allic | -0.488 |
Lund | -0.487 |
Token | King |
Token ID | 15708 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
sent | +0.118 |
kins | +0.115 |
.# | +0.113 |
SEE | +0.111 |
\\ | +0.111 |
Neg logit contributions | |
�� | -0.248 |
esty | -0.248 |
allic | -0.246 |
Dickinson | -0.246 |
Lund | -0.246 |
Token | dom |
Token ID | 3438 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
sent | +0.405 |
kins | +0.396 |
.# | +0.393 |
SEE | +0.389 |
\\ | +0.386 |
Neg logit contributions | |
�� | -0.571 |
esty | -0.568 |
Dickinson | -0.565 |
Lund | -0.563 |
allic | -0.563 |
Token | to |
Token ID | 284 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
sent | +0.563 |
kins | +0.554 |
.# | +0.545 |
SEE | +0.545 |
\\ | +0.543 |
Neg logit contributions | |
esty | -0.593 |
�� | -0.591 |
Dickinson | -0.589 |
Lund | -0.583 |
allic | -0.583 |
Token | plea |
Token ID | 16720 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
�� | +0.329 |
esty | +0.325 |
Dickinson | +0.323 |
allic | +0.322 |
Lund | +0.321 |
Neg logit contributions | |
sent | -0.304 |
kins | -0.299 |
.# | -0.297 |
SEE | -0.293 |
\\ | -0.293 |
Token | - |
Token ID | 12 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
esty | +0.561 |
�� | +0.560 |
Dickinson | +0.557 |
Lund | +0.556 |
allic | +0.554 |
Neg logit contributions | |
sent | -0.495 |
kins | -0.485 |
.# | -0.479 |
SEE | -0.477 |
\\ | -0.475 |
Token | b |
Token ID | 65 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
sent | +0.095 |
kins | +0.094 |
.# | +0.093 |
SEE | +0.092 |
\\ | +0.092 |
Neg logit contributions | |
�� | -0.092 |
esty | -0.091 |
Dickinson | -0.091 |
allic | -0.090 |
Lund | -0.090 |
Token | arg |
Token ID | 853 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
�� | +0.050 |
esty | +0.049 |
Dickinson | +0.049 |
allic | +0.049 |
Lund | +0.049 |
Neg logit contributions | |
sent | -0.063 |
kins | -0.062 |
.# | -0.062 |
\\ | -0.061 |
SEE | -0.061 |
Token | ain |
Token ID | 391 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
esty | +0.204 |
�� | +0.203 |
Dickinson | +0.202 |
allic | +0.202 |
Lund | +0.202 |
Neg logit contributions | |
sent | -0.180 |
kins | -0.178 |
.# | -0.176 |
SEE | -0.175 |
\\ | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
sent | +1.452 |
.# | +1.425 |
kins | +1.421 |
\\ | +1.384 |
SEE | +1.380 |
Neg logit contributions | |
�� | -2.111 |
esty | -2.044 |
allic | -2.043 |
Dickinson | -2.040 |
abbit | -2.033 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
�� | +0.073 |
esty | +0.072 |
Dickinson | +0.072 |
allic | +0.072 |
Lund | +0.071 |
Neg logit contributions | |
sent | -0.057 |
kins | -0.056 |
.# | -0.055 |
SEE | -0.054 |
\\ | -0.054 |
Token | lawyers |
Token ID | 9326 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
�� | +0.266 |
esty | +0.266 |
Dickinson | +0.265 |
Lund | +0.264 |
allic | +0.263 |
Neg logit contributions | |
sent | -0.215 |
kins | -0.212 |
.# | -0.210 |
SEE | -0.208 |
\\ | -0.208 |
Token | make |
Token ID | 787 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +0.551 |
esty | +0.548 |
Dickinson | +0.545 |
allic | +0.542 |
Lund | +0.541 |
Neg logit contributions | |
sent | -0.497 |
kins | -0.489 |
.# | -0.485 |
SEE | -0.480 |
\\ | -0.478 |
Token | a |
Token ID | 257 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
�� | +0.128 |
esty | +0.127 |
Dickinson | +0.127 |
allic | +0.126 |
Lund | +0.126 |
Neg logit contributions | |
sent | -0.120 |
kins | -0.118 |
.# | -0.117 |
SEE | -0.116 |
\\ | -0.116 |
Token | ventures |
Token ID | 10065 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
sent | +0.377 |
kins | +0.371 |
.# | +0.369 |
SEE | +0.364 |
\\ | +0.364 |
Neg logit contributions | |
�� | -0.371 |
esty | -0.368 |
Dickinson | -0.365 |
allic | -0.365 |
Lund | -0.363 |
Token | t |
Token ID | 256 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
sent | +0.162 |
kins | +0.159 |
.# | +0.158 |
SEE | +0.156 |
\\ | +0.155 |
Neg logit contributions | |
�� | -0.211 |
esty | -0.210 |
Dickinson | -0.210 |
allic | -0.209 |
Lund | -0.208 |
Token | - |
Token ID | 12 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
sent | +0.522 |
kins | +0.514 |
.# | +0.509 |
SEE | +0.503 |
\\ | +0.503 |
Neg logit contributions | |
�� | -0.588 |
esty | -0.582 |
Dickinson | -0.579 |
allic | -0.577 |
Lund | -0.576 |
Token | shirts |
Token ID | 23231 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
sent | +0.111 |
kins | +0.109 |
.# | +0.106 |
\\ | +0.106 |
SEE | +0.106 |
Neg logit contributions | |
�� | -0.159 |
esty | -0.157 |
Dickinson | -0.156 |
Lund | -0.156 |
allic | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
sent | +0.159 |
kins | +0.157 |
.# | +0.156 |
SEE | +0.153 |
\\ | +0.153 |
Neg logit contributions | |
�� | -0.203 |
esty | -0.201 |
allic | -0.200 |
Dickinson | -0.200 |
Lund | -0.199 |
Token | prints |
Token ID | 20842 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
sent | +0.234 |
kins | +0.230 |
.# | +0.228 |
\\ | +0.225 |
SEE | +0.225 |
Neg logit contributions | |
�� | -0.270 |
esty | -0.268 |
Dickinson | -0.266 |
allic | -0.265 |
Lund | -0.264 |
Token | , |
Token ID | 11 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
sent | +1.495 |
kins | +1.481 |
.# | +1.459 |
\\ | +1.440 |
SEE | +1.438 |
Neg logit contributions | |
�� | -1.996 |
esty | -1.977 |
allic | -1.969 |
Dickinson | -1.968 |
Lund | -1.958 |
Token | DVDs |
Token ID | 35962 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
sent | +0.246 |
kins | +0.242 |
.# | +0.240 |
SEE | +0.237 |
\\ | +0.236 |
Neg logit contributions | |
�� | -0.294 |
esty | -0.292 |
Dickinson | -0.290 |
allic | -0.289 |
Lund | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
sent | +0.332 |
kins | +0.325 |
.# | +0.323 |
SEE | +0.319 |
\\ | +0.318 |
Neg logit contributions | |
�� | -0.412 |
esty | -0.411 |
Dickinson | -0.408 |
allic | -0.406 |
Lund | -0.406 |
Token | comic |
Token ID | 9048 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
sent | +0.161 |
kins | +0.158 |
.# | +0.157 |
SEE | +0.155 |
\\ | +0.155 |
Neg logit contributions | |
�� | -0.194 |
esty | -0.192 |
Dickinson | -0.192 |
allic | -0.191 |
Lund | -0.191 |
Token | books |
Token ID | 3835 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
�� | +0.334 |
esty | +0.331 |
Dickinson | +0.329 |
allic | +0.328 |
Lund | +0.327 |
Neg logit contributions | |
sent | -0.354 |
kins | -0.349 |
.# | -0.347 |
SEE | -0.343 |
\\ | -0.342 |
Token | go |
Token ID | 467 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
�� | +0.032 |
esty | +0.031 |
Dickinson | +0.031 |
allic | +0.031 |
Lund | +0.031 |
Neg logit contributions | |
sent | -0.033 |
kins | -0.033 |
.# | -0.033 |
\\ | -0.032 |
SEE | -0.032 |
Token | sour |
Token ID | 11348 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
sent | +0.067 |
kins | +0.067 |
.# | +0.066 |
\\ | +0.065 |
SEE | +0.065 |
Neg logit contributions | |
�� | -0.068 |
esty | -0.067 |
Dickinson | -0.066 |
allic | -0.066 |
Lund | -0.066 |
Token | ." |
Token ID | 526 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
sent | +0.992 |
kins | +0.984 |
.# | +0.973 |
\\ | +0.950 |
SEE | +0.941 |
Neg logit contributions | |
�� | -1.517 |
Dickinson | -1.482 |
esty | -1.480 |
allic | -1.472 |
Lund | -1.468 |
Token | Does |
Token ID | 8314 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
�� | +0.358 |
esty | +0.353 |
allic | +0.349 |
abbit | +0.347 |
Dickinson | +0.346 |
Neg logit contributions | |
sent | -0.279 |
kins | -0.275 |
.# | -0.272 |
SEE | -0.269 |
\\ | -0.269 |
Token | that |
Token ID | 326 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
sent | +0.747 |
kins | +0.741 |
.# | +0.729 |
\\ | +0.723 |
SEE | +0.721 |
Neg logit contributions | |
�� | -0.855 |
esty | -0.832 |
allic | -0.830 |
abbit | -0.824 |
Dickinson | -0.823 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
�� | +0.255 |
esty | +0.252 |
Dickinson | +0.250 |
allic | +0.249 |
Lund | +0.248 |
Neg logit contributions | |
sent | -0.280 |
kins | -0.276 |
.# | -0.274 |
\\ | -0.270 |
SEE | -0.270 |
Token | that |
Token ID | 326 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +1.291 |
esty | +1.279 |
Dickinson | +1.271 |
allic | +1.268 |
Lund | +1.263 |
Neg logit contributions | |
sent | -1.267 |
kins | -1.248 |
.# | -1.238 |
SEE | -1.223 |
\\ | -1.222 |
Token | all |
Token ID | 477 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
�� | +0.131 |
esty | +0.128 |
allic | +0.127 |
Dickinson | +0.126 |
abbit | +0.126 |
Neg logit contributions | |
sent | -0.119 |
kins | -0.117 |
.# | -0.116 |
\\ | -0.115 |
Limit | -0.114 |
Token | Got |
Token ID | 11853 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
�� | +0.043 |
esty | +0.041 |
allic | +0.041 |
abbit | +0.041 |
Dickinson | +0.041 |
Neg logit contributions | |
sent | -0.043 |
kins | -0.042 |
.# | -0.042 |
\\ | -0.041 |
SEE | -0.041 |
Token | lands |
Token ID | 4447 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
sent | +0.446 |
kins | +0.442 |
.# | +0.430 |
\\ | +0.424 |
SEE | +0.424 |
Neg logit contributions | |
�� | -0.677 |
Dickinson | -0.657 |
esty | -0.657 |
allic | -0.653 |
Lund | -0.651 |
Token | d |
Token ID | 67 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
sent | +0.490 |
kins | +0.486 |
.# | +0.479 |
\\ | +0.474 |
SEE | +0.473 |
Neg logit contributions | |
�� | -0.380 |
esty | -0.369 |
allic | -0.366 |
Dickinson | -0.364 |
abbit | -0.361 |
Token | actually |
Token ID | 1682 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
sent | +0.123 |
kins | +0.121 |
.# | +0.120 |
\\ | +0.119 |
SEE | +0.118 |
Neg logit contributions | |
�� | -0.125 |
esty | -0.124 |
Dickinson | -0.123 |
allic | -0.122 |
Lund | -0.122 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
sent | +0.254 |
kins | +0.250 |
.# | +0.249 |
\\ | +0.245 |
SEE | +0.245 |
Neg logit contributions | |
�� | -0.256 |
esty | -0.251 |
Dickinson | -0.249 |
allic | -0.249 |
Lund | -0.248 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
sent | +0.193 |
kins | +0.190 |
.# | +0.188 |
SEE | +0.187 |
\\ | +0.186 |
Neg logit contributions | |
esty | -0.214 |
�� | -0.213 |
Dickinson | -0.212 |
allic | -0.211 |
Lund | -0.211 |
Token | how |
Token ID | 703 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
esty | +0.060 |
�� | +0.060 |
Dickinson | +0.060 |
Lund | +0.059 |
allic | +0.059 |
Neg logit contributions | |
sent | -0.057 |
kins | -0.056 |
.# | -0.055 |
SEE | -0.055 |
\\ | -0.055 |
Token | non |
Token ID | 1729 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
sent | +0.367 |
kins | +0.361 |
.# | +0.358 |
\\ | +0.352 |
SEE | +0.351 |
Neg logit contributions | |
�� | -0.421 |
esty | -0.409 |
allic | -0.408 |
abbit | -0.405 |
Dickinson | -0.405 |
Token | chal |
Token ID | 38009 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
sent | +0.358 |
kins | +0.353 |
.# | +0.349 |
\\ | +0.345 |
SEE | +0.345 |
Neg logit contributions | |
�� | -0.356 |
esty | -0.350 |
Dickinson | -0.349 |
allic | -0.347 |
Lund | -0.347 |
Token | antly |
Token ID | 3875 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
esty | +0.989 |
allic | +0.974 |
Dickinson | +0.969 |
Lund | +0.964 |
abbit | +0.963 |
Neg logit contributions | |
sent | -1.394 |
kins | -1.381 |
.# | -1.370 |
SEE | -1.359 |
\\ | -1.351 |
Token | some |
Token ID | 617 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
�� | +0.414 |
esty | +0.413 |
Dickinson | +0.411 |
allic | +0.409 |
Lund | +0.409 |
Neg logit contributions | |
sent | -0.357 |
kins | -0.351 |
.# | -0.347 |
SEE | -0.343 |
\\ | -0.343 |
Token | say |
Token ID | 910 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
esty | +0.234 |
Dickinson | +0.233 |
�� | +0.233 |
Lund | +0.232 |
allic | +0.232 |
Neg logit contributions | |
sent | -0.191 |
kins | -0.188 |
.# | -0.186 |
SEE | -0.184 |
\\ | -0.183 |
Token | that |
Token ID | 326 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
sent | +0.057 |
kins | +0.056 |
.# | +0.055 |
SEE | +0.055 |
\\ | +0.054 |
Neg logit contributions | |
�� | -0.066 |
esty | -0.065 |
Dickinson | -0.065 |
allic | -0.065 |
Lund | -0.064 |
Token | it |
Token ID | 340 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
sent | +0.019 |
kins | +0.019 |
.# | +0.019 |
SEE | +0.018 |
\\ | +0.018 |
Neg logit contributions | |
�� | -0.022 |
esty | -0.022 |
Dickinson | -0.022 |
allic | -0.022 |
Lund | -0.022 |
Token | | |
Token ID | 930 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�� | +0.862 |
esty | +0.862 |
Lund | +0.861 |
Dickinson | +0.854 |
allic | +0.853 |
Neg logit contributions | |
sent | -0.781 |
kins | -0.778 |
.# | -0.768 |
SEE | -0.748 |
\\ | -0.747 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
�� | +0.873 |
Dickinson | +0.866 |
Lund | +0.863 |
esty | +0.863 |
allic | +0.860 |
Neg logit contributions | |
sent | -0.859 |
kins | -0.847 |
.# | -0.837 |
SEE | -0.825 |
Tab | -0.818 |
Token | | |
Token ID | 930 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
sent | +0.270 |
kins | +0.264 |
.# | +0.264 |
\\ | +0.262 |
SEE | +0.259 |
Neg logit contributions | |
�� | -0.360 |
esty | -0.348 |
Dickinson | -0.345 |
allic | -0.344 |
abbit | -0.342 |
Token | org |
Token ID | 8745 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
�� | +0.841 |
esty | +0.835 |
Lund | +0.831 |
Dickinson | +0.830 |
allic | +0.824 |
Neg logit contributions | |
sent | -0.908 |
kins | -0.893 |
.# | -0.888 |
SEE | -0.877 |
\\ | -0.868 |
Token | . |
Token ID | 764 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
�� | +1.311 |
esty | +1.305 |
Dickinson | +1.300 |
allic | +1.297 |
Lund | +1.294 |
Neg logit contributions | |
sent | -0.594 |
kins | -0.580 |
.# | -0.572 |
SEE | -0.562 |
\\ | -0.560 |
Token | cl |
Token ID | 537 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
�� | +0.420 |
esty | +0.405 |
Dickinson | +0.403 |
allic | +0.400 |
abbit | +0.397 |
Neg logit contributions | |
sent | -0.454 |
kins | -0.447 |
.# | -0.445 |
\\ | -0.442 |
SEE | -0.434 |
Token | ojure |
Token ID | 32511 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
�� | +1.860 |
esty | +1.842 |
Dickinson | +1.836 |
allic | +1.828 |
Lund | +1.827 |
Neg logit contributions | |
sent | -1.184 |
kins | -1.161 |
.# | -1.149 |
\\ | -1.130 |
SEE | -1.128 |
Token | / |
Token ID | 1220 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
�� | +0.506 |
esty | +0.498 |
Dickinson | +0.494 |
allic | +0.492 |
Lund | +0.490 |
Neg logit contributions | |
sent | -0.406 |
kins | -0.399 |
.# | -0.396 |
\\ | -0.392 |
SEE | -0.390 |
Token | core |
Token ID | 4755 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
�� | +0.394 |
esty | +0.392 |
Dickinson | +0.389 |
allic | +0.388 |
Lund | +0.387 |
Neg logit contributions | |
sent | -0.378 |
kins | -0.372 |
.# | -0.369 |
SEE | -0.365 |
\\ | -0.364 |
Token | . |
Token ID | 764 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
esty | +1.922 |
�� | +1.921 |
Dickinson | +1.911 |
allic | +1.901 |
Lund | +1.901 |
Neg logit contributions | |
sent | -1.032 |
kins | -1.002 |
.# | -0.989 |
SEE | -0.976 |
Limit | -0.967 |
Token | match |
Token ID | 2872 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
�� | +0.763 |
esty | +0.760 |
Dickinson | +0.756 |
Lund | +0.752 |
allic | +0.752 |
Neg logit contributions | |
sent | -0.640 |
kins | -0.628 |
.# | -0.623 |
SEE | -0.616 |
\\ | -0.613 |
Token | null |
Token ID | 9242 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
esty | +0.575 |
�� | +0.574 |
Dickinson | +0.572 |
Lund | +0.570 |
allic | +0.569 |
Neg logit contributions | |
sent | -0.625 |
kins | -0.618 |
.# | -0.613 |
SEE | -0.608 |
\\ | -0.602 |
Token | atomic |
Token ID | 17226 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
�� | +0.523 |
esty | +0.519 |
Dickinson | +0.516 |
allic | +0.514 |
Lund | +0.512 |
Neg logit contributions | |
sent | -0.685 |
kins | -0.676 |
.# | -0.672 |
SEE | -0.665 |
\\ | -0.664 |
Token | pointer |
Token ID | 17562 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
�� | +0.818 |
Dickinson | +0.817 |
esty | +0.817 |
allic | +0.813 |
Lund | +0.811 |
Neg logit contributions | |
sent | -0.667 |
kins | -0.658 |
.# | -0.645 |
SEE | -0.642 |
\\ | -0.636 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Dickinson | +1.479 |
esty | +1.473 |
allic | +1.467 |
Lund | +1.467 |
�� | +1.462 |
Neg logit contributions | |
sent | -1.158 |
kins | -1.137 |
SEE | -1.112 |
.# | -1.106 |
\\ | -1.094 |
Token | pub |
Token ID | 2240 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
�� | +0.925 |
esty | +0.924 |
Dickinson | +0.924 |
allic | +0.920 |
Lund | +0.918 |
Neg logit contributions | |
sent | -0.733 |
kins | -0.722 |
.# | -0.711 |
SEE | -0.704 |
\\ | -0.700 |
Token | fn |
Token ID | 24714 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
�� | +1.282 |
esty | +1.276 |
Lund | +1.272 |
Dickinson | +1.272 |
allic | +1.265 |
Neg logit contributions | |
sent | -1.204 |
kins | -1.195 |
SEE | -1.167 |
.# | -1.165 |
\\ | -1.144 |
Token | null |
Token ID | 9242 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Lund | +1.708 |
Dickinson | +1.703 |
esty | +1.699 |
�� | +1.697 |
allic | +1.692 |
Neg logit contributions | |
sent | -1.016 |
kins | -1.004 |
SEE | -0.986 |
.# | -0.985 |
\\ | -0.961 |
Token | () |
Token ID | 7499 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
�� | +0.477 |
esty | +0.476 |
allic | +0.475 |
Dickinson | +0.473 |
Lund | +0.471 |
Neg logit contributions | |
sent | -0.308 |
kins | -0.303 |
.# | -0.301 |
SEE | -0.297 |
\\ | -0.296 |
Token | -> |
Token ID | 4613 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
esty | +0.483 |
Lund | +0.482 |
Dickinson | +0.482 |
allic | +0.481 |
�� | +0.480 |
Neg logit contributions | |
sent | -0.192 |
kins | -0.187 |
.# | -0.184 |
SEE | -0.184 |
\\ | -0.177 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
�� | +0.525 |
esty | +0.524 |
Dickinson | +0.523 |
Lund | +0.520 |
allic | +0.520 |
Neg logit contributions | |
sent | -0.360 |
kins | -0.354 |
.# | -0.349 |
SEE | -0.345 |
\\ | -0.343 |
Token | < |
Token ID | 1279 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
�� | +0.671 |
esty | +0.671 |
Dickinson | +0.669 |
Lund | +0.666 |
allic | +0.666 |
Neg logit contributions | |
sent | -0.607 |
kins | -0.602 |
.# | -0.593 |
SEE | -0.585 |
\\ | -0.583 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
�� | +0.890 |
esty | +0.885 |
Dickinson | +0.881 |
allic | +0.877 |
Lund | +0.875 |
Neg logit contributions | |
sent | -0.769 |
kins | -0.757 |
.# | -0.750 |
SEE | -0.741 |
\\ | -0.740 |
Token | sight |
Token ID | 6504 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
�� | +0.298 |
esty | +0.295 |
Dickinson | +0.293 |
allic | +0.292 |
Lund | +0.291 |
Neg logit contributions | |
sent | -0.295 |
kins | -0.291 |
.# | -0.289 |
SEE | -0.285 |
\\ | -0.285 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
sent | +0.538 |
kins | +0.526 |
.# | +0.525 |
\\ | +0.515 |
SEE | +0.514 |
Neg logit contributions | |
�� | -0.719 |
esty | -0.705 |
allic | -0.702 |
Dickinson | -0.700 |
abbit | -0.696 |
Token | the |
Token ID | 262 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
�� | +0.187 |
esty | +0.185 |
Dickinson | +0.184 |
allic | +0.183 |
Lund | +0.183 |
Neg logit contributions | |
sent | -0.177 |
kins | -0.174 |
.# | -0.173 |
SEE | -0.171 |
\\ | -0.170 |
Token | Cuban |
Token ID | 18147 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
�� | +0.261 |
esty | +0.259 |
Dickinson | +0.257 |
allic | +0.256 |
Lund | +0.255 |
Neg logit contributions | |
sent | -0.254 |
kins | -0.249 |
.# | -0.248 |
SEE | -0.245 |
\\ | -0.244 |
Token | flag |
Token ID | 6056 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
esty | +0.463 |
�� | +0.462 |
Dickinson | +0.460 |
allic | +0.458 |
Lund | +0.457 |
Neg logit contributions | |
sent | -0.496 |
kins | -0.488 |
.# | -0.486 |
SEE | -0.481 |
\\ | -0.478 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
esty | +1.462 |
Dickinson | +1.457 |
�� | +1.448 |
Lund | +1.448 |
allic | +1.443 |
Neg logit contributions | |
sent | -1.551 |
kins | -1.524 |
.# | -1.517 |
SEE | -1.513 |
\\ | -1.499 |
Token | new |
Token ID | 649 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
�� | +0.294 |
esty | +0.290 |
Dickinson | +0.289 |
allic | +0.288 |
Lund | +0.287 |
Neg logit contributions | |
sent | -0.277 |
kins | -0.272 |
.# | -0.270 |
SEE | -0.267 |
\\ | -0.267 |
Token | and |
Token ID | 290 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
�� | +0.690 |
esty | +0.689 |
Dickinson | +0.683 |
allic | +0.682 |
Lund | +0.681 |
Neg logit contributions | |
sent | -0.558 |
kins | -0.549 |
.# | -0.544 |
SEE | -0.539 |
\\ | -0.537 |
Token | brightly |
Token ID | 35254 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
�� | +0.005 |
esty | +0.005 |
Dickinson | +0.005 |
allic | +0.005 |
Lund | +0.005 |
Neg logit contributions | |
sent | -0.005 |
kins | -0.005 |
.# | -0.005 |
\\ | -0.005 |
SEE | -0.005 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
�� | +0.757 |
esty | +0.753 |
Dickinson | +0.748 |
allic | +0.745 |
Lund | +0.743 |
Neg logit contributions | |
sent | -0.908 |
kins | -0.895 |
.# | -0.889 |
SEE | -0.880 |
\\ | -0.878 |
Token | wa |
Token ID | 10247 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
�� | +0.779 |
esty | +0.777 |
Dickinson | +0.772 |
allic | +0.771 |
Lund | +0.769 |
Neg logit contributions | |
sent | -0.676 |
kins | -0.665 |
.# | -0.660 |
SEE | -0.653 |
\\ | -0.650 |
Token | na |
Token ID | 12385 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
�� | +0.326 |
esty | +0.324 |
Dickinson | +0.322 |
allic | +0.321 |
Lund | +0.320 |
Neg logit contributions | |
sent | -0.270 |
kins | -0.265 |
.# | -0.263 |
SEE | -0.260 |
\\ | -0.259 |
Token | ang |
Token ID | 3550 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
sent | +0.555 |
kins | +0.547 |
.# | +0.542 |
\\ | +0.537 |
SEE | +0.532 |
Neg logit contributions | |
�� | -0.562 |
esty | -0.553 |
Dickinson | -0.551 |
allic | -0.548 |
Lund | -0.544 |
Token | kan |
Token ID | 43998 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
sent | +0.170 |
kins | +0.167 |
.# | +0.166 |
\\ | +0.164 |
SEE | +0.164 |
Neg logit contributions | |
�� | -0.174 |
esty | -0.171 |
Dickinson | -0.171 |
allic | -0.170 |
Lund | -0.169 |
Token | il |
Token ID | 346 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
�� | +0.212 |
Dickinson | +0.210 |
esty | +0.209 |
Lund | +0.208 |
allic | +0.208 |
Neg logit contributions | |
sent | -0.185 |
kins | -0.182 |
.# | -0.179 |
\\ | -0.178 |
SEE | -0.177 |
Token | ang |
Token ID | 648 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
�� | +0.067 |
esty | +0.066 |
Dickinson | +0.066 |
Lund | +0.065 |
allic | +0.065 |
Neg logit contributions | |
sent | -0.061 |
kins | -0.060 |
.# | -0.059 |
\\ | -0.058 |
SEE | -0.058 |
Token | an |
Token ID | 281 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
�� | +0.231 |
esty | +0.229 |
Dickinson | +0.227 |
allic | +0.226 |
Lund | +0.226 |
Neg logit contributions | |
sent | -0.210 |
kins | -0.207 |
.# | -0.205 |
\\ | -0.202 |
SEE | -0.202 |
Token | ak |
Token ID | 461 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
�� | +0.099 |
esty | +0.098 |
Dickinson | +0.097 |
allic | +0.097 |
Lund | +0.097 |
Neg logit contributions | |
sent | -0.086 |
kins | -0.085 |
.# | -0.084 |
SEE | -0.083 |
\\ | -0.083 |
Token | ay |
Token ID | 38762 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
sent | +0.920 |
kins | +0.907 |
.# | +0.883 |
\\ | +0.879 |
SEE | +0.868 |
Neg logit contributions | |
�� | -1.043 |
Dickinson | -1.021 |
esty | -1.006 |
Lund | -1.001 |
abbit | -0.998 |
Token | n |
Token ID | 299 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
�� | +0.164 |
esty | +0.163 |
Dickinson | +0.162 |
allic | +0.161 |
Lund | +0.161 |
Neg logit contributions | |
sent | -0.165 |
kins | -0.162 |
.# | -0.161 |
\\ | -0.159 |
SEE | -0.159 |
Token | al |
Token ID | 282 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
�� | +0.009 |
esty | +0.009 |
Dickinson | +0.009 |
allic | +0.009 |
Lund | +0.009 |
Neg logit contributions | |
sent | -0.008 |
kins | -0.007 |
.# | -0.007 |
SEE | -0.007 |
\\ | -0.007 |
Token | such |
Token ID | 884 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
�� | +0.534 |
esty | +0.533 |
Dickinson | +0.530 |
allic | +0.528 |
Lund | +0.528 |
Neg logit contributions | |
sent | -0.522 |
kins | -0.514 |
.# | -0.510 |
SEE | -0.504 |
\\ | -0.503 |
Token | as |
Token ID | 355 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
�� | +0.468 |
esty | +0.459 |
allic | +0.456 |
Dickinson | +0.455 |
abbit | +0.452 |
Neg logit contributions | |
sent | -0.281 |
kins | -0.277 |
.# | -0.274 |
\\ | -0.269 |
SEE | -0.268 |
Token | doctors |
Token ID | 7519 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Dickinson | +0.553 |
esty | +0.551 |
Lund | +0.551 |
�� | +0.550 |
allic | +0.545 |
Neg logit contributions | |
sent | -0.482 |
kins | -0.474 |
.# | -0.469 |
SEE | -0.464 |
\\ | -0.462 |
Token | – |
Token ID | 784 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
esty | +0.178 |
�� | +0.178 |
Dickinson | +0.177 |
Lund | +0.176 |
allic | +0.176 |
Neg logit contributions | |
sent | -0.155 |
kins | -0.151 |
.# | -0.150 |
SEE | -0.149 |
\\ | -0.148 |
Token | out |
Token ID | 503 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
esty | +0.503 |
Dickinson | +0.502 |
�� | +0.500 |
Lund | +0.497 |
allic | +0.496 |
Neg logit contributions | |
sent | -0.455 |
kins | -0.448 |
.# | -0.447 |
SEE | -0.442 |
\\ | -0.439 |
Token | of |
Token ID | 286 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
esty | +0.045 |
�� | +0.045 |
Dickinson | +0.045 |
Lund | +0.044 |
allic | +0.044 |
Neg logit contributions | |
sent | -0.035 |
kins | -0.034 |
SEE | -0.034 |
.# | -0.034 |
\\ | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
�� | +0.220 |
esty | +0.219 |
Dickinson | +0.219 |
Lund | +0.218 |
allic | +0.217 |
Neg logit contributions | |
sent | -0.194 |
kins | -0.191 |
.# | -0.189 |
SEE | -0.187 |
\\ | -0.186 |
Token | country |
Token ID | 1499 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
�� | +0.201 |
esty | +0.199 |
Dickinson | +0.198 |
allic | +0.197 |
Lund | +0.197 |
Neg logit contributions | |
sent | -0.184 |
kins | -0.182 |
.# | -0.180 |
SEE | -0.178 |
\\ | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
sent | +0.056 |
kins | +0.055 |
.# | +0.055 |
SEE | +0.054 |
\\ | +0.054 |
Neg logit contributions | |
�� | -0.081 |
esty | -0.081 |
Dickinson | -0.080 |
Lund | -0.080 |
allic | -0.080 |
Token | The |
Token ID | 383 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Dickinson | +0.054 |
Lund | +0.054 |
esty | +0.054 |
�� | +0.054 |
allic | +0.054 |
Neg logit contributions | |
sent | -0.043 |
kins | -0.043 |
.# | -0.042 |
SEE | -0.042 |
\\ | -0.042 |
Token | Liberals |
Token ID | 20162 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
sent | +0.137 |
kins | +0.135 |
.# | +0.134 |
SEE | +0.132 |
\\ | +0.132 |
Neg logit contributions | |
�� | -0.148 |
esty | -0.147 |
Dickinson | -0.146 |
allic | -0.146 |
Lund | -0.145 |
Token | Republican |
Token ID | 3415 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
�� | +0.546 |
esty | +0.536 |
Dickinson | +0.531 |
allic | +0.531 |
Lund | +0.527 |
Neg logit contributions | |
sent | -0.743 |
kins | -0.733 |
.# | -0.729 |
SEE | -0.722 |
\\ | -0.719 |
Token | contenders |
Token ID | 29467 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
sent | +0.283 |
kins | +0.279 |
.# | +0.277 |
SEE | +0.275 |
\\ | +0.273 |
Neg logit contributions | |
�� | -0.268 |
esty | -0.262 |
Dickinson | -0.261 |
allic | -0.261 |
Lund | -0.259 |
Token | have |
Token ID | 423 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
�� | +0.383 |
esty | +0.381 |
Dickinson | +0.379 |
allic | +0.378 |
Lund | +0.377 |
Neg logit contributions | |
sent | -0.342 |
kins | -0.336 |
.# | -0.334 |
SEE | -0.330 |
\\ | -0.329 |
Token | gone |
Token ID | 3750 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
�� | +0.242 |
esty | +0.238 |
Dickinson | +0.237 |
allic | +0.236 |
Lund | +0.235 |
Neg logit contributions | |
sent | -0.257 |
kins | -0.253 |
.# | -0.252 |
SEE | -0.248 |
\\ | -0.248 |
Token | out |
Token ID | 503 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
�� | +0.076 |
esty | +0.075 |
Dickinson | +0.074 |
allic | +0.074 |
Lund | +0.074 |
Neg logit contributions | |
sent | -0.075 |
kins | -0.073 |
.# | -0.073 |
SEE | -0.072 |
\\ | -0.072 |
Token | of |
Token ID | 286 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
esty | +0.005 |
�� | +0.005 |
Dickinson | +0.005 |
allic | +0.005 |
Lund | +0.005 |
Neg logit contributions | |
sent | -0.004 |
kins | -0.004 |
.# | -0.004 |
SEE | -0.004 |
\\ | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
�� | +0.317 |
esty | +0.317 |
Dickinson | +0.315 |
Lund | +0.314 |
allic | +0.313 |
Neg logit contributions | |
sent | -0.198 |
kins | -0.193 |
.# | -0.191 |
SEE | -0.188 |
\\ | -0.188 |
Token | way |
Token ID | 835 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
�� | +0.050 |
esty | +0.049 |
allic | +0.049 |
Dickinson | +0.049 |
Lund | +0.049 |
Neg logit contributions | |
sent | -0.051 |
kins | -0.050 |
.# | -0.050 |
\\ | -0.049 |
SEE | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
�� | +0.293 |
esty | +0.292 |
Dickinson | +0.289 |
Lund | +0.289 |
allic | +0.288 |
Neg logit contributions | |
sent | -0.285 |
kins | -0.280 |
.# | -0.277 |
\\ | -0.276 |
SEE | -0.275 |
Token | assure |
Token ID | 19832 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
�� | +0.307 |
esty | +0.303 |
Dickinson | +0.302 |
allic | +0.300 |
Lund | +0.300 |
Neg logit contributions | |
sent | -0.286 |
kins | -0.282 |
.# | -0.280 |
SEE | -0.276 |
\\ | -0.276 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
sent | +0.017 |
kins | +0.017 |
.# | +0.016 |
SEE | +0.016 |
\\ | +0.016 |
Neg logit contributions | |
�� | -0.017 |
esty | -0.017 |
Dickinson | -0.017 |
allic | -0.017 |
Lund | -0.017 |
Token | Wi |
Token ID | 11759 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
sent | +0.271 |
kins | +0.267 |
.# | +0.264 |
\\ | +0.261 |
SEE | +0.260 |
Neg logit contributions | |
�� | -0.277 |
esty | -0.273 |
allic | -0.271 |
Dickinson | -0.270 |
abbit | -0.269 |
Token | ener |
Token ID | 877 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
sent | +0.067 |
kins | +0.067 |
.# | +0.066 |
\\ | +0.065 |
SEE | +0.065 |
Neg logit contributions | |
�� | -0.062 |
Dickinson | -0.061 |
esty | -0.060 |
allic | -0.060 |
Lund | -0.060 |
Token | / |
Token ID | 14 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
�� | +0.080 |
esty | +0.079 |
Dickinson | +0.079 |
allic | +0.078 |
Lund | +0.078 |
Neg logit contributions | |
sent | -0.077 |
kins | -0.076 |
.# | -0.075 |
SEE | -0.074 |
\\ | -0.074 |
Token | File |
Token ID | 8979 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
�� | +0.009 |
esty | +0.009 |
Dickinson | +0.009 |
allic | +0.009 |
Lund | +0.009 |
Neg logit contributions | |
sent | -0.007 |
kins | -0.007 |
.# | -0.007 |
SEE | -0.007 |
\\ | -0.007 |
Token | / |
Token ID | 14 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
sent | +0.598 |
kins | +0.590 |
.# | +0.586 |
\\ | +0.579 |
SEE | +0.574 |
Neg logit contributions | |
�� | -0.713 |
allic | -0.699 |
esty | -0.697 |
Dickinson | -0.693 |
abbit | -0.692 |
Token | 1963 |
Token ID | 45192 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
�� | +0.075 |
esty | +0.075 |
Dickinson | +0.074 |
allic | +0.074 |
Lund | +0.074 |
Neg logit contributions | |
sent | -0.063 |
kins | -0.062 |
.# | -0.062 |
SEE | -0.061 |
\\ | -0.061 |
Token | Basketball |
Token ID | 25911 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
�� | +0.014 |
esty | +0.013 |
allic | +0.013 |
Dickinson | +0.013 |
abbit | +0.013 |
Neg logit contributions | |
sent | -0.011 |
kins | -0.011 |
.# | -0.011 |
\\ | -0.011 |
SEE | -0.011 |
Token | goals |
Token ID | 4661 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
�� | +0.092 |
esty | +0.091 |
Dickinson | +0.091 |
allic | +0.091 |
Lund | +0.090 |
Neg logit contributions | |
sent | -0.078 |
kins | -0.077 |
.# | -0.076 |
SEE | -0.075 |
\\ | -0.075 |
Token | were |
Token ID | 547 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
�� | +0.248 |
esty | +0.245 |
allic | +0.243 |
Dickinson | +0.243 |
abbit | +0.241 |
Neg logit contributions | |
sent | -0.198 |
kins | -0.195 |
.# | -0.194 |
\\ | -0.191 |
SEE | -0.190 |
Token | added |
Token ID | 2087 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
sent | +0.198 |
kins | +0.194 |
.# | +0.194 |
\\ | +0.191 |
SEE | +0.190 |
Neg logit contributions | |
�� | -0.194 |
esty | -0.189 |
allic | -0.189 |
Dickinson | -0.188 |
abbit | -0.187 |
Token | to |
Token ID | 284 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
�� | +0.021 |
esty | +0.021 |
Dickinson | +0.021 |
allic | +0.021 |
Lund | +0.021 |
Neg logit contributions | |
sent | -0.018 |
kins | -0.018 |
.# | -0.018 |
\\ | -0.018 |
SEE | -0.018 |
Token | now |
Token ID | 783 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
sent | +0.267 |
kins | +0.263 |
.# | +0.262 |
\\ | +0.259 |
SEE | +0.258 |
Neg logit contributions | |
�� | -0.243 |
esty | -0.238 |
allic | -0.236 |
Dickinson | -0.235 |
Lund | -0.233 |
Token | available |
Token ID | 1695 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
sent | +0.246 |
kins | +0.242 |
.# | +0.241 |
\\ | +0.238 |
SEE | +0.237 |
Neg logit contributions | |
�� | -0.224 |
esty | -0.219 |
allic | -0.218 |
Dickinson | -0.217 |
Lund | -0.215 |
Token | through |
Token ID | 832 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
�� | +0.169 |
esty | +0.167 |
Dickinson | +0.166 |
allic | +0.166 |
Lund | +0.165 |
Neg logit contributions | |
sent | -0.137 |
kins | -0.134 |
.# | -0.133 |
SEE | -0.131 |
\\ | -0.131 |
Token | examination |
Token ID | 12452 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
�� | +0.089 |
esty | +0.088 |
Dickinson | +0.088 |
allic | +0.088 |
Lund | +0.087 |
Neg logit contributions | |
sent | -0.082 |
kins | -0.081 |
.# | -0.080 |
SEE | -0.079 |
\\ | -0.079 |
Token | ( |
Token ID | 357 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
sent | +0.020 |
kins | +0.019 |
.# | +0.019 |
SEE | +0.019 |
\\ | +0.019 |
Neg logit contributions | |
�� | -0.026 |
esty | -0.026 |
Dickinson | -0.026 |
allic | -0.025 |
Lund | -0.025 |
Token | including |
Token ID | 8201 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
sent | +0.051 |
kins | +0.050 |
.# | +0.050 |
SEE | +0.049 |
\\ | +0.049 |
Neg logit contributions | |
�� | -0.071 |
esty | -0.070 |
Dickinson | -0.070 |
allic | -0.070 |
Lund | -0.070 |
Token | at |
Token ID | 379 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
�� | +0.320 |
esty | +0.317 |
Dickinson | +0.315 |
allic | +0.314 |
Lund | +0.313 |
Neg logit contributions | |
sent | -0.278 |
kins | -0.273 |
.# | -0.271 |
SEE | -0.268 |
\\ | -0.267 |
Token | S |
Token ID | 311 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
�� | +0.141 |
esty | +0.139 |
allic | +0.138 |
Dickinson | +0.138 |
Lund | +0.137 |
Neg logit contributions | |
sent | -0.140 |
kins | -0.138 |
.# | -0.137 |
SEE | -0.135 |
\\ | -0.135 |
Token | DS |
Token ID | 5258 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
�� | +0.004 |
esty | +0.004 |
Dickinson | +0.004 |
allic | +0.004 |
Lund | +0.004 |
Neg logit contributions | |
sent | -0.003 |
kins | -0.003 |
.# | -0.003 |
SEE | -0.003 |
\\ | -0.003 |
Token | U |
Token ID | 52 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
�� | +0.577 |
esty | +0.573 |
Dickinson | +0.572 |
allic | +0.570 |
Lund | +0.569 |
Neg logit contributions | |
sent | -0.273 |
kins | -0.266 |
.# | -0.262 |
SEE | -0.257 |
\\ | -0.257 |
Token | ), |
Token ID | 828 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
�� | +0.686 |
esty | +0.684 |
Dickinson | +0.682 |
Lund | +0.679 |
allic | +0.676 |
Neg logit contributions | |
sent | -0.708 |
kins | -0.697 |
.# | -0.689 |
SEE | -0.683 |
\\ | -0.680 |
Token | line |
Token ID | 1627 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
�� | +0.120 |
esty | +0.117 |
Dickinson | +0.117 |
allic | +0.117 |
Lund | +0.116 |
Neg logit contributions | |
sent | -0.119 |
kins | -0.117 |
.# | -0.116 |
\\ | -0.115 |
SEE | -0.115 |
Token | arguments |
Token ID | 7159 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
�� | +1.157 |
esty | +1.150 |
Dickinson | +1.143 |
allic | +1.138 |
Lund | +1.136 |
Neg logit contributions | |
sent | -1.143 |
kins | -1.125 |
.# | -1.116 |
SEE | -1.104 |
\\ | -1.101 |
Token | are |
Token ID | 389 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
�� | +0.862 |
esty | +0.854 |
Dickinson | +0.850 |
allic | +0.847 |
Lund | +0.844 |
Neg logit contributions | |
sent | -0.747 |
kins | -0.735 |
.# | -0.729 |
\\ | -0.720 |
SEE | -0.718 |
Token | parsed |
Token ID | 44267 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
�� | +0.102 |
esty | +0.099 |
allic | +0.099 |
Dickinson | +0.098 |
abbit | +0.098 |
Neg logit contributions | |
sent | -0.105 |
kins | -0.103 |
.# | -0.103 |
\\ | -0.102 |
SEE | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
�� | +0.076 |
esty | +0.075 |
Dickinson | +0.075 |
allic | +0.075 |
Lund | +0.075 |
Neg logit contributions | |
sent | -0.065 |
kins | -0.064 |
.# | -0.063 |
\\ | -0.062 |
SEE | -0.062 |
Token | we |
Token ID | 356 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
�� | +0.239 |
esty | +0.237 |
Dickinson | +0.235 |
allic | +0.235 |
Lund | +0.234 |
Neg logit contributions | |
sent | -0.235 |
kins | -0.232 |
.# | -0.230 |
\\ | -0.227 |
SEE | -0.227 |
Token | can |
Token ID | 460 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
sent | +0.101 |
kins | +0.099 |
.# | +0.099 |
\\ | +0.098 |
SEE | +0.097 |
Neg logit contributions | |
�� | -0.106 |
esty | -0.105 |
Dickinson | -0.104 |
allic | -0.103 |
Lund | -0.103 |
Token | start |
Token ID | 923 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
�� | +0.044 |
esty | +0.043 |
Dickinson | +0.043 |
allic | +0.043 |
Lund | +0.043 |
Neg logit contributions | |
sent | -0.039 |
kins | -0.038 |
.# | -0.038 |
\\ | -0.038 |
SEE | -0.037 |
Token | loop |
Token ID | 9052 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
�� | +0.436 |
esty | +0.432 |
Dickinson | +0.430 |
allic | +0.429 |
Lund | +0.427 |
Neg logit contributions | |
sent | -0.403 |
kins | -0.396 |
.# | -0.393 |
SEE | -0.388 |
\\ | -0.388 |
Token | ing |
Token ID | 278 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
�� | +0.284 |
esty | +0.282 |
Dickinson | +0.281 |
allic | +0.280 |
Lund | +0.279 |
Neg logit contributions | |
sent | -0.161 |
kins | -0.158 |
.# | -0.156 |
SEE | -0.154 |
\\ | -0.153 |
Token | over |
Token ID | 625 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
sent | +0.357 |
kins | +0.352 |
.# | +0.352 |
\\ | +0.345 |
SEE | +0.344 |
Neg logit contributions | |
�� | -0.371 |
esty | -0.365 |
allic | -0.361 |
Dickinson | -0.359 |
Lund | -0.358 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
sent | +0.228 |
kins | +0.225 |
.# | +0.224 |
\\ | +0.221 |
SEE | +0.220 |
Neg logit contributions | |
�� | -0.218 |
esty | -0.213 |
Dickinson | -0.212 |
allic | -0.212 |
Lund | -0.210 |
Token | woman |
Token ID | 2415 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
sent | +0.129 |
kins | +0.127 |
.# | +0.126 |
\\ | +0.125 |
SEE | +0.124 |
Neg logit contributions | |
�� | -0.100 |
esty | -0.099 |
Dickinson | -0.098 |
allic | -0.097 |
Lund | -0.097 |
Token | � |
Token ID | 447 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
sent | +0.139 |
kins | +0.136 |
.# | +0.135 |
\\ | +0.133 |
SEE | +0.133 |
Neg logit contributions | |
�� | -0.165 |
esty | -0.163 |
Dickinson | -0.162 |
allic | -0.162 |
Lund | -0.161 |
Token | � |
Token ID | 247 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
�� | +0.041 |
esty | +0.041 |
Dickinson | +0.041 |
allic | +0.041 |
Lund | +0.041 |
Neg logit contributions | |
sent | -0.024 |
.# | -0.023 |
kins | -0.023 |
\\ | -0.023 |
SEE | -0.022 |
Token | s |
Token ID | 82 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
�� | +0.073 |
Dickinson | +0.071 |
esty | +0.070 |
allic | +0.070 |
Lund | +0.070 |
Neg logit contributions | |
sent | -0.082 |
kins | -0.080 |
.# | -0.079 |
\\ | -0.079 |
SEE | -0.078 |
Token | body |
Token ID | 1767 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
�� | +0.323 |
esty | +0.320 |
Dickinson | +0.319 |
allic | +0.317 |
Lund | +0.317 |
Neg logit contributions | |
sent | -0.296 |
kins | -0.291 |
.# | -0.289 |
SEE | -0.285 |
\\ | -0.285 |
Token | could |
Token ID | 714 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
sent | +0.460 |
kins | +0.453 |
.# | +0.449 |
\\ | +0.444 |
SEE | +0.442 |
Neg logit contributions | |
�� | -0.525 |
esty | -0.518 |
Dickinson | -0.516 |
allic | -0.513 |
Lund | -0.512 |
Token | not |
Token ID | 407 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
sent | +0.202 |
kins | +0.199 |
.# | +0.198 |
\\ | +0.195 |
SEE | +0.194 |
Neg logit contributions | |
�� | -0.208 |
esty | -0.206 |
Dickinson | -0.205 |
allic | -0.204 |
Lund | -0.204 |
Token | manage |
Token ID | 6687 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
�� | +0.142 |
esty | +0.141 |
Dickinson | +0.140 |
allic | +0.139 |
Lund | +0.139 |
Neg logit contributions | |
sent | -0.142 |
kins | -0.140 |
.# | -0.139 |
\\ | -0.137 |
SEE | -0.137 |
Token | two |
Token ID | 734 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
�� | +0.460 |
esty | +0.451 |
Dickinson | +0.449 |
allic | +0.446 |
Lund | +0.445 |
Neg logit contributions | |
sent | -0.402 |
kins | -0.395 |
.# | -0.393 |
\\ | -0.387 |
SEE | -0.387 |
Token | processes |
Token ID | 7767 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
�� | +0.194 |
esty | +0.190 |
Dickinson | +0.189 |
allic | +0.187 |
Lund | +0.187 |
Neg logit contributions | |
sent | -0.194 |
kins | -0.190 |
.# | -0.189 |
\\ | -0.187 |
SEE | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
sent | +0.023 |
kins | +0.022 |
.# | +0.022 |
SEE | +0.022 |
\\ | +0.022 |
Neg logit contributions | |
�� | -0.024 |
esty | -0.024 |
allic | -0.023 |
Dickinson | -0.023 |
abbit | -0.023 |
Token | housing |
Token ID | 5627 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
�� | +0.097 |
esty | +0.095 |
allic | +0.095 |
Dickinson | +0.094 |
abbit | +0.094 |
Neg logit contributions | |
sent | -0.093 |
kins | -0.091 |
.# | -0.090 |
SEE | -0.090 |
\\ | -0.090 |
Token | slump |
Token ID | 37758 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
�� | +0.235 |
esty | +0.232 |
Dickinson | +0.231 |
allic | +0.230 |
Lund | +0.229 |
Neg logit contributions | |
sent | -0.234 |
kins | -0.231 |
.# | -0.229 |
SEE | -0.226 |
\\ | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
�� | +0.218 |
esty | +0.216 |
Dickinson | +0.214 |
allic | +0.214 |
Lund | +0.213 |
Neg logit contributions | |
sent | -0.209 |
kins | -0.205 |
.# | -0.204 |
SEE | -0.201 |
\\ | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
�� | +0.142 |
esty | +0.140 |
allic | +0.139 |
Dickinson | +0.138 |
abbit | +0.138 |
Neg logit contributions | |
sent | -0.138 |
kins | -0.135 |
.# | -0.135 |
\\ | -0.133 |
SEE | -0.133 |
Token | associated |
Token ID | 3917 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
�� | +0.153 |
esty | +0.150 |
allic | +0.149 |
Dickinson | +0.148 |
abbit | +0.148 |
Neg logit contributions | |
sent | -0.151 |
kins | -0.148 |
.# | -0.148 |
\\ | -0.146 |
SEE | -0.146 |
Token | credit |
Token ID | 3884 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
sent | +0.907 |
.# | +0.888 |
kins | +0.881 |
\\ | +0.879 |
SEE | +0.871 |
Neg logit contributions | |
�� | -0.906 |
esty | -0.873 |
allic | -0.871 |
abbit | -0.862 |
Dickinson | -0.855 |
Token | crunch |
Token ID | 23527 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
�� | +0.340 |
esty | +0.330 |
allic | +0.328 |
Dickinson | +0.328 |
Lund | +0.326 |
Neg logit contributions | |
sent | -0.448 |
kins | -0.442 |
.# | -0.440 |
SEE | -0.435 |
\\ | -0.435 |
Token | accelerate |
Token ID | 22636 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
�� | +0.420 |
esty | +0.416 |
Dickinson | +0.414 |
allic | +0.412 |
Lund | +0.411 |
Neg logit contributions | |
sent | -0.396 |
kins | -0.389 |
.# | -0.386 |
SEE | -0.382 |
\\ | -0.381 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
�� | +0.132 |
esty | +0.131 |
Dickinson | +0.130 |
allic | +0.130 |
Lund | +0.129 |
Neg logit contributions | |
sent | -0.119 |
kins | -0.117 |
.# | -0.116 |
SEE | -0.115 |
\\ | -0.115 |
Token | spill |
Token ID | 19431 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
�� | +0.099 |
esty | +0.097 |
allic | +0.096 |
Dickinson | +0.096 |
abbit | +0.095 |
Neg logit contributions | |
sent | -0.094 |
kins | -0.092 |
.# | -0.092 |
SEE | -0.091 |
\\ | -0.091 |
Token | movie |
Token ID | 3807 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
sent | +0.138 |
kins | +0.136 |
.# | +0.135 |
SEE | +0.134 |
\\ | +0.133 |
Neg logit contributions | |
�� | -0.160 |
esty | -0.158 |
Dickinson | -0.157 |
allic | -0.157 |
Lund | -0.156 |
Token | and |
Token ID | 290 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
sent | +0.827 |
.# | +0.823 |
kins | +0.819 |
\\ | +0.800 |
SEE | +0.797 |
Neg logit contributions | |
�� | -0.764 |
esty | -0.744 |
Dickinson | -0.739 |
allic | -0.737 |
abbit | -0.733 |
Token | c |
Token ID | 269 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
sent | +0.133 |
kins | +0.131 |
.# | +0.130 |
\\ | +0.129 |
SEE | +0.128 |
Neg logit contributions | |
�� | -0.159 |
esty | -0.155 |
Dickinson | -0.154 |
allic | -0.154 |
Lund | -0.153 |
Token | uddle |
Token ID | 24500 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sent | +0.100 |
kins | +0.098 |
.# | +0.098 |
\\ | +0.097 |
SEE | +0.097 |
Neg logit contributions | |
�� | -0.065 |
Dickinson | -0.063 |
esty | -0.063 |
Lund | -0.063 |
allic | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
esty | +1.364 |
Dickinson | +1.362 |
allic | +1.354 |
Lund | +1.354 |
�� | +1.341 |
Neg logit contributions | |
sent | -1.173 |
kins | -1.145 |
SEE | -1.134 |
.# | -1.127 |
\\ | -1.120 |
Token | Sounds |
Token ID | 27107 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
�� | +0.170 |
esty | +0.169 |
Dickinson | +0.168 |
allic | +0.167 |
Lund | +0.167 |
Neg logit contributions | |
sent | -0.152 |
kins | -0.150 |
.# | -0.148 |
SEE | -0.147 |
\\ | -0.146 |
Token | good |
Token ID | 922 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
sent | +0.283 |
kins | +0.279 |
.# | +0.276 |
\\ | +0.273 |
SEE | +0.272 |
Neg logit contributions | |
�� | -0.333 |
esty | -0.327 |
Dickinson | -0.325 |
allic | -0.325 |
Lund | -0.323 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
sent | +0.034 |
kins | +0.034 |
.# | +0.033 |
SEE | +0.033 |
\\ | +0.033 |
Neg logit contributions | |
�� | -0.043 |
esty | -0.043 |
Dickinson | -0.043 |
allic | -0.043 |
Lund | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
�� | +0.434 |
esty | +0.434 |
Dickinson | +0.431 |
Lund | +0.430 |
allic | +0.428 |
Neg logit contributions | |
sent | -0.356 |
kins | -0.349 |
.# | -0.347 |
SEE | -0.343 |
\\ | -0.341 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
sent | +0.143 |
kins | +0.140 |
.# | +0.139 |
\\ | +0.138 |
SEE | +0.136 |
Neg logit contributions | |
�� | -0.196 |
esty | -0.190 |
Dickinson | -0.188 |
allic | -0.188 |
abbit | -0.187 |
Token | She |
Token ID | 3347 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
sent | +0.098 |
kins | +0.096 |
.# | +0.095 |
SEE | +0.092 |
\\ | +0.092 |
Neg logit contributions | |
esty | -0.197 |
�� | -0.197 |
Dickinson | -0.196 |
allic | -0.196 |
Lund | -0.196 |
Token | ahead |
Token ID | 4058 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
�� | +0.071 |
esty | +0.071 |
Dickinson | +0.070 |
allic | +0.070 |
Lund | +0.070 |
Neg logit contributions | |
sent | -0.059 |
kins | -0.058 |
.# | -0.058 |
SEE | -0.057 |
\\ | -0.057 |
Token | of |
Token ID | 286 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
�� | +0.104 |
esty | +0.104 |
Dickinson | +0.103 |
Lund | +0.103 |
allic | +0.102 |
Neg logit contributions | |
sent | -0.078 |
kins | -0.076 |
.# | -0.075 |
SEE | -0.075 |
\\ | -0.075 |
Token | data |
Token ID | 1366 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
sent | +0.223 |
kins | +0.220 |
.# | +0.218 |
SEE | +0.215 |
\\ | +0.215 |
Neg logit contributions | |
�� | -0.247 |
esty | -0.244 |
Dickinson | -0.243 |
allic | -0.242 |
Lund | -0.241 |
Token | , |
Token ID | 11 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
sent | +0.012 |
kins | +0.012 |
.# | +0.012 |
SEE | +0.012 |
\\ | +0.012 |
Neg logit contributions | |
�� | -0.014 |
esty | -0.014 |
Dickinson | -0.014 |
allic | -0.014 |
Lund | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
�� | +0.005 |
esty | +0.005 |
allic | +0.005 |
Dickinson | +0.005 |
Lund | +0.005 |
Neg logit contributions | |
sent | -0.004 |
kins | -0.004 |
.# | -0.004 |
SEE | -0.004 |
\\ | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
sent | +0.225 |
kins | +0.222 |
.# | +0.220 |
SEE | +0.217 |
\\ | +0.217 |
Neg logit contributions | |
�� | -0.246 |
esty | -0.243 |
Dickinson | -0.242 |
allic | -0.242 |
Lund | -0.240 |
Token | has |
Token ID | 468 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
sent | +0.281 |
kins | +0.277 |
.# | +0.275 |
\\ | +0.271 |
SEE | +0.268 |
Neg logit contributions | |
�� | -0.286 |
allic | -0.278 |
Dickinson | -0.277 |
esty | -0.277 |
Lund | -0.275 |
Token | begun |
Token ID | 9258 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
sent | +0.084 |
kins | +0.082 |
.# | +0.082 |
\\ | +0.081 |
SEE | +0.080 |
Neg logit contributions | |
�� | -0.080 |
allic | -0.078 |
esty | -0.078 |
Dickinson | -0.078 |
Lund | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
�� | +0.240 |
esty | +0.237 |
Dickinson | +0.236 |
allic | +0.236 |
Lund | +0.235 |
Neg logit contributions | |
sent | -0.222 |
kins | -0.219 |
.# | -0.217 |
SEE | -0.214 |
\\ | -0.214 |
Token | look |
Token ID | 804 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
�� | +0.242 |
esty | +0.238 |
Dickinson | +0.238 |
allic | +0.236 |
Lund | +0.235 |
Neg logit contributions | |
sent | -0.232 |
kins | -0.229 |
.# | -0.228 |
\\ | -0.224 |
SEE | -0.223 |
Token | like |
Token ID | 588 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
sent | +0.307 |
kins | +0.303 |
.# | +0.300 |
SEE | +0.297 |
\\ | +0.295 |
Neg logit contributions | |
�� | -0.343 |
esty | -0.335 |
allic | -0.334 |
Dickinson | -0.333 |
Lund | -0.331 |
Token | only |
Token ID | 691 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
�� | +0.194 |
esty | +0.193 |
Dickinson | +0.192 |
allic | +0.191 |
Lund | +0.191 |
Neg logit contributions | |
sent | -0.163 |
kins | -0.160 |
.# | -0.159 |
SEE | -0.157 |
\\ | -0.156 |
Token | motion |
Token ID | 6268 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
�� | +0.334 |
esty | +0.333 |
Dickinson | +0.333 |
Lund | +0.330 |
allic | +0.330 |
Neg logit contributions | |
sent | -0.259 |
kins | -0.255 |
.# | -0.251 |
SEE | -0.249 |
\\ | -0.247 |
Token | we |
Token ID | 356 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
sent | +0.514 |
kins | +0.504 |
.# | +0.500 |
\\ | +0.494 |
SEE | +0.494 |
Neg logit contributions | |
�� | -0.598 |
esty | -0.593 |
allic | -0.587 |
Dickinson | -0.587 |
Lund | -0.586 |
Token | have |
Token ID | 423 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
sent | +0.235 |
kins | +0.231 |
.# | +0.229 |
SEE | +0.226 |
\\ | +0.226 |
Neg logit contributions | |
�� | -0.310 |
esty | -0.307 |
Dickinson | -0.305 |
allic | -0.304 |
Lund | -0.304 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
�� | +0.080 |
esty | +0.079 |
Dickinson | +0.079 |
allic | +0.078 |
Lund | +0.078 |
Neg logit contributions | |
sent | -0.075 |
kins | -0.074 |
.# | -0.073 |
SEE | -0.072 |
\\ | -0.072 |
Token | space |
Token ID | 2272 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
sent | +0.007 |
kins | +0.006 |
.# | +0.006 |
SEE | +0.006 |
\\ | +0.006 |
Neg logit contributions | |
�� | -0.008 |
esty | -0.008 |
Dickinson | -0.008 |
allic | -0.008 |
Lund | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
sent | +1.235 |
.# | +1.208 |
kins | +1.207 |
SEE | +1.180 |
\\ | +1.177 |
Neg logit contributions | |
�� | -1.945 |
esty | -1.917 |
Dickinson | -1.901 |
allic | -1.900 |
Lund | -1.895 |
Token | Our |
Token ID | 3954 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
�� | +0.107 |
esty | +0.106 |
Dickinson | +0.106 |
allic | +0.105 |
Lund | +0.105 |
Neg logit contributions | |
sent | -0.082 |
kins | -0.081 |
.# | -0.080 |
SEE | -0.079 |
\\ | -0.079 |
Token | orbital |
Token ID | 32362 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
sent | +0.107 |
kins | +0.105 |
.# | +0.105 |
SEE | +0.103 |
\\ | +0.103 |
Neg logit contributions | |
�� | -0.122 |
esty | -0.121 |
Dickinson | -0.121 |
allic | -0.120 |
Lund | -0.120 |
Token | speed |
Token ID | 2866 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
sent | +0.870 |
kins | +0.852 |
.# | +0.845 |
\\ | +0.833 |
SEE | +0.833 |
Neg logit contributions | |
�� | -1.300 |
esty | -1.289 |
Dickinson | -1.278 |
allic | -1.278 |
Lund | -1.273 |
Token | around |
Token ID | 1088 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
sent | +0.541 |
kins | +0.532 |
.# | +0.528 |
SEE | +0.522 |
\\ | +0.522 |
Neg logit contributions | |
�� | -0.546 |
esty | -0.541 |
Dickinson | -0.538 |
allic | -0.537 |
Lund | -0.535 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
sent | +0.259 |
kins | +0.253 |
.# | +0.251 |
\\ | +0.249 |
SEE | +0.247 |
Neg logit contributions | |
�� | -0.350 |
esty | -0.344 |
Dickinson | -0.338 |
allic | -0.338 |
Lund | -0.336 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
sent | +0.174 |
kins | +0.170 |
.# | +0.170 |
\\ | +0.168 |
SEE | +0.166 |
Neg logit contributions | |
�� | -0.244 |
esty | -0.236 |
Dickinson | -0.233 |
allic | -0.233 |
abbit | -0.232 |
Token | Fight |
Token ID | 27365 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
sent | +0.160 |
kins | +0.156 |
.# | +0.155 |
SEE | +0.152 |
\\ | +0.151 |
Neg logit contributions | |
�� | -0.341 |
esty | -0.336 |
Dickinson | -0.335 |
Lund | -0.333 |
allic | -0.333 |
Token | Back |
Token ID | 5157 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
sent | +0.615 |
.# | +0.607 |
kins | +0.606 |
\\ | +0.592 |
SEE | +0.588 |
Neg logit contributions | |
�� | -0.998 |
esty | -0.973 |
allic | -0.963 |
Dickinson | -0.960 |
abbit | -0.949 |
Token | ! |
Token ID | 0 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
sent | +0.239 |
kins | +0.233 |
SEE | +0.230 |
.# | +0.229 |
\\ | +0.227 |
Neg logit contributions | |
Dickinson | -0.297 |
Lund | -0.297 |
esty | -0.296 |
�� | -0.293 |
abbit | -0.292 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
sent | +0.430 |
kins | +0.412 |
SEE | +0.410 |
.# | +0.406 |
Tab | +0.397 |
Neg logit contributions | |
Dickinson | -1.256 |
esty | -1.252 |
Lund | -1.251 |
allic | -1.238 |
abbit | -1.234 |
Token | up |
Token ID | 510 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
sent | +1.397 |
kins | +1.387 |
.# | +1.371 |
\\ | +1.362 |
Limit | +1.342 |
Neg logit contributions | |
�� | -2.028 |
esty | -1.944 |
Lund | -1.931 |
Dickinson | -1.927 |
allic | -1.926 |
Token | for |
Token ID | 329 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
sent | +0.319 |
kins | +0.315 |
.# | +0.312 |
\\ | +0.309 |
SEE | +0.305 |
Neg logit contributions | |
�� | -0.387 |
esty | -0.380 |
Dickinson | -0.377 |
allic | -0.376 |
Lund | -0.375 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sent | +0.320 |
kins | +0.313 |
SEE | +0.310 |
.# | +0.309 |
\\ | +0.308 |
Neg logit contributions | |
Dickinson | -0.400 |
esty | -0.398 |
�� | -0.398 |
allic | -0.397 |
Lund | -0.397 |
Token | Action |
Token ID | 7561 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
sent | +0.396 |
kins | +0.384 |
.# | +0.382 |
\\ | +0.372 |
SEE | +0.368 |
Neg logit contributions | |
�� | -1.038 |
esty | -1.023 |
Dickinson | -1.015 |
allic | -1.013 |
Lund | -1.011 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
sent | +0.318 |
kins | +0.311 |
.# | +0.308 |
\\ | +0.302 |
SEE | +0.301 |
Neg logit contributions | |
�� | -0.658 |
esty | -0.651 |
Dickinson | -0.648 |
allic | -0.647 |
Lund | -0.645 |
Token | practices |
Token ID | 6593 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
�� | +0.177 |
esty | +0.175 |
Dickinson | +0.174 |
allic | +0.173 |
Lund | +0.173 |
Neg logit contributions | |
sent | -0.164 |
kins | -0.161 |
.# | -0.160 |
SEE | -0.158 |
\\ | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
sent | +0.098 |
kins | +0.097 |
.# | +0.096 |
\\ | +0.095 |
SEE | +0.094 |
Neg logit contributions | |
�� | -0.130 |
esty | -0.129 |
Dickinson | -0.128 |
allic | -0.128 |
Lund | -0.127 |
Token | first |
Token ID | 717 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
sent | +0.061 |
kins | +0.060 |
.# | +0.060 |
SEE | +0.059 |
\\ | +0.059 |
Neg logit contributions | |
�� | -0.070 |
esty | -0.069 |
allic | -0.069 |
Dickinson | -0.068 |
abbit | -0.068 |
Token | access |
Token ID | 1895 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
�� | +0.207 |
esty | +0.206 |
Dickinson | +0.205 |
allic | +0.204 |
Lund | +0.204 |
Neg logit contributions | |
sent | -0.183 |
kins | -0.179 |
.# | -0.178 |
SEE | -0.176 |
\\ | -0.176 |
Token | to |
Token ID | 284 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
sent | +0.399 |
kins | +0.393 |
.# | +0.390 |
SEE | +0.385 |
\\ | +0.384 |
Neg logit contributions | |
�� | -0.444 |
esty | -0.440 |
Dickinson | -0.438 |
allic | -0.436 |
Lund | -0.435 |
Token | prospects |
Token ID | 13285 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
�� | +0.250 |
esty | +0.248 |
Dickinson | +0.246 |
allic | +0.246 |
Lund | +0.245 |
Neg logit contributions | |
sent | -0.229 |
kins | -0.225 |
.# | -0.223 |
SEE | -0.220 |
\\ | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
sent | +1.129 |
kins | +1.114 |
.# | +1.107 |
\\ | +1.084 |
SEE | +1.080 |
Neg logit contributions | |
�� | -1.542 |
esty | -1.514 |
allic | -1.510 |
Dickinson | -1.507 |
abbit | -1.494 |
Token | all |
Token ID | 477 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
�� | +0.202 |
esty | +0.201 |
Dickinson | +0.200 |
Lund | +0.199 |
allic | +0.199 |
Neg logit contributions | |
sent | -0.165 |
kins | -0.162 |
.# | -0.161 |
SEE | -0.159 |
\\ | -0.159 |
Token | being |
Token ID | 852 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
sent | +0.039 |
kins | +0.038 |
.# | +0.038 |
\\ | +0.037 |
SEE | +0.037 |
Neg logit contributions | |
�� | -0.048 |
esty | -0.047 |
Dickinson | -0.047 |
allic | -0.047 |
abbit | -0.047 |
Token | combined |
Token ID | 5929 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
sent | +0.181 |
kins | +0.178 |
.# | +0.176 |
\\ | +0.174 |
SEE | +0.173 |
Neg logit contributions | |
�� | -0.185 |
allic | -0.180 |
esty | -0.180 |
Dickinson | -0.179 |
abbit | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
sent | +0.011 |
kins | +0.011 |
.# | +0.011 |
SEE | +0.011 |
\\ | +0.011 |
Neg logit contributions | |
�� | -0.013 |
esty | -0.013 |
Dickinson | -0.013 |
allic | -0.013 |
Lund | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
�� | +0.126 |
esty | +0.124 |
Dickinson | +0.124 |
Lund | +0.123 |
allic | +0.123 |
Neg logit contributions | |
sent | -0.180 |
kins | -0.177 |
.# | -0.176 |
SEE | -0.175 |
\\ | -0.174 |
Token | 1903 |
Token ID | 41625 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
sent | +0.157 |
kins | +0.154 |
.# | +0.154 |
SEE | +0.152 |
\\ | +0.152 |
Neg logit contributions | |
�� | -0.088 |
esty | -0.086 |
Dickinson | -0.086 |
allic | -0.085 |
Lund | -0.085 |
Token | used |
Token ID | 973 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
sent | +0.142 |
kins | +0.140 |
.# | +0.139 |
SEE | +0.137 |
\\ | +0.137 |
Neg logit contributions | |
�� | -0.161 |
esty | -0.159 |
Dickinson | -0.158 |
allic | -0.158 |
Lund | -0.157 |
Token | tang |
Token ID | 13875 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
sent | +0.444 |
kins | +0.439 |
.# | +0.435 |
\\ | +0.429 |
SEE | +0.429 |
Neg logit contributions | |
�� | -0.446 |
esty | -0.442 |
Dickinson | -0.438 |
allic | -0.437 |
abbit | -0.434 |
Token | ent |
Token ID | 298 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
sent | +0.124 |
kins | +0.122 |
.# | +0.121 |
SEE | +0.119 |
\\ | +0.119 |
Neg logit contributions | |
�� | -0.135 |
esty | -0.134 |
Dickinson | -0.133 |
allic | -0.133 |
Lund | -0.133 |
Token | sight |
Token ID | 6504 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
sent | +0.277 |
kins | +0.275 |
.# | +0.272 |
SEE | +0.269 |
\\ | +0.268 |
Neg logit contributions | |
�� | -0.309 |
esty | -0.305 |
Dickinson | -0.303 |
allic | -0.301 |
abbit | -0.301 |
Token | located |
Token ID | 5140 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
kins | +1.151 |
sent | +1.141 |
.# | +1.131 |
SEE | +1.114 |
\\ | +1.110 |
Neg logit contributions | |
�� | -1.407 |
esty | -1.358 |
allic | -1.346 |
Dickinson | -1.344 |
abbit | -1.334 |
Token | on |
Token ID | 319 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
�� | +0.512 |
esty | +0.509 |
Dickinson | +0.506 |
allic | +0.504 |
Lund | +0.503 |
Neg logit contributions | |
sent | -0.475 |
kins | -0.467 |
.# | -0.463 |
SEE | -0.458 |
\\ | -0.457 |
Token | the |
Token ID | 262 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
sent | +0.003 |
kins | +0.003 |
.# | +0.002 |
SEE | +0.002 |
\\ | +0.002 |
Neg logit contributions | |
�� | -0.003 |
esty | -0.003 |
Dickinson | -0.003 |
allic | -0.003 |
Lund | -0.003 |
Token | barrel |
Token ID | 9036 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
�� | +0.031 |
esty | +0.030 |
allic | +0.030 |
Dickinson | +0.030 |
abbit | +0.030 |
Neg logit contributions | |
sent | -0.031 |
kins | -0.031 |
.# | -0.030 |
SEE | -0.030 |
\\ | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
sent | +0.186 |
kins | +0.184 |
.# | +0.183 |
\\ | +0.179 |
SEE | +0.179 |
Neg logit contributions | |
�� | -0.247 |
esty | -0.244 |
Dickinson | -0.242 |
allic | -0.242 |
Lund | -0.241 |
Token | $ |
Token ID | 720 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
sent | +0.071 |
kins | +0.070 |
.# | +0.069 |
SEE | +0.068 |
\\ | +0.067 |
Neg logit contributions | |
Dickinson | -0.115 |
esty | -0.114 |
�� | -0.114 |
Lund | -0.114 |
allic | -0.113 |
Token | b |
Token ID | 65 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
�� | +0.262 |
esty | +0.262 |
allic | +0.261 |
abbit | +0.259 |
Dickinson | +0.259 |
Neg logit contributions | |
sent | -0.200 |
kins | -0.198 |
.# | -0.195 |
SEE | -0.192 |
\\ | -0.192 |
Token | mp |
Token ID | 3149 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
sent | +0.194 |
kins | +0.191 |
.# | +0.189 |
\\ | +0.187 |
SEE | +0.186 |
Neg logit contributions | |
�� | -0.222 |
Dickinson | -0.218 |
esty | -0.217 |
Lund | -0.216 |
allic | -0.215 |
Token | | |
Token ID | 930 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
sent | +0.978 |
kins | +0.959 |
.# | +0.946 |
SEE | +0.938 |
\\ | +0.934 |
Neg logit contributions | |
�� | -1.387 |
esty | -1.381 |
Dickinson | -1.374 |
allic | -1.370 |
Lund | -1.367 |
Token | Select |
Token ID | 9683 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
sent | +0.385 |
kins | +0.380 |
.# | +0.375 |
SEE | +0.372 |
\\ | +0.369 |
Neg logit contributions | |
esty | -0.358 |
�� | -0.358 |
Dickinson | -0.357 |
Lund | -0.356 |
allic | -0.356 |
Token | Width |
Token ID | 38807 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
esty | +0.270 |
allic | +0.269 |
Lund | +0.268 |
Dickinson | +0.268 |
�� | +0.267 |
Neg logit contributions | |
sent | -0.248 |
kins | -0.242 |
.# | -0.239 |
SEE | -0.237 |
\\ | -0.234 |
Token | , |
Token ID | 11 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
sent | +1.446 |
kins | +1.422 |
.# | +1.411 |
SEE | +1.392 |
\\ | +1.391 |
Neg logit contributions | |
�� | -1.785 |
esty | -1.770 |
Dickinson | -1.762 |
allic | -1.756 |
Lund | -1.751 |
Token | Height |
Token ID | 23106 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
sent | +0.326 |
kins | +0.320 |
.# | +0.316 |
SEE | +0.311 |
\\ | +0.310 |
Neg logit contributions | |
�� | -0.558 |
esty | -0.555 |
Dickinson | -0.553 |
allic | -0.551 |
Lund | -0.551 |
Token | } |
Token ID | 1782 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
sent | +0.542 |
kins | +0.532 |
.# | +0.526 |
SEE | +0.521 |
\\ | +0.518 |
Neg logit contributions | |
�� | -0.634 |
esty | -0.632 |
Dickinson | -0.627 |
Lund | -0.626 |
allic | -0.626 |
Token | else |
Token ID | 2073 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
sent | +0.912 |
kins | +0.896 |
.# | +0.890 |
\\ | +0.877 |
SEE | +0.876 |
Neg logit contributions | |
�� | -1.181 |
esty | -1.168 |
Dickinson | -1.163 |
allic | -1.160 |
Lund | -1.155 |
Token | { |
Token ID | 1391 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
sent | +0.290 |
kins | +0.281 |
.# | +0.278 |
SEE | +0.275 |
\\ | +0.271 |
Neg logit contributions | |
esty | -0.643 |
�� | -0.640 |
Dickinson | -0.638 |
Lund | -0.635 |
allic | -0.635 |