Token |
|
Token ID | 198 |
Feature activation | +5.28e-04 |
Pos logit contributions | |
...] | +0.176 |
Virtue | +0.167 |
…] | +0.165 |
alog | +0.159 |
gee | +0.158 |
Neg logit contributions | |
ILCS | -0.179 |
aten | -0.176 |
dayName | -0.175 |
otle | -0.167 |
UGC | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
...] | +0.000 |
Virtue | +0.000 |
…] | +0.000 |
alog | +0.000 |
gee | +0.000 |
Neg logit contributions | |
ILCS | -0.000 |
aten | -0.000 |
dayName | -0.000 |
otle | -0.000 |
UGC | -0.000 |
Token | Bron |
Token ID | 18760 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
...] | +0.110 |
Virtue | +0.104 |
…] | +0.103 |
alog | +0.099 |
gee | +0.098 |
Neg logit contributions | |
ILCS | -0.127 |
aten | -0.125 |
dayName | -0.124 |
otle | -0.119 |
UGC | -0.113 |
Token | cos |
Token ID | 6966 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
...] | +0.388 |
Virtue | +0.359 |
…] | +0.352 |
alog | +0.331 |
gee | +0.327 |
Neg logit contributions | |
ILCS | -0.759 |
aten | -0.756 |
dayName | -0.746 |
otle | -0.725 |
UGC | -0.694 |
Token | coach |
Token ID | 3985 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
...] | +0.060 |
Virtue | +0.057 |
…] | +0.056 |
alog | +0.054 |
gee | +0.054 |
Neg logit contributions | |
ILCS | -0.058 |
aten | -0.058 |
dayName | -0.057 |
otle | -0.054 |
UGC | -0.052 |
Token | Vance |
Token ID | 40154 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ILCS | +0.538 |
aten | +0.531 |
dayName | +0.531 |
otle | +0.500 |
UGC | +0.477 |
Neg logit contributions | |
...] | -0.513 |
Virtue | -0.486 |
…] | -0.480 |
alog | -0.462 |
gee | -0.459 |
Token | Joseph |
Token ID | 7212 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
...] | +2.348 |
…] | +2.256 |
�� | +2.207 |
alog | +2.197 |
Virtue | +2.194 |
Neg logit contributions | |
ILCS | -1.706 |
aten | -1.682 |
dayName | -1.636 |
otle | -1.614 |
ENTS | -1.509 |
Token | said |
Token ID | 531 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
...] | +0.006 |
Virtue | +0.005 |
…] | +0.005 |
alog | +0.005 |
gee | +0.005 |
Neg logit contributions | |
ILCS | -0.007 |
aten | -0.007 |
dayName | -0.007 |
otle | -0.007 |
UGC | -0.006 |
Token | Monday |
Token ID | 3321 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
...] | +0.202 |
Virtue | +0.191 |
…] | +0.189 |
alog | +0.182 |
gee | +0.181 |
Neg logit contributions | |
ILCS | -0.220 |
aten | -0.217 |
dayName | -0.215 |
otle | -0.206 |
UGC | -0.196 |
Token | that |
Token ID | 326 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
...] | +0.057 |
Virtue | +0.054 |
…] | +0.054 |
alog | +0.052 |
gee | +0.051 |
Neg logit contributions | |
ILCS | -0.059 |
aten | -0.059 |
dayName | -0.058 |
otle | -0.055 |
UGC | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
...] | +0.295 |
Virtue | +0.278 |
…] | +0.276 |
alog | +0.265 |
gee | +0.263 |
Neg logit contributions | |
ILCS | -0.331 |
aten | -0.328 |
dayName | -0.324 |
otle | -0.311 |
UGC | -0.296 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
...] | +0.694 |
Virtue | +0.650 |
…] | +0.644 |
alog | +0.619 |
>] | +0.614 |
Neg logit contributions | |
ILCS | -0.921 |
aten | -0.908 |
dayName | -0.900 |
otle | -0.864 |
UGC | -0.836 |
Token | look |
Token ID | 804 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
...] | +1.262 |
Virtue | +1.190 |
…] | +1.180 |
>] | +1.135 |
gee | +1.131 |
Neg logit contributions | |
ILCS | -1.363 |
dayName | -1.354 |
aten | -1.351 |
otle | -1.309 |
UGC | -1.260 |
Token | at |
Token ID | 379 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
...] | +0.190 |
Virtue | +0.179 |
…] | +0.176 |
alog | +0.167 |
gee | +0.167 |
Neg logit contributions | |
ILCS | -0.271 |
aten | -0.269 |
dayName | -0.267 |
otle | -0.256 |
UGC | -0.245 |
Token | what |
Token ID | 644 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ILCS | +0.239 |
aten | +0.236 |
dayName | +0.235 |
otle | +0.226 |
UGC | +0.216 |
Neg logit contributions | |
...] | -0.167 |
Virtue | -0.156 |
…] | -0.155 |
alog | -0.146 |
gee | -0.146 |
Token | is |
Token ID | 318 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
...] | +0.270 |
Virtue | +0.256 |
…] | +0.254 |
alog | +0.244 |
gee | +0.243 |
Neg logit contributions | |
ILCS | -0.259 |
aten | -0.257 |
dayName | -0.254 |
otle | -0.243 |
UGC | -0.229 |
Token | happening |
Token ID | 5836 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
...] | +0.671 |
Virtue | +0.642 |
…] | +0.634 |
alog | +0.615 |
Fu | +0.612 |
Neg logit contributions | |
ILCS | -0.487 |
aten | -0.484 |
dayName | -0.475 |
otle | -0.453 |
UGC | -0.423 |
Token | in |
Token ID | 287 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
...] | +2.128 |
Virtue | +2.035 |
…] | +1.999 |
>] | +1.946 |
Lump | +1.942 |
Neg logit contributions | |
aten | -1.914 |
ILCS | -1.842 |
dayName | -1.837 |
otle | -1.782 |
ENTS | -1.683 |
Token | our |
Token ID | 674 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
...] | +1.189 |
Virtue | +1.125 |
…] | +1.115 |
Fu | +1.067 |
�� | +1.062 |
Neg logit contributions | |
ILCS | -1.245 |
aten | -1.244 |
dayName | -1.221 |
otle | -1.172 |
UGC | -1.101 |
Token | city |
Token ID | 1748 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
...] | +1.240 |
Virtue | +1.182 |
…] | +1.167 |
alog | +1.133 |
Fu | +1.125 |
Neg logit contributions | |
ILCS | -1.154 |
aten | -1.133 |
dayName | -1.106 |
otle | -1.064 |
ENTS | -1.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
...] | +0.151 |
Virtue | +0.144 |
…] | +0.142 |
alog | +0.137 |
gee | +0.136 |
Neg logit contributions | |
ILCS | -0.146 |
aten | -0.145 |
dayName | -0.143 |
otle | -0.137 |
UGC | -0.129 |
Token | state |
Token ID | 1181 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ILCS | +0.342 |
aten | +0.337 |
dayName | +0.336 |
otle | +0.320 |
UGC | +0.306 |
Neg logit contributions | |
...] | -0.303 |
Virtue | -0.287 |
…] | -0.284 |
gee | -0.271 |
alog | -0.271 |
Token | With |
Token ID | 3152 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
...] | +0.184 |
Virtue | +0.172 |
…] | +0.170 |
alog | +0.161 |
gee | +0.160 |
Neg logit contributions | |
ILCS | -0.271 |
aten | -0.269 |
dayName | -0.266 |
otle | -0.257 |
UGC | -0.246 |
Token | low |
Token ID | 1877 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
...] | +1.133 |
Virtue | +1.068 |
…] | +1.060 |
Fu | +1.021 |
>] | +1.013 |
Neg logit contributions | |
ILCS | -1.044 |
aten | -1.038 |
dayName | -1.034 |
otle | -0.993 |
UGC | -0.935 |
Token | birth |
Token ID | 4082 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
...] | +0.271 |
Virtue | +0.254 |
…] | +0.251 |
alog | +0.240 |
Fu | +0.238 |
Neg logit contributions | |
ILCS | -0.346 |
aten | -0.343 |
dayName | -0.339 |
otle | -0.326 |
UGC | -0.311 |
Token | rate |
Token ID | 2494 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ILCS | +0.039 |
aten | +0.038 |
dayName | +0.038 |
otle | +0.037 |
UGC | +0.035 |
Neg logit contributions | |
...] | -0.027 |
Virtue | -0.025 |
…] | -0.025 |
alog | -0.023 |
gee | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ILCS | +0.200 |
aten | +0.198 |
dayName | +0.196 |
otle | +0.187 |
UGC | +0.178 |
Neg logit contributions | |
...] | -0.195 |
Virtue | -0.185 |
…] | -0.183 |
alog | -0.175 |
gee | -0.175 |
Token | America |
Token ID | 2253 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
...] | +0.696 |
Virtue | +0.656 |
…] | +0.648 |
Fu | +0.622 |
alog | +0.621 |
Neg logit contributions | |
ILCS | -0.740 |
aten | -0.732 |
dayName | -0.724 |
otle | -0.700 |
UGC | -0.657 |
Token | needs |
Token ID | 2476 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
...] | +2.070 |
Virtue | +1.949 |
…] | +1.947 |
>] | +1.872 |
�� | +1.863 |
Neg logit contributions | |
ILCS | -1.776 |
aten | -1.717 |
dayName | -1.710 |
otle | -1.651 |
ENTS | -1.554 |
Token | future |
Token ID | 2003 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
...] | +0.812 |
Virtue | +0.770 |
…] | +0.757 |
alog | +0.726 |
Lump | +0.725 |
Neg logit contributions | |
ILCS | -0.896 |
aten | -0.880 |
dayName | -0.867 |
otle | -0.842 |
UGC | -0.799 |
Token | migrants |
Token ID | 12783 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
...] | +0.730 |
Virtue | +0.687 |
…] | +0.679 |
alog | +0.656 |
gee | +0.652 |
Neg logit contributions | |
ILCS | -0.798 |
dayName | -0.777 |
aten | -0.776 |
otle | -0.744 |
UGC | -0.710 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
...] | +0.399 |
Virtue | +0.378 |
…] | +0.373 |
alog | +0.359 |
gee | +0.357 |
Neg logit contributions | |
ILCS | -0.426 |
aten | -0.420 |
dayName | -0.415 |
otle | -0.399 |
UGC | -0.378 |
Token | ways |
Token ID | 2842 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
...] | +0.879 |
…] | +0.835 |
Virtue | +0.835 |
alog | +0.808 |
>] | +0.790 |
Neg logit contributions | |
ILCS | -0.738 |
aten | -0.729 |
dayName | -0.725 |
otle | -0.694 |
UGC | -0.654 |
Token | and |
Token ID | 290 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
...] | +0.173 |
Virtue | +0.164 |
…] | +0.162 |
alog | +0.155 |
gee | +0.155 |
Neg logit contributions | |
ILCS | -0.177 |
aten | -0.175 |
dayName | -0.173 |
otle | -0.166 |
UGC | -0.157 |
Token | conducted |
Token ID | 5952 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
...] | +0.069 |
Virtue | +0.065 |
…] | +0.065 |
alog | +0.062 |
gee | +0.062 |
Neg logit contributions | |
ILCS | -0.067 |
aten | -0.067 |
dayName | -0.066 |
otle | -0.063 |
UGC | -0.060 |
Token | by |
Token ID | 416 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ILCS | +0.330 |
aten | +0.325 |
dayName | +0.323 |
otle | +0.309 |
UGC | +0.295 |
Neg logit contributions | |
...] | -0.293 |
Virtue | -0.277 |
…] | -0.273 |
alog | -0.261 |
gee | -0.261 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
...] | +0.219 |
Virtue | +0.207 |
…] | +0.205 |
alog | +0.196 |
gee | +0.196 |
Neg logit contributions | |
ILCS | -0.234 |
aten | -0.231 |
dayName | -0.229 |
otle | -0.219 |
UGC | -0.208 |
Token | bipartisan |
Token ID | 20953 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
...] | +0.154 |
Virtue | +0.146 |
…] | +0.144 |
alog | +0.138 |
gee | +0.138 |
Neg logit contributions | |
ILCS | -0.162 |
aten | -0.160 |
dayName | -0.158 |
otle | -0.151 |
UGC | -0.144 |
Token | Purple |
Token ID | 17265 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
...] | +0.420 |
Virtue | +0.396 |
…] | +0.394 |
alog | +0.377 |
gee | +0.376 |
Neg logit contributions | |
ILCS | -0.430 |
aten | -0.426 |
dayName | -0.421 |
otle | -0.403 |
UGC | -0.382 |
Token | Ins |
Token ID | 7088 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
...] | +1.732 |
…] | +1.607 |
Virtue | +1.592 |
gee | +1.524 |
alog | +1.524 |
Neg logit contributions | |
ILCS | -1.829 |
aten | -1.811 |
dayName | -1.778 |
otle | -1.705 |
UGC | -1.613 |
Token | ights |
Token ID | 2337 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
...] | +0.815 |
Virtue | +0.769 |
…] | +0.762 |
gee | +0.730 |
Fu | +0.724 |
Neg logit contributions | |
ILCS | -0.871 |
aten | -0.868 |
dayName | -0.850 |
otle | -0.817 |
UGC | -0.773 |
Token | group |
Token ID | 1448 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
...] | +0.310 |
Virtue | +0.292 |
…] | +0.290 |
alog | +0.277 |
gee | +0.277 |
Neg logit contributions | |
ILCS | -0.340 |
aten | -0.336 |
dayName | -0.333 |
otle | -0.319 |
UGC | -0.303 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
...] | +0.335 |
Virtue | +0.317 |
…] | +0.314 |
alog | +0.301 |
gee | +0.301 |
Neg logit contributions | |
ILCS | -0.336 |
aten | -0.332 |
dayName | -0.329 |
otle | -0.314 |
UGC | -0.298 |
Token | found |
Token ID | 1043 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
...] | +0.133 |
Virtue | +0.126 |
…] | +0.125 |
alog | +0.120 |
gee | +0.120 |
Neg logit contributions | |
ILCS | -0.138 |
aten | -0.137 |
dayName | -0.135 |
otle | -0.129 |
UGC | -0.123 |
Token | deep |
Token ID | 2769 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
ILCS | +0.112 |
aten | +0.111 |
dayName | +0.110 |
otle | +0.105 |
UGC | +0.100 |
Neg logit contributions | |
...] | -0.101 |
Virtue | -0.095 |
…] | -0.094 |
alog | -0.090 |
gee | -0.090 |
Token | balls |
Token ID | 11333 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
...] | +0.262 |
Virtue | +0.247 |
…] | +0.245 |
alog | +0.234 |
gee | +0.234 |
Neg logit contributions | |
ILCS | -0.302 |
aten | -0.299 |
dayName | -0.296 |
otle | -0.284 |
UGC | -0.270 |
Token | to |
Token ID | 284 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
...] | +0.147 |
Virtue | +0.139 |
…] | +0.138 |
alog | +0.132 |
gee | +0.131 |
Neg logit contributions | |
ILCS | -0.155 |
aten | -0.153 |
dayName | -0.152 |
otle | -0.145 |
UGC | -0.138 |
Token | Stef |
Token ID | 22350 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ILCS | +0.045 |
aten | +0.044 |
dayName | +0.044 |
otle | +0.042 |
UGC | +0.040 |
Neg logit contributions | |
...] | -0.039 |
Virtue | -0.037 |
…] | -0.037 |
alog | -0.035 |
gee | -0.035 |
Token | on |
Token ID | 261 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
...] | +0.077 |
Virtue | +0.073 |
…] | +0.073 |
alog | +0.070 |
gee | +0.070 |
Neg logit contributions | |
ILCS | -0.066 |
aten | -0.065 |
dayName | -0.065 |
otle | -0.061 |
UGC | -0.058 |
Token | D |
Token ID | 360 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
...] | +1.463 |
…] | +1.360 |
Virtue | +1.357 |
alog | +1.325 |
gee | +1.316 |
Neg logit contributions | |
ILCS | -1.460 |
aten | -1.448 |
dayName | -1.415 |
otle | -1.354 |
ENTS | -1.280 |
Token | iggs |
Token ID | 20340 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
...] | +2.353 |
Virtue | +2.261 |
…] | +2.257 |
>] | +2.185 |
�� | +2.162 |
Neg logit contributions | |
aten | -1.197 |
ILCS | -1.167 |
dayName | -1.115 |
otle | -1.083 |
ENTS | -0.992 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
...] | +0.117 |
Virtue | +0.111 |
…] | +0.110 |
alog | +0.106 |
gee | +0.105 |
Neg logit contributions | |
ILCS | -0.120 |
aten | -0.118 |
dayName | -0.117 |
otle | -0.112 |
UGC | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
ILCS | +0.089 |
aten | +0.088 |
dayName | +0.087 |
otle | +0.083 |
UGC | +0.079 |
Neg logit contributions | |
...] | -0.079 |
Virtue | -0.075 |
…] | -0.074 |
alog | -0.071 |
gee | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ILCS | +0.042 |
aten | +0.041 |
dayName | +0.041 |
otle | +0.039 |
UGC | +0.037 |
Neg logit contributions | |
...] | -0.041 |
Virtue | -0.039 |
…] | -0.038 |
alog | -0.037 |
gee | -0.037 |
Token | R |
Token ID | 49 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ILCS | +0.098 |
aten | +0.096 |
dayName | +0.095 |
otle | +0.091 |
UGC | +0.087 |
Neg logit contributions | |
...] | -0.091 |
Virtue | -0.086 |
…] | -0.086 |
alog | -0.082 |
gee | -0.082 |
Token | Though |
Token ID | 7486 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
...] | +0.019 |
Virtue | +0.018 |
…] | +0.018 |
alog | +0.017 |
gee | +0.017 |
Neg logit contributions | |
ILCS | -0.021 |
aten | -0.020 |
dayName | -0.020 |
otle | -0.019 |
UGC | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
...] | +0.168 |
Virtue | +0.159 |
…] | +0.157 |
alog | +0.151 |
gee | +0.150 |
Neg logit contributions | |
ILCS | -0.189 |
aten | -0.187 |
dayName | -0.185 |
otle | -0.177 |
UGC | -0.168 |
Token | quarterback |
Token ID | 7880 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
...] | +0.162 |
Virtue | +0.154 |
…] | +0.152 |
alog | +0.146 |
gee | +0.146 |
Neg logit contributions | |
ILCS | -0.157 |
aten | -0.155 |
dayName | -0.154 |
otle | -0.147 |
UGC | -0.139 |
Token | competition |
Token ID | 5449 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
...] | +0.019 |
Virtue | +0.018 |
…] | +0.018 |
alog | +0.017 |
gee | +0.017 |
Neg logit contributions | |
ILCS | -0.023 |
aten | -0.022 |
dayName | -0.022 |
otle | -0.021 |
UGC | -0.020 |
Token | between |
Token ID | 1022 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ILCS | +0.065 |
aten | +0.064 |
dayName | +0.064 |
otle | +0.061 |
UGC | +0.058 |
Neg logit contributions | |
...] | -0.056 |
Virtue | -0.053 |
…] | -0.053 |
alog | -0.050 |
gee | -0.050 |
Token | Trevor |
Token ID | 25389 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
...] | +0.273 |
Virtue | +0.258 |
…] | +0.256 |
alog | +0.245 |
gee | +0.244 |
Neg logit contributions | |
ILCS | -0.295 |
aten | -0.292 |
dayName | -0.289 |
otle | -0.276 |
UGC | -0.263 |
Token | Siem |
Token ID | 45196 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
...] | +0.821 |
…] | +0.711 |
Virtue | +0.711 |
alog | +0.667 |
Fu | +0.638 |
Neg logit contributions | |
ILCS | -2.596 |
aten | -2.594 |
dayName | -2.530 |
otle | -2.515 |
UGC | -2.405 |
Token | ian |
Token ID | 666 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ILCS | +0.026 |
aten | +0.025 |
dayName | +0.025 |
otle | +0.023 |
UGC | +0.021 |
Neg logit contributions | |
...] | -0.059 |
Virtue | -0.057 |
…] | -0.056 |
alog | -0.055 |
gee | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ILCS | +0.014 |
aten | +0.014 |
dayName | +0.013 |
otle | +0.013 |
UGC | +0.012 |
Neg logit contributions | |
...] | -0.014 |
Virtue | -0.013 |
…] | -0.013 |
alog | -0.012 |
gee | -0.012 |
Token | Pa |
Token ID | 11243 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
...] | +0.234 |
Virtue | +0.222 |
…] | +0.220 |
alog | +0.211 |
gee | +0.211 |
Neg logit contributions | |
ILCS | -0.233 |
aten | -0.231 |
dayName | -0.228 |
otle | -0.218 |
UGC | -0.207 |
Token | xton |
Token ID | 22874 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
...] | +0.979 |
Virtue | +0.937 |
…] | +0.931 |
alog | +0.899 |
gee | +0.899 |
Neg logit contributions | |
ILCS | -0.605 |
aten | -0.602 |
dayName | -0.582 |
otle | -0.561 |
UGC | -0.518 |
Token | Fight |
Token ID | 27365 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
...] | +0.613 |
Virtue | +0.586 |
…] | +0.577 |
alog | +0.557 |
gee | +0.555 |
Neg logit contributions | |
ILCS | -0.576 |
aten | -0.567 |
dayName | -0.565 |
otle | -0.538 |
UGC | -0.507 |
Token | Back |
Token ID | 5157 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ILCS | +0.447 |
aten | +0.442 |
dayName | +0.438 |
otle | +0.424 |
UGC | +0.404 |
Neg logit contributions | |
...] | -0.320 |
Virtue | -0.298 |
…] | -0.296 |
alog | -0.280 |
gee | -0.278 |
Token | ! |
Token ID | 0 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ILCS | +0.532 |
aten | +0.526 |
dayName | +0.520 |
otle | +0.501 |
UGC | +0.476 |
Neg logit contributions | |
...] | -0.438 |
Virtue | -0.408 |
…] | -0.406 |
alog | -0.384 |
Fu | -0.384 |
Token | Sign |
Token ID | 5865 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
...] | +0.466 |
Virtue | +0.420 |
…] | +0.416 |
alog | +0.391 |
Fu | +0.387 |
Neg logit contributions | |
ILCS | -1.027 |
dayName | -1.014 |
aten | -1.013 |
otle | -0.978 |
UGC | -0.937 |
Token | up |
Token ID | 510 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
...] | +0.476 |
Virtue | +0.444 |
…] | +0.439 |
alog | +0.417 |
gee | +0.414 |
Neg logit contributions | |
ILCS | -0.747 |
aten | -0.742 |
dayName | -0.736 |
otle | -0.710 |
UGC | -0.678 |
Token | for |
Token ID | 329 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
...] | +0.636 |
Virtue | +0.603 |
…] | +0.597 |
alog | +0.574 |
gee | +0.572 |
Neg logit contributions | |
ILCS | -0.658 |
aten | -0.652 |
dayName | -0.649 |
otle | -0.619 |
UGC | -0.585 |
Token | Take |
Token ID | 7214 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
...] | +1.427 |
Virtue | +1.348 |
…] | +1.336 |
alog | +1.293 |
>] | +1.259 |
Neg logit contributions | |
dayName | -1.801 |
ILCS | -1.795 |
aten | -1.794 |
otle | -1.703 |
ENTS | -1.621 |
Token | Action |
Token ID | 7561 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
...] | +0.397 |
Virtue | +0.375 |
…] | +0.371 |
alog | +0.356 |
gee | +0.356 |
Neg logit contributions | |
ILCS | -0.434 |
aten | -0.429 |
dayName | -0.426 |
otle | -0.408 |
UGC | -0.388 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ILCS | +0.285 |
aten | +0.283 |
dayName | +0.280 |
otle | +0.270 |
UGC | +0.258 |
Neg logit contributions | |
...] | -0.192 |
Virtue | -0.180 |
…] | -0.177 |
alog | -0.168 |
gee | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
...] | +0.264 |
Virtue | +0.250 |
…] | +0.248 |
alog | +0.239 |
gee | +0.237 |
Neg logit contributions | |
ILCS | -0.253 |
aten | -0.250 |
dayName | -0.248 |
otle | -0.236 |
UGC | -0.224 |
Token | we |
Token ID | 356 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
...] | +0.400 |
Virtue | +0.381 |
…] | +0.377 |
alog | +0.364 |
gee | +0.362 |
Neg logit contributions | |
ILCS | -0.362 |
aten | -0.358 |
dayName | -0.354 |
otle | -0.338 |
UGC | -0.319 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ILCS | +0.048 |
aten | +0.047 |
dayName | +0.047 |
otle | +0.045 |
UGC | +0.043 |
Neg logit contributions | |
...] | -0.039 |
Virtue | -0.037 |
…] | -0.036 |
alog | -0.035 |
gee | -0.035 |
Token | airline |
Token ID | 18091 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
...] | +0.787 |
Virtue | +0.741 |
…] | +0.734 |
alog | +0.711 |
Fu | +0.702 |
Neg logit contributions | |
ILCS | -0.819 |
aten | -0.807 |
dayName | -0.806 |
otle | -0.769 |
UGC | -0.730 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
...] | +0.265 |
Virtue | +0.251 |
…] | +0.249 |
alog | +0.239 |
gee | +0.238 |
Neg logit contributions | |
ILCS | -0.256 |
aten | -0.253 |
dayName | -0.251 |
otle | -0.239 |
UGC | -0.226 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
...] | +0.674 |
Virtue | +0.624 |
…] | +0.621 |
gee | +0.592 |
Fu | +0.591 |
Neg logit contributions | |
ILCS | -0.902 |
aten | -0.900 |
dayName | -0.892 |
otle | -0.857 |
UGC | -0.818 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
...] | +1.551 |
Virtue | +1.509 |
…] | +1.463 |
gee | +1.450 |
alog | +1.430 |
Neg logit contributions | |
ILCS | -1.480 |
aten | -1.470 |
dayName | -1.465 |
otle | -1.410 |
UGC | -1.338 |
Token | open |
Token ID | 1280 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
...] | +1.022 |
Virtue | +0.970 |
…] | +0.958 |
Fu | +0.924 |
alog | +0.917 |
Neg logit contributions | |
aten | -0.975 |
ILCS | -0.968 |
dayName | -0.965 |
otle | -0.931 |
UGC | -0.881 |
Token | flights |
Token ID | 13956 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
...] | +1.499 |
…] | +1.402 |
Virtue | +1.397 |
�� | +1.349 |
alog | +1.341 |
Neg logit contributions | |
aten | -1.712 |
dayName | -1.686 |
ILCS | -1.685 |
otle | -1.663 |
UGC | -1.552 |
Token | to |
Token ID | 284 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
...] | +0.483 |
Virtue | +0.458 |
…] | +0.453 |
alog | +0.437 |
gee | +0.436 |
Neg logit contributions | |
ILCS | -0.508 |
aten | -0.505 |
dayName | -0.504 |
otle | -0.479 |
UGC | -0.453 |
Token | US |
Token ID | 1294 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
...] | +0.164 |
Virtue | +0.155 |
…] | +0.153 |
alog | +0.146 |
gee | +0.145 |
Neg logit contributions | |
ILCS | -0.206 |
aten | -0.204 |
dayName | -0.202 |
otle | -0.194 |
UGC | -0.185 |
Token | on |
Token ID | 319 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
...] | +0.704 |
Virtue | +0.660 |
…] | +0.658 |
alog | +0.632 |
gee | +0.626 |
Neg logit contributions | |
ILCS | -0.719 |
dayName | -0.715 |
aten | -0.711 |
otle | -0.676 |
UGC | -0.640 |
Token | sidelines |
Token ID | 29394 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
...] | +0.448 |
Virtue | +0.423 |
…] | +0.420 |
alog | +0.402 |
gee | +0.401 |
Neg logit contributions | |
ILCS | -0.477 |
aten | -0.473 |
dayName | -0.468 |
otle | -0.447 |
UGC | -0.425 |
Token | : |
Token ID | 25 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
...] | +0.261 |
Virtue | +0.246 |
…] | +0.244 |
alog | +0.234 |
gee | +0.233 |
Neg logit contributions | |
ILCS | -0.286 |
aten | -0.283 |
dayName | -0.280 |
otle | -0.268 |
UGC | -0.254 |
Token | report |
Token ID | 989 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
...] | +0.301 |
Virtue | +0.283 |
…] | +0.281 |
alog | +0.270 |
gee | +0.268 |
Neg logit contributions | |
ILCS | -0.330 |
aten | -0.326 |
dayName | -0.324 |
otle | -0.310 |
UGC | -0.295 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ILCS | +0.156 |
aten | +0.154 |
dayName | +0.153 |
otle | +0.147 |
UGC | +0.141 |
Neg logit contributions | |
...] | -0.111 |
Virtue | -0.104 |
…] | -0.103 |
alog | -0.098 |
gee | -0.097 |
Token | airline |
Token ID | 18091 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
...] | +0.900 |
Virtue | +0.844 |
…] | +0.837 |
alog | +0.813 |
Fu | +0.801 |
Neg logit contributions | |
ILCS | -0.997 |
dayName | -0.980 |
aten | -0.979 |
otle | -0.937 |
UGC | -0.891 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
...] | +0.392 |
Virtue | +0.371 |
…] | +0.368 |
alog | +0.354 |
gee | +0.352 |
Neg logit contributions | |
ILCS | -0.380 |
aten | -0.378 |
dayName | -0.374 |
otle | -0.357 |
UGC | -0.338 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
...] | +0.763 |
Virtue | +0.705 |
…] | +0.703 |
gee | +0.670 |
Fu | +0.669 |
Neg logit contributions | |
ILCS | -1.014 |
aten | -1.012 |
dayName | -1.004 |
otle | -0.965 |
UGC | -0.921 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
...] | +1.628 |
Virtue | +1.587 |
…] | +1.538 |
gee | +1.523 |
�� | +1.507 |
Neg logit contributions | |
ILCS | -1.534 |
aten | -1.524 |
dayName | -1.522 |
otle | -1.466 |
UGC | -1.390 |
Token | open |
Token ID | 1280 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
...] | +1.002 |
Virtue | +0.950 |
…] | +0.936 |
Fu | +0.905 |
alog | +0.897 |
Neg logit contributions | |
aten | -1.067 |
ILCS | -1.064 |
dayName | -1.056 |
otle | -1.022 |
UGC | -0.972 |
Token | flights |
Token ID | 13956 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
...] | +1.397 |
…] | +1.309 |
Virtue | +1.308 |
�� | +1.254 |
alog | +1.253 |
Neg logit contributions | |
aten | -1.528 |
ILCS | -1.504 |
dayName | -1.500 |
otle | -1.480 |
UGC | -1.382 |
Token | to |
Token ID | 284 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
...] | +0.379 |
Virtue | +0.360 |
…] | +0.355 |
alog | +0.342 |
gee | +0.341 |
Neg logit contributions | |
ILCS | -0.401 |
aten | -0.397 |
dayName | -0.396 |
otle | -0.377 |
UGC | -0.357 |
Token | US |
Token ID | 1294 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
...] | +0.214 |
Virtue | +0.201 |
…] | +0.199 |
alog | +0.190 |
gee | +0.189 |
Neg logit contributions | |
ILCS | -0.266 |
aten | -0.264 |
dayName | -0.261 |
otle | -0.251 |
UGC | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e-05 |
Pos logit contributions | |
...] | +0.154 |
Virtue | +0.146 |
…] | +0.145 |
alog | +0.139 |
gee | +0.138 |
Neg logit contributions | |
ILCS | -0.156 |
aten | -0.155 |
dayName | -0.153 |
otle | -0.146 |
UGC | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ILCS | +0.000 |
aten | +0.000 |
dayName | +0.000 |
otle | +0.000 |
UGC | +0.000 |
Neg logit contributions | |
...] | -0.000 |
Virtue | -0.000 |
…] | -0.000 |
alog | -0.000 |
gee | -0.000 |
Token | Follow |
Token ID | 7155 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
...] | +0.105 |
Virtue | +0.099 |
…] | +0.098 |
alog | +0.094 |
gee | +0.093 |
Neg logit contributions | |
ILCS | -0.129 |
aten | -0.128 |
dayName | -0.127 |
otle | -0.122 |
UGC | -0.116 |
Token | Dan |
Token ID | 6035 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
...] | +0.169 |
Virtue | +0.161 |
…] | +0.160 |
alog | +0.154 |
gee | +0.153 |
Neg logit contributions | |
ILCS | -0.145 |
aten | -0.143 |
dayName | -0.141 |
otle | -0.135 |
UGC | -0.127 |
Token | Han |
Token ID | 9530 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
...] | +0.438 |
Virtue | +0.415 |
…] | +0.413 |
alog | +0.397 |
gee | +0.396 |
Neg logit contributions | |
ILCS | -0.361 |
aten | -0.357 |
dayName | -0.352 |
otle | -0.336 |
UGC | -0.315 |
Token | z |
Token ID | 89 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
...] | +0.810 |
Virtue | +0.765 |
…] | +0.754 |
gee | +0.718 |
Lump | +0.717 |
Neg logit contributions | |
aten | -0.943 |
ILCS | -0.941 |
dayName | -0.922 |
otle | -0.891 |
UGC | -0.845 |
Token | us |
Token ID | 385 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
...] | +1.794 |
Virtue | +1.690 |
…] | +1.683 |
>] | +1.606 |
gee | +1.603 |
Neg logit contributions | |
aten | -1.451 |
ILCS | -1.423 |
dayName | -1.363 |
otle | -1.342 |
uther | -1.236 |
Token | on |
Token ID | 319 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
...] | +0.275 |
Virtue | +0.260 |
…] | +0.257 |
alog | +0.246 |
gee | +0.246 |
Neg logit contributions | |
ILCS | -0.284 |
aten | -0.281 |
dayName | -0.279 |
otle | -0.266 |
UGC | -0.253 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ILCS | +0.173 |
aten | +0.170 |
dayName | +0.168 |
otle | +0.160 |
UGC | +0.151 |
Neg logit contributions | |
...] | -0.211 |
Virtue | -0.201 |
…] | -0.199 |
alog | -0.192 |
gee | -0.191 |
Token | @ |
Token ID | 2488 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ILCS | +0.226 |
aten | +0.223 |
dayName | +0.221 |
otle | +0.210 |
UGC | +0.198 |
Neg logit contributions | |
...] | -0.272 |
Virtue | -0.259 |
…] | -0.257 |
alog | -0.247 |
gee | -0.247 |
Token | dan |
Token ID | 25604 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
ILCS | +0.265 |
aten | +0.262 |
dayName | +0.260 |
otle | +0.249 |
UGC | +0.237 |
Neg logit contributions | |
...] | -0.228 |
Virtue | -0.215 |
…] | -0.213 |
alog | -0.204 |
gee | -0.203 |
Token | brings |
Token ID | 6774 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ILCS | +0.087 |
aten | +0.086 |
dayName | +0.086 |
otle | +0.082 |
UGC | +0.078 |
Neg logit contributions | |
...] | -0.076 |
Virtue | -0.072 |
…] | -0.071 |
alog | -0.068 |
gee | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
...] | +0.304 |
Virtue | +0.288 |
…] | +0.284 |
alog | +0.273 |
gee | +0.272 |
Neg logit contributions | |
ILCS | -0.343 |
aten | -0.340 |
dayName | -0.336 |
otle | -0.322 |
UGC | -0.307 |
Token | great |
Token ID | 1049 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
...] | +1.114 |
Virtue | +1.049 |
…] | +1.046 |
>] | +1.008 |
alog | +0.999 |
Neg logit contributions | |
ILCS | -1.208 |
aten | -1.198 |
dayName | -1.180 |
otle | -1.132 |
UGC | -1.085 |
Token | games |
Token ID | 1830 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
...] | +0.576 |
Virtue | +0.545 |
…] | +0.541 |
alog | +0.519 |
gee | +0.515 |
Neg logit contributions | |
ILCS | -0.561 |
aten | -0.556 |
dayName | -0.552 |
otle | -0.524 |
UGC | -0.499 |
Token | created |
Token ID | 2727 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
ILCS | +0.217 |
aten | +0.215 |
dayName | +0.212 |
otle | +0.204 |
UGC | +0.193 |
Neg logit contributions | |
...] | -0.198 |
Virtue | -0.187 |
…] | -0.185 |
alog | -0.177 |
gee | -0.177 |
Token | for |
Token ID | 329 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
...] | +0.066 |
Virtue | +0.062 |
…] | +0.062 |
alog | +0.059 |
gee | +0.059 |
Neg logit contributions | |
ILCS | -0.072 |
aten | -0.071 |
dayName | -0.070 |
otle | -0.067 |
UGC | -0.064 |
Token | consoles |
Token ID | 22629 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
...] | +1.563 |
Virtue | +1.484 |
…] | +1.471 |
gee | +1.421 |
alog | +1.404 |
Neg logit contributions | |
aten | -1.636 |
ILCS | -1.632 |
dayName | -1.608 |
otle | -1.515 |
UGC | -1.456 |
Token | such |
Token ID | 884 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ILCS | +0.468 |
aten | +0.462 |
dayName | +0.459 |
otle | +0.444 |
UGC | +0.425 |
Neg logit contributions | |
...] | -0.268 |
Virtue | -0.251 |
…] | -0.246 |
alog | -0.234 |
gee | -0.233 |
Token | as |
Token ID | 355 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
...] | +0.079 |
Virtue | +0.075 |
…] | +0.074 |
alog | +0.071 |
gee | +0.071 |
Neg logit contributions | |
ILCS | -0.079 |
aten | -0.078 |
dayName | -0.077 |
otle | -0.074 |
UGC | -0.070 |
Token | NES |
Token ID | 31925 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
...] | +0.416 |
Virtue | +0.386 |
…] | +0.383 |
alog | +0.364 |
gee | +0.362 |
Neg logit contributions | |
ILCS | -0.640 |
aten | -0.636 |
dayName | -0.628 |
otle | -0.607 |
UGC | -0.583 |
Token | ™ |
Token ID | 8151 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
...] | +0.758 |
Virtue | +0.714 |
…] | +0.711 |
alog | +0.684 |
>] | +0.679 |
Neg logit contributions | |
ILCS | -0.690 |
aten | -0.687 |
dayName | -0.684 |
otle | -0.648 |
UGC | -0.618 |
Token | umble |
Token ID | 10344 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
ILCS | +0.065 |
aten | +0.064 |
dayName | +0.063 |
otle | +0.060 |
UGC | +0.056 |
Neg logit contributions | |
...] | -0.096 |
Virtue | -0.092 |
…] | -0.091 |
alog | -0.088 |
gee | -0.088 |
Token | Upon |
Token ID | 23792 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ILCS | +0.448 |
aten | +0.440 |
dayName | +0.440 |
otle | +0.415 |
UGC | +0.392 |
Neg logit contributions | |
...] | -0.551 |
Virtue | -0.521 |
…] | -0.518 |
Fu | -0.500 |
gee | -0.499 |
Token | What |
Token ID | 1867 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ILCS | +0.304 |
aten | +0.300 |
dayName | +0.298 |
otle | +0.284 |
UGC | +0.270 |
Neg logit contributions | |
...] | -0.267 |
Virtue | -0.252 |
…] | -0.249 |
alog | -0.239 |
gee | -0.239 |
Token | are |
Token ID | 389 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ILCS | +0.401 |
aten | +0.395 |
dayName | +0.393 |
otle | +0.372 |
UGC | +0.354 |
Neg logit contributions | |
...] | -0.453 |
Virtue | -0.430 |
…] | -0.425 |
alog | -0.407 |
Fu | -0.407 |
Token | these |
Token ID | 777 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ILCS | +0.167 |
aten | +0.166 |
dayName | +0.165 |
otle | +0.157 |
UGC | +0.150 |
Neg logit contributions | |
...] | -0.140 |
Virtue | -0.132 |
…] | -0.130 |
alog | -0.125 |
gee | -0.124 |
Token | ? |
Token ID | 30 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
...] | +0.587 |
Virtue | +0.561 |
…] | +0.554 |
alog | +0.536 |
Fu | +0.533 |
Neg logit contributions | |
ILCS | -0.506 |
aten | -0.497 |
dayName | -0.493 |
otle | -0.472 |
UGC | -0.442 |
Token | E |
Token ID | 412 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
...] | +1.532 |
…] | +1.460 |
Virtue | +1.446 |
Fu | +1.382 |
gee | +1.373 |
Neg logit contributions | |
ILCS | -1.666 |
dayName | -1.628 |
aten | -1.582 |
otle | -1.553 |
UGC | -1.484 |
Token | - |
Token ID | 12 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ILCS | +1.226 |
dayName | +1.204 |
aten | +1.202 |
otle | +1.155 |
ENTS | +1.086 |
Neg logit contributions | |
...] | -1.106 |
Virtue | -1.033 |
…] | -1.032 |
alog | -0.998 |
Fu | -0.995 |
Token | mail |
Token ID | 4529 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ILCS | +0.179 |
aten | +0.177 |
dayName | +0.175 |
otle | +0.166 |
UGC | +0.155 |
Neg logit contributions | |
...] | -0.235 |
Virtue | -0.223 |
…] | -0.222 |
Fu | -0.214 |
alog | -0.214 |
Token | this |
Token ID | 428 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
...] | +0.455 |
Virtue | +0.429 |
…] | +0.428 |
alog | +0.409 |
Fu | +0.408 |
Neg logit contributions | |
ILCS | -0.444 |
aten | -0.439 |
dayName | -0.435 |
otle | -0.416 |
UGC | -0.393 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
...] | +0.012 |
Virtue | +0.011 |
…] | +0.011 |
alog | +0.011 |
gee | +0.011 |
Neg logit contributions | |
ILCS | -0.013 |
aten | -0.013 |
dayName | -0.013 |
otle | -0.012 |
UGC | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
...] | +0.109 |
Virtue | +0.103 |
…] | +0.102 |
alog | +0.098 |
gee | +0.097 |
Neg logit contributions | |
ILCS | -0.112 |
aten | -0.111 |
dayName | -0.110 |
otle | -0.105 |
UGC | -0.099 |
Token | t |
Token ID | 256 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
...] | +0.210 |
Virtue | +0.198 |
…] | +0.196 |
alog | +0.188 |
gee | +0.188 |
Neg logit contributions | |
ILCS | -0.218 |
aten | -0.216 |
dayName | -0.213 |
otle | -0.204 |
UGC | -0.194 |
Token | rolled |
Token ID | 8375 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
...] | +1.044 |
Virtue | +1.002 |
…] | +0.996 |
alog | +0.958 |
gee | +0.957 |
Neg logit contributions | |
aten | -0.597 |
ILCS | -0.592 |
dayName | -0.574 |
otle | -0.551 |
UGC | -0.502 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
...] | +0.132 |
Virtue | +0.125 |
…] | +0.124 |
alog | +0.119 |
gee | +0.119 |
Neg logit contributions | |
ILCS | -0.131 |
aten | -0.130 |
dayName | -0.128 |
otle | -0.123 |
UGC | -0.116 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
...] | +0.312 |
Virtue | +0.295 |
…] | +0.292 |
alog | +0.280 |
gee | +0.279 |
Neg logit contributions | |
ILCS | -0.318 |
aten | -0.315 |
dayName | -0.311 |
otle | -0.298 |
UGC | -0.282 |
Token | p |
Token ID | 79 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
...] | +0.846 |
Virtue | +0.801 |
…] | +0.790 |
alog | +0.752 |
>] | +0.752 |
Neg logit contributions | |
ILCS | -0.836 |
aten | -0.827 |
dayName | -0.812 |
otle | -0.785 |
UGC | -0.739 |
Token | iled |
Token ID | 3902 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
...] | +1.085 |
Virtue | +1.039 |
…] | +0.985 |
�� | +0.943 |
Lump | +0.931 |
Neg logit contributions | |
aten | -2.090 |
ILCS | -2.075 |
dayName | -2.020 |
otle | -2.002 |
utor | -1.912 |
Token | on |
Token ID | 319 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ILCS | +0.015 |
aten | +0.015 |
dayName | +0.015 |
otle | +0.014 |
UGC | +0.013 |
Neg logit contributions | |
...] | -0.015 |
Virtue | -0.014 |
…] | -0.014 |
alog | -0.013 |
gee | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
...] | +0.218 |
Virtue | +0.206 |
…] | +0.204 |
alog | +0.196 |
gee | +0.196 |
Neg logit contributions | |
ILCS | -0.206 |
aten | -0.204 |
dayName | -0.201 |
otle | -0.192 |
UGC | -0.182 |
Token | dumped |
Token ID | 24105 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
...] | +0.271 |
Virtue | +0.257 |
…] | +0.254 |
alog | +0.244 |
gee | +0.243 |
Neg logit contributions | |
ILCS | -0.277 |
aten | -0.274 |
dayName | -0.270 |
otle | -0.259 |
UGC | -0.245 |
Token | on |
Token ID | 319 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
...] | +0.185 |
Virtue | +0.175 |
…] | +0.173 |
alog | +0.166 |
gee | +0.166 |
Neg logit contributions | |
ILCS | -0.188 |
aten | -0.186 |
dayName | -0.183 |
otle | -0.176 |
UGC | -0.166 |
Token | Night |
Token ID | 5265 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
...] | +0.023 |
Virtue | +0.022 |
…] | +0.021 |
alog | +0.021 |
gee | +0.020 |
Neg logit contributions | |
ILCS | -0.024 |
aten | -0.024 |
dayName | -0.024 |
otle | -0.023 |
UGC | -0.021 |
Token | c |
Token ID | 66 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
...] | +0.373 |
Virtue | +0.354 |
…] | +0.352 |
alog | +0.338 |
gee | +0.337 |
Neg logit contributions | |
ILCS | -0.321 |
aten | -0.317 |
dayName | -0.313 |
otle | -0.299 |
UGC | -0.281 |
Token | rawler |
Token ID | 39464 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ILCS | +0.329 |
aten | +0.325 |
dayName | +0.324 |
otle | +0.311 |
UGC | +0.299 |
Neg logit contributions | |
...] | -0.192 |
Virtue | -0.179 |
…] | -0.176 |
alog | -0.167 |
gee | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
ILCS | +0.023 |
aten | +0.023 |
dayName | +0.023 |
otle | +0.022 |
UGC | +0.021 |
Neg logit contributions | |
...] | -0.023 |
Virtue | -0.022 |
…] | -0.022 |
alog | -0.021 |
gee | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ILCS | +0.056 |
aten | +0.055 |
dayName | +0.055 |
otle | +0.052 |
UGC | +0.050 |
Neg logit contributions | |
...] | -0.053 |
Virtue | -0.051 |
…] | -0.050 |
alog | -0.048 |
gee | -0.048 |
Token | Jub |
Token ID | 38075 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
...] | +0.078 |
Virtue | +0.074 |
…] | +0.073 |
alog | +0.070 |
gee | +0.070 |
Neg logit contributions | |
ILCS | -0.085 |
aten | -0.084 |
dayName | -0.083 |
otle | -0.080 |
UGC | -0.076 |
Token | ilee |
Token ID | 40626 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
...] | +1.758 |
Virtue | +1.687 |
…] | +1.670 |
Fu | +1.616 |
�� | +1.613 |
Neg logit contributions | |
aten | -1.389 |
ILCS | -1.356 |
dayName | -1.327 |
otle | -1.290 |
utor | -1.211 |
Token | hanging |
Token ID | 10938 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
ILCS | +0.026 |
aten | +0.025 |
dayName | +0.025 |
otle | +0.024 |
UGC | +0.023 |
Neg logit contributions | |
...] | -0.024 |
Virtue | -0.023 |
…] | -0.022 |
alog | -0.022 |
gee | -0.021 |
Token | out |
Token ID | 503 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
...] | +0.017 |
Virtue | +0.016 |
…] | +0.016 |
alog | +0.015 |
gee | +0.015 |
Neg logit contributions | |
ILCS | -0.015 |
aten | -0.015 |
dayName | -0.015 |
otle | -0.014 |
UGC | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
...] | +0.125 |
Virtue | +0.118 |
…] | +0.117 |
alog | +0.112 |
gee | +0.111 |
Neg logit contributions | |
ILCS | -0.142 |
aten | -0.141 |
dayName | -0.139 |
otle | -0.134 |
UGC | -0.127 |
Token | a |
Token ID | 257 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
...] | +0.353 |
Virtue | +0.334 |
…] | +0.330 |
alog | +0.317 |
gee | +0.316 |
Neg logit contributions | |
ILCS | -0.376 |
aten | -0.371 |
dayName | -0.367 |
otle | -0.352 |
UGC | -0.334 |
Token | : |
Token ID | 25 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
...] | +0.522 |
Virtue | +0.488 |
…] | +0.486 |
alog | +0.463 |
gee | +0.461 |
Neg logit contributions | |
ILCS | -0.634 |
aten | -0.628 |
dayName | -0.623 |
otle | -0.596 |
UGC | -0.567 |
Token | report |
Token ID | 989 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
...] | +0.575 |
Virtue | +0.539 |
…] | +0.535 |
alog | +0.516 |
gee | +0.512 |
Neg logit contributions | |
ILCS | -0.615 |
aten | -0.606 |
dayName | -0.602 |
otle | -0.575 |
UGC | -0.547 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ILCS | +0.083 |
aten | +0.082 |
dayName | +0.081 |
otle | +0.078 |
UGC | +0.074 |
Neg logit contributions | |
...] | -0.074 |
Virtue | -0.070 |
…] | -0.069 |
alog | -0.066 |
gee | -0.066 |
Token | airline |
Token ID | 18091 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
...] | +1.064 |
Virtue | +1.000 |
…] | +0.990 |
alog | +0.967 |
Fu | +0.951 |
Neg logit contributions | |
ILCS | -1.113 |
dayName | -1.095 |
aten | -1.090 |
otle | -1.043 |
UGC | -0.990 |
Token | takes |
Token ID | 2753 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
...] | +0.305 |
Virtue | +0.289 |
…] | +0.286 |
alog | +0.275 |
gee | +0.274 |
Neg logit contributions | |
ILCS | -0.312 |
aten | -0.310 |
dayName | -0.306 |
otle | -0.293 |
UGC | -0.277 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
...] | +0.511 |
Virtue | +0.475 |
…] | +0.472 |
gee | +0.449 |
Fu | +0.448 |
Neg logit contributions | |
ILCS | -0.694 |
aten | -0.690 |
dayName | -0.685 |
otle | -0.659 |
UGC | -0.629 |
Token | to |
Token ID | 284 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
...] | +1.558 |
Virtue | +1.518 |
…] | +1.472 |
gee | +1.461 |
�� | +1.443 |
Neg logit contributions | |
ILCS | -1.486 |
aten | -1.476 |
dayName | -1.471 |
otle | -1.417 |
UGC | -1.343 |
Token | open |
Token ID | 1280 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
...] | +0.780 |
Virtue | +0.735 |
…] | +0.724 |
Fu | +0.695 |
alog | +0.689 |
Neg logit contributions | |
aten | -1.008 |
ILCS | -1.005 |
dayName | -0.998 |
otle | -0.967 |
UGC | -0.925 |
Token | flights |
Token ID | 13956 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
...] | +1.323 |
Virtue | +1.242 |
…] | +1.241 |
alog | +1.190 |
�� | +1.188 |
Neg logit contributions | |
aten | -1.391 |
ILCS | -1.369 |
dayName | -1.369 |
otle | -1.343 |
UGC | -1.254 |
Token | to |
Token ID | 284 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
...] | +0.478 |
Virtue | +0.454 |
…] | +0.447 |
alog | +0.432 |
gee | +0.431 |
Neg logit contributions | |
ILCS | -0.502 |
aten | -0.499 |
dayName | -0.498 |
otle | -0.474 |
UGC | -0.447 |
Token | US |
Token ID | 1294 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
...] | +0.291 |
Virtue | +0.273 |
…] | +0.270 |
alog | +0.257 |
gee | +0.256 |
Neg logit contributions | |
ILCS | -0.404 |
aten | -0.400 |
dayName | -0.397 |
otle | -0.382 |
UGC | -0.366 |
Token | : |
Token ID | 25 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
...] | +0.210 |
Virtue | +0.198 |
…] | +0.197 |
alog | +0.188 |
gee | +0.188 |
Neg logit contributions | |
ILCS | -0.228 |
aten | -0.225 |
dayName | -0.223 |
otle | -0.213 |
UGC | -0.203 |
Token | report |
Token ID | 989 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
ILCS | +0.072 |
aten | +0.071 |
dayName | +0.071 |
otle | +0.068 |
UGC | +0.064 |
Neg logit contributions | |
...] | -0.064 |
Virtue | -0.061 |
…] | -0.060 |
alog | -0.057 |
gee | -0.057 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ILCS | +0.048 |
aten | +0.047 |
dayName | +0.047 |
otle | +0.045 |
UGC | +0.043 |
Neg logit contributions | |
...] | -0.039 |
Virtue | -0.037 |
…] | -0.036 |
alog | -0.035 |
gee | -0.035 |
Token | airline |
Token ID | 18091 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
...] | +0.787 |
Virtue | +0.741 |
…] | +0.734 |
alog | +0.711 |
Fu | +0.702 |
Neg logit contributions | |
ILCS | -0.819 |
aten | -0.807 |
dayName | -0.806 |
otle | -0.769 |
UGC | -0.730 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
...] | +0.265 |
Virtue | +0.251 |
…] | +0.249 |
alog | +0.239 |
gee | +0.238 |
Neg logit contributions | |
ILCS | -0.256 |
aten | -0.253 |
dayName | -0.251 |
otle | -0.239 |
UGC | -0.226 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
...] | +0.674 |
Virtue | +0.624 |
…] | +0.621 |
gee | +0.592 |
Fu | +0.591 |
Neg logit contributions | |
ILCS | -0.902 |
aten | -0.900 |
dayName | -0.892 |
otle | -0.857 |
UGC | -0.818 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
...] | +1.551 |
Virtue | +1.509 |
…] | +1.463 |
gee | +1.450 |
alog | +1.430 |
Neg logit contributions | |
ILCS | -1.480 |
aten | -1.470 |
dayName | -1.465 |
otle | -1.410 |
UGC | -1.338 |
Token | open |
Token ID | 1280 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
...] | +1.022 |
Virtue | +0.970 |
…] | +0.958 |
Fu | +0.924 |
alog | +0.917 |
Neg logit contributions | |
aten | -0.975 |
ILCS | -0.968 |
dayName | -0.965 |
otle | -0.931 |
UGC | -0.881 |
Token | flights |
Token ID | 13956 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
...] | +1.499 |
…] | +1.402 |
Virtue | +1.397 |
�� | +1.349 |
alog | +1.341 |
Neg logit contributions | |
aten | -1.712 |
dayName | -1.686 |
ILCS | -1.685 |
otle | -1.663 |
UGC | -1.552 |
Token | to |
Token ID | 284 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
...] | +0.483 |
Virtue | +0.458 |
…] | +0.453 |
alog | +0.437 |
gee | +0.436 |
Neg logit contributions | |
ILCS | -0.508 |
aten | -0.505 |
dayName | -0.504 |
otle | -0.479 |
UGC | -0.453 |
Token | US |
Token ID | 1294 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
...] | +0.164 |
Virtue | +0.155 |
…] | +0.153 |
alog | +0.146 |
gee | +0.145 |
Neg logit contributions | |
ILCS | -0.206 |
aten | -0.204 |
dayName | -0.202 |
otle | -0.194 |
UGC | -0.185 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
...] | +0.118 |
Virtue | +0.111 |
…] | +0.110 |
alog | +0.106 |
gee | +0.105 |
Neg logit contributions | |
ILCS | -0.124 |
aten | -0.123 |
dayName | -0.122 |
otle | -0.116 |
UGC | -0.111 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
...] | +0.087 |
Virtue | +0.083 |
…] | +0.082 |
alog | +0.078 |
gee | +0.078 |
Neg logit contributions | |
ILCS | -0.093 |
aten | -0.092 |
dayName | -0.091 |
otle | -0.087 |
UGC | -0.083 |
Token | in |
Token ID | 287 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
...] | +0.209 |
Virtue | +0.197 |
…] | +0.196 |
alog | +0.188 |
gee | +0.187 |
Neg logit contributions | |
ILCS | -0.218 |
aten | -0.215 |
dayName | -0.213 |
otle | -0.204 |
UGC | -0.194 |
Token | Gone |
Token ID | 26893 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
...] | +0.093 |
Virtue | +0.088 |
…] | +0.088 |
alog | +0.084 |
gee | +0.084 |
Neg logit contributions | |
ILCS | -0.099 |
aten | -0.097 |
dayName | -0.096 |
otle | -0.092 |
UGC | -0.088 |
Token | With |
Token ID | 2080 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
...] | +0.059 |
Virtue | +0.056 |
…] | +0.055 |
alog | +0.053 |
gee | +0.053 |
Neg logit contributions | |
ILCS | -0.063 |
aten | -0.062 |
dayName | -0.062 |
otle | -0.059 |
UGC | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ILCS | +0.088 |
aten | +0.087 |
dayName | +0.086 |
otle | +0.082 |
UGC | +0.078 |
Neg logit contributions | |
...] | -0.080 |
Virtue | -0.075 |
…] | -0.074 |
alog | -0.071 |
gee | -0.071 |
Token | Wind |
Token ID | 8731 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
...] | +1.103 |
Virtue | +0.997 |
…] | +0.997 |
alog | +0.955 |
gee | +0.951 |
Neg logit contributions | |
ILCS | -1.983 |
aten | -1.948 |
dayName | -1.925 |
otle | -1.880 |
ENTS | -1.799 |
Token | ( |
Token ID | 357 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
...] | +0.337 |
Virtue | +0.318 |
…] | +0.315 |
alog | +0.302 |
gee | +0.301 |
Neg logit contributions | |
ILCS | -0.369 |
aten | -0.365 |
dayName | -0.361 |
otle | -0.346 |
UGC | -0.329 |
Token | 19 |
Token ID | 1129 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ILCS | +0.257 |
aten | +0.253 |
dayName | +0.251 |
otle | +0.238 |
UGC | +0.224 |
Neg logit contributions | |
...] | -0.313 |
Virtue | -0.298 |
…] | -0.296 |
alog | -0.284 |
gee | -0.284 |
Token | 39 |
Token ID | 2670 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
...] | +0.180 |
Virtue | +0.171 |
…] | +0.169 |
alog | +0.162 |
gee | +0.162 |
Neg logit contributions | |
ILCS | -0.168 |
aten | -0.166 |
dayName | -0.165 |
otle | -0.157 |
UGC | -0.149 |
Token | ). |
Token ID | 737 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ILCS | +0.039 |
aten | +0.039 |
dayName | +0.038 |
otle | +0.037 |
UGC | +0.035 |
Neg logit contributions | |
...] | -0.031 |
Virtue | -0.029 |
…] | -0.029 |
alog | -0.027 |
gee | -0.027 |
Token | bomber |
Token ID | 24065 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
...] | +0.511 |
Virtue | +0.472 |
…] | +0.468 |
alog | +0.443 |
gee | +0.437 |
Neg logit contributions | |
ILCS | -0.842 |
aten | -0.836 |
dayName | -0.825 |
otle | -0.800 |
UGC | -0.768 |
Token | jacket |
Token ID | 15224 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
...] | +0.790 |
Virtue | +0.743 |
…] | +0.742 |
alog | +0.715 |
gee | +0.710 |
Neg logit contributions | |
ILCS | -0.747 |
aten | -0.737 |
dayName | -0.726 |
otle | -0.698 |
UGC | -0.659 |
Token | with |
Token ID | 351 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
...] | +0.203 |
Virtue | +0.194 |
…] | +0.193 |
alog | +0.186 |
gee | +0.186 |
Neg logit contributions | |
ILCS | -0.134 |
aten | -0.132 |
dayName | -0.130 |
otle | -0.123 |
UGC | -0.115 |
Token | ' |
Token ID | 705 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
...] | +0.085 |
Virtue | +0.079 |
…] | +0.078 |
alog | +0.074 |
gee | +0.074 |
Neg logit contributions | |
ILCS | -0.142 |
aten | -0.141 |
dayName | -0.139 |
otle | -0.135 |
UGC | -0.129 |
Token | 44 |
Token ID | 2598 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
...] | +0.895 |
Virtue | +0.852 |
…] | +0.837 |
alog | +0.801 |
Lump | +0.797 |
Neg logit contributions | |
ILCS | -0.940 |
aten | -0.930 |
dayName | -0.913 |
otle | -0.882 |
UGC | -0.842 |
Token | ' |
Token ID | 6 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
...] | +1.056 |
…] | +0.986 |
Virtue | +0.974 |
alog | +0.934 |
gee | +0.932 |
Neg logit contributions | |
ILCS | -1.323 |
aten | -1.301 |
dayName | -1.282 |
otle | -1.241 |
UGC | -1.183 |
Token | on |
Token ID | 319 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
...] | +1.495 |
…] | +1.394 |
Virtue | +1.385 |
alog | +1.332 |
Fu | +1.331 |
Neg logit contributions | |
ILCS | -1.556 |
aten | -1.538 |
dayName | -1.513 |
otle | -1.471 |
UGC | -1.390 |
Token | sleeve |
Token ID | 23179 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
...] | +0.805 |
Virtue | +0.759 |
…] | +0.754 |
alog | +0.723 |
Fu | +0.719 |
Neg logit contributions | |
ILCS | -0.752 |
aten | -0.745 |
dayName | -0.733 |
otle | -0.705 |
UGC | -0.661 |
Token | at |
Token ID | 379 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ILCS | +0.704 |
aten | +0.700 |
dayName | +0.696 |
otle | +0.663 |
UGC | +0.632 |
Neg logit contributions | |
...] | -0.617 |
Virtue | -0.588 |
…] | -0.578 |
gee | -0.555 |
alog | -0.551 |
Token | basketball |
Token ID | 9669 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
...] | +0.075 |
Virtue | +0.070 |
…] | +0.070 |
alog | +0.067 |
gee | +0.066 |
Neg logit contributions | |
ILCS | -0.086 |
aten | -0.085 |
dayName | -0.084 |
otle | -0.080 |
UGC | -0.076 |
Token | game |
Token ID | 983 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
...] | +0.128 |
Virtue | +0.121 |
…] | +0.120 |
alog | +0.115 |
gee | +0.114 |
Neg logit contributions | |
ILCS | -0.134 |
aten | -0.132 |
dayName | -0.131 |
otle | -0.125 |
UGC | -0.119 |
Token | k |
Token ID | 74 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ILCS | +0.117 |
aten | +0.115 |
dayName | +0.114 |
otle | +0.109 |
UGC | +0.103 |
Neg logit contributions | |
...] | -0.126 |
Virtue | -0.119 |
…] | -0.118 |
alog | -0.114 |
gee | -0.113 |
Token | ings |
Token ID | 654 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ILCS | +0.117 |
aten | +0.114 |
dayName | +0.113 |
otle | +0.105 |
UGC | +0.097 |
Neg logit contributions | |
...] | -0.240 |
Virtue | -0.230 |
…] | -0.229 |
alog | -0.222 |
gee | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
...] | +0.236 |
Virtue | +0.223 |
…] | +0.221 |
alog | +0.212 |
gee | +0.211 |
Neg logit contributions | |
ILCS | -0.242 |
aten | -0.240 |
dayName | -0.237 |
otle | -0.227 |
UGC | -0.215 |
Token | Watts |
Token ID | 27555 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
...] | +0.233 |
Virtue | +0.220 |
…] | +0.218 |
alog | +0.209 |
gee | +0.208 |
Neg logit contributions | |
ILCS | -0.243 |
aten | -0.240 |
dayName | -0.238 |
otle | -0.228 |
UGC | -0.216 |
Token | Up |
Token ID | 4933 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
...] | +0.002 |
Virtue | +0.002 |
…] | +0.002 |
alog | +0.002 |
gee | +0.002 |
Neg logit contributions | |
ILCS | -0.002 |
aten | -0.002 |
dayName | -0.002 |
otle | -0.002 |
UGC | -0.002 |
Token | With |
Token ID | 3152 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
...] | +0.367 |
Virtue | +0.348 |
…] | +0.344 |
alog | +0.331 |
gee | +0.330 |
Neg logit contributions | |
ILCS | -0.372 |
aten | -0.371 |
dayName | -0.365 |
otle | -0.350 |
UGC | -0.333 |
Token | That |
Token ID | 2504 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
...] | +1.484 |
Virtue | +1.398 |
…] | +1.382 |
alog | +1.326 |
>] | +1.325 |
Neg logit contributions | |
aten | -1.462 |
ILCS | -1.457 |
dayName | -1.426 |
otle | -1.378 |
UGC | -1.329 |
Token | is |
Token ID | 318 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
...] | +0.371 |
Virtue | +0.351 |
…] | +0.347 |
alog | +0.332 |
gee | +0.331 |
Neg logit contributions | |
ILCS | -0.400 |
aten | -0.397 |
dayName | -0.392 |
otle | -0.376 |
UGC | -0.358 |
Token | now |
Token ID | 783 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
...] | +0.178 |
Virtue | +0.168 |
…] | +0.166 |
alog | +0.159 |
gee | +0.159 |
Neg logit contributions | |
ILCS | -0.189 |
aten | -0.187 |
dayName | -0.185 |
otle | -0.177 |
UGC | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
...] | +0.056 |
Virtue | +0.053 |
…] | +0.052 |
alog | +0.050 |
gee | +0.050 |
Neg logit contributions | |
ILCS | -0.059 |
aten | -0.058 |
dayName | -0.057 |
otle | -0.055 |
UGC | -0.052 |
Token | place |
Token ID | 1295 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ILCS | +0.045 |
aten | +0.045 |
dayName | +0.044 |
otle | +0.042 |
UGC | +0.040 |
Neg logit contributions | |
...] | -0.041 |
Virtue | -0.038 |
…] | -0.038 |
alog | -0.036 |
gee | -0.036 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ILCS | +0.156 |
aten | +0.154 |
dayName | +0.153 |
otle | +0.147 |
UGC | +0.141 |
Neg logit contributions | |
...] | -0.111 |
Virtue | -0.104 |
…] | -0.103 |
alog | -0.098 |
gee | -0.097 |
Token | airline |
Token ID | 18091 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
...] | +0.900 |
Virtue | +0.844 |
…] | +0.837 |
alog | +0.813 |
Fu | +0.801 |
Neg logit contributions | |
ILCS | -0.997 |
dayName | -0.980 |
aten | -0.979 |
otle | -0.937 |
UGC | -0.891 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
...] | +0.392 |
Virtue | +0.371 |
…] | +0.368 |
alog | +0.354 |
gee | +0.352 |
Neg logit contributions | |
ILCS | -0.380 |
aten | -0.378 |
dayName | -0.374 |
otle | -0.357 |
UGC | -0.338 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
...] | +0.763 |
Virtue | +0.705 |
…] | +0.703 |
gee | +0.670 |
Fu | +0.669 |
Neg logit contributions | |
ILCS | -1.014 |
aten | -1.012 |
dayName | -1.004 |
otle | -0.965 |
UGC | -0.921 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
...] | +1.628 |
Virtue | +1.587 |
…] | +1.538 |
gee | +1.523 |
�� | +1.507 |
Neg logit contributions | |
ILCS | -1.534 |
aten | -1.524 |
dayName | -1.522 |
otle | -1.466 |
UGC | -1.390 |
Token | open |
Token ID | 1280 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
...] | +1.002 |
Virtue | +0.950 |
…] | +0.936 |
Fu | +0.905 |
alog | +0.897 |
Neg logit contributions | |
aten | -1.067 |
ILCS | -1.064 |
dayName | -1.056 |
otle | -1.022 |
UGC | -0.972 |
Token | flights |
Token ID | 13956 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
...] | +1.397 |
…] | +1.309 |
Virtue | +1.308 |
�� | +1.254 |
alog | +1.253 |
Neg logit contributions | |
aten | -1.528 |
ILCS | -1.504 |
dayName | -1.500 |
otle | -1.480 |
UGC | -1.382 |
Token | to |
Token ID | 284 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
...] | +0.379 |
Virtue | +0.360 |
…] | +0.355 |
alog | +0.342 |
gee | +0.341 |
Neg logit contributions | |
ILCS | -0.401 |
aten | -0.397 |
dayName | -0.396 |
otle | -0.377 |
UGC | -0.357 |
Token | US |
Token ID | 1294 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
...] | +0.214 |
Virtue | +0.201 |
…] | +0.199 |
alog | +0.190 |
gee | +0.189 |
Neg logit contributions | |
ILCS | -0.266 |
aten | -0.264 |
dayName | -0.261 |
otle | -0.251 |
UGC | -0.239 |
Token | on |
Token ID | 319 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
...] | +0.940 |
Virtue | +0.881 |
…] | +0.880 |
alog | +0.849 |
gee | +0.840 |
Neg logit contributions | |
dayName | -0.873 |
ILCS | -0.872 |
aten | -0.862 |
otle | -0.820 |
UGC | -0.775 |
Token | sidelines |
Token ID | 29394 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
...] | +0.504 |
Virtue | +0.475 |
…] | +0.472 |
alog | +0.453 |
gee | +0.451 |
Neg logit contributions | |
ILCS | -0.520 |
aten | -0.514 |
dayName | -0.509 |
otle | -0.486 |
UGC | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ILCS | +0.016 |
aten | +0.016 |
dayName | +0.016 |
otle | +0.015 |
UGC | +0.015 |
Neg logit contributions | |
...] | -0.016 |
Virtue | -0.015 |
…] | -0.015 |
alog | -0.014 |
gee | -0.014 |
Token | I |
Token ID | 40 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
ILCS | +0.408 |
aten | +0.403 |
dayName | +0.399 |
otle | +0.382 |
UGC | +0.366 |
Neg logit contributions | |
...] | -0.307 |
Virtue | -0.287 |
…] | -0.285 |
gee | -0.273 |
alog | -0.272 |
Token | � |
Token ID | 447 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ILCS | +0.023 |
aten | +0.022 |
dayName | +0.022 |
otle | +0.021 |
UGC | +0.020 |
Neg logit contributions | |
...] | -0.024 |
Virtue | -0.023 |
…] | -0.023 |
alog | -0.022 |
gee | -0.022 |
Token | � |
Token ID | 247 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ILCS | +0.320 |
aten | +0.317 |
dayName | +0.315 |
otle | +0.303 |
UGC | +0.289 |
Neg logit contributions | |
...] | -0.237 |
Virtue | -0.222 |
…] | -0.220 |
alog | -0.209 |
gee | -0.209 |
Token | ve |
Token ID | 303 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ILCS | +0.595 |
aten | +0.590 |
dayName | +0.586 |
otle | +0.563 |
UGC | +0.535 |
Neg logit contributions | |
...] | -0.456 |
Virtue | -0.429 |
…] | -0.426 |
alog | -0.405 |
gee | -0.404 |
Token | written |
Token ID | 3194 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
aten | +1.407 |
ILCS | +1.407 |
dayName | +1.405 |
otle | +1.358 |
UGC | +1.304 |
Neg logit contributions | |
...] | -0.598 |
Virtue | -0.556 |
…] | -0.542 |
Fu | -0.507 |
gee | -0.504 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ILCS | +2.520 |
dayName | +2.497 |
aten | +2.458 |
otle | +2.315 |
UGC | +2.254 |
Neg logit contributions | |
...] | -2.043 |
Virtue | -1.948 |
…] | -1.904 |
alog | -1.832 |
gee | -1.785 |
Token | couple |
Token ID | 3155 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ILCS | +1.186 |
aten | +1.173 |
dayName | +1.151 |
otle | +1.095 |
UGC | +1.054 |
Neg logit contributions | |
...] | -1.110 |
Virtue | -1.066 |
…] | -1.049 |
alog | -1.009 |
gee | -0.996 |
Token | of |
Token ID | 286 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ILCS | +0.822 |
aten | +0.816 |
dayName | +0.806 |
otle | +0.770 |
UGC | +0.729 |
Neg logit contributions | |
...] | -0.701 |
Virtue | -0.662 |
…] | -0.658 |
alog | -0.627 |
Fu | -0.620 |
Token | books |
Token ID | 3835 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ILCS | +0.334 |
aten | +0.333 |
dayName | +0.326 |
otle | +0.310 |
UGC | +0.295 |
Neg logit contributions | |
...] | -0.402 |
Virtue | -0.383 |
…] | -0.379 |
alog | -0.366 |
gee | -0.364 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ILCS | +0.494 |
aten | +0.488 |
dayName | +0.485 |
otle | +0.461 |
UGC | +0.438 |
Neg logit contributions | |
...] | -0.468 |
Virtue | -0.442 |
…] | -0.440 |
Fu | -0.420 |
alog | -0.420 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ILCS | +0.528 |
aten | +0.523 |
dayName | +0.520 |
otle | +0.498 |
UGC | +0.473 |
Neg logit contributions | |
...] | -0.460 |
Virtue | -0.433 |
…] | -0.430 |
alog | -0.409 |
gee | -0.408 |
Token | views |
Token ID | 5009 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ILCS | +0.923 |
dayName | +0.906 |
aten | +0.896 |
otle | +0.857 |
UGC | +0.804 |
Neg logit contributions | |
...] | -1.071 |
…] | -1.018 |
Virtue | -1.018 |
alog | -0.977 |
gee | -0.970 |
Token | of |
Token ID | 286 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ILCS | +0.609 |
aten | +0.602 |
dayName | +0.595 |
otle | +0.571 |
UGC | +0.545 |
Neg logit contributions | |
...] | -0.538 |
Virtue | -0.504 |
…] | -0.502 |
alog | -0.479 |
gee | -0.476 |
Token | The |
Token ID | 383 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ILCS | +0.619 |
aten | +0.611 |
dayName | +0.608 |
otle | +0.577 |
UGC | +0.541 |
Neg logit contributions | |
...] | -0.706 |
Virtue | -0.672 |
…] | -0.667 |
gee | -0.639 |
alog | -0.637 |
Token | Hill |
Token ID | 3327 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ILCS | +0.872 |
dayName | +0.868 |
aten | +0.866 |
otle | +0.831 |
UGC | +0.790 |
Neg logit contributions | |
...] | -0.611 |
Virtue | -0.576 |
…] | -0.569 |
alog | -0.539 |
Lump | -0.538 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
aten | +0.990 |
dayName | +0.987 |
ILCS | +0.987 |
otle | +0.943 |
UGC | +0.894 |
Neg logit contributions | |
...] | -0.901 |
…] | -0.846 |
Virtue | -0.840 |
alog | -0.804 |
Fu | -0.796 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
aten | +2.256 |
dayName | +2.239 |
ILCS | +2.237 |
otle | +2.175 |
utor | +2.042 |
Neg logit contributions | |
...] | -1.659 |
Virtue | -1.550 |
…] | -1.547 |
gee | -1.484 |
Lump | -1.463 |
Token | K |
Token ID | 42 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
...] | +0.038 |
Virtue | +0.036 |
…] | +0.036 |
alog | +0.034 |
gee | +0.034 |
Neg logit contributions | |
ILCS | -0.043 |
aten | -0.042 |
dayName | -0.042 |
otle | -0.040 |
UGC | -0.038 |
Token | UAL |
Token ID | 25620 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
ILCS | +0.394 |
aten | +0.387 |
dayName | +0.386 |
otle | +0.365 |
UGC | +0.345 |
Neg logit contributions | |
...] | -0.443 |
Virtue | -0.421 |
…] | -0.417 |
alog | -0.403 |
gee | -0.401 |
Token | A |
Token ID | 32 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
...] | +0.667 |
Virtue | +0.630 |
…] | +0.621 |
alog | +0.599 |
gee | +0.597 |
Neg logit contributions | |
ILCS | -0.747 |
aten | -0.736 |
dayName | -0.722 |
otle | -0.692 |
UGC | -0.663 |
Token | L |
Token ID | 406 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ILCS | +0.413 |
aten | +0.413 |
dayName | +0.407 |
otle | +0.388 |
UGC | +0.366 |
Neg logit contributions | |
...] | -0.427 |
Virtue | -0.406 |
…] | -0.402 |
Fu | -0.386 |
Lump | -0.384 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
...] | +0.718 |
Virtue | +0.676 |
…] | +0.667 |
alog | +0.642 |
gee | +0.637 |
Neg logit contributions | |
ILCS | -0.800 |
aten | -0.791 |
dayName | -0.783 |
otle | -0.747 |
ENTS | -0.717 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
...] | +0.673 |
Virtue | +0.637 |
…] | +0.630 |
gee | +0.603 |
alog | +0.603 |
Neg logit contributions | |
aten | -0.755 |
ILCS | -0.753 |
dayName | -0.740 |
otle | -0.713 |
ENTS | -0.676 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ILCS | +0.016 |
aten | +0.015 |
dayName | +0.015 |
otle | +0.015 |
UGC | +0.014 |
Neg logit contributions | |
...] | -0.018 |
Virtue | -0.017 |
…] | -0.017 |
alog | -0.016 |
gee | -0.016 |
Token | : |
Token ID | 25 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
...] | +0.486 |
Virtue | +0.460 |
…] | +0.457 |
alog | +0.440 |
gee | +0.438 |
Neg logit contributions | |
ILCS | -0.470 |
aten | -0.467 |
dayName | -0.461 |
otle | -0.442 |
UGC | -0.419 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
...] | +0.514 |
Virtue | +0.484 |
…] | +0.479 |
alog | +0.462 |
Fu | +0.460 |
Neg logit contributions | |
ILCS | -0.571 |
aten | -0.567 |
dayName | -0.562 |
otle | -0.543 |
UGC | -0.512 |
Token | staff |
Token ID | 3085 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
...] | +0.365 |
Virtue | +0.346 |
…] | +0.342 |
alog | +0.329 |
gee | +0.328 |
Neg logit contributions | |
ILCS | -0.401 |
aten | -0.398 |
dayName | -0.391 |
otle | -0.377 |
UGC | -0.358 |
Token | are |
Token ID | 389 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ILCS | +2.047 |
aten | +1.989 |
dayName | +1.979 |
otle | +1.871 |
UGC | +1.785 |
Neg logit contributions | |
...] | -1.603 |
Virtue | -1.533 |
…] | -1.495 |
gee | -1.447 |
>] | -1.445 |
Token | ' |
Token ID | 705 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
...] | +0.654 |
Virtue | +0.609 |
…] | +0.598 |
alog | +0.575 |
gee | +0.571 |
Neg logit contributions | |
aten | -1.012 |
ILCS | -1.010 |
dayName | -0.993 |
otle | -0.959 |
UGC | -0.927 |
Token | big |
Token ID | 14261 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
...] | +0.418 |
Virtue | +0.384 |
…] | +0.374 |
alog | +0.353 |
gee | +0.346 |
Neg logit contributions | |
aten | -0.970 |
ILCS | -0.967 |
dayName | -0.958 |
otle | -0.926 |
UGC | -0.898 |
Token | gest |
Token ID | 3495 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
...] | +1.364 |
Virtue | +1.284 |
…] | +1.259 |
gee | +1.207 |
Fu | +1.204 |
Neg logit contributions | |
ILCS | -1.279 |
aten | -1.278 |
dayName | -1.268 |
otle | -1.204 |
UGC | -1.153 |
Token | a |
Token ID | 257 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
...] | +1.130 |
Virtue | +1.048 |
…] | +1.046 |
alog | +1.003 |
gee | +0.993 |
Neg logit contributions | |
dayName | -1.213 |
ILCS | -1.213 |
aten | -1.213 |
otle | -1.158 |
UGC | -1.102 |
Token | per |
Token ID | 583 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ILCS | +0.486 |
aten | +0.478 |
dayName | +0.475 |
otle | +0.455 |
UGC | +0.437 |
Neg logit contributions | |
...] | -0.344 |
Virtue | -0.321 |
…] | -0.317 |
alog | -0.304 |
gee | -0.302 |
Token | use |
Token ID | 1904 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
ILCS | +0.442 |
aten | +0.437 |
dayName | +0.432 |
otle | +0.413 |
UGC | +0.390 |
Neg logit contributions | |
...] | -0.493 |
Virtue | -0.465 |
…] | -0.462 |
gee | -0.443 |
alog | -0.443 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ILCS | +0.679 |
aten | +0.675 |
dayName | +0.669 |
otle | +0.636 |
UGC | +0.607 |
Neg logit contributions | |
...] | -0.620 |
Virtue | -0.583 |
…] | -0.578 |
alog | -0.553 |
Fu | -0.549 |
Token | Here |
Token ID | 3423 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
aten | +1.232 |
ILCS | +1.232 |
dayName | +1.198 |
otle | +1.146 |
utor | +1.078 |
Neg logit contributions | |
...] | -1.532 |
Virtue | -1.459 |
…] | -1.451 |
gee | -1.388 |
alog | -1.382 |
Token | is |
Token ID | 318 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
ILCS | +0.514 |
aten | +0.506 |
dayName | +0.501 |
otle | +0.479 |
UGC | +0.456 |
Neg logit contributions | |
...] | -0.486 |
Virtue | -0.463 |
…] | -0.458 |
alog | -0.438 |
gee | -0.438 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ILCS | +0.466 |
aten | +0.460 |
dayName | +0.457 |
otle | +0.436 |
UGC | +0.415 |
Neg logit contributions | |
...] | -0.402 |
Virtue | -0.382 |
…] | -0.375 |
alog | -0.360 |
Fu | -0.358 |
Token | link |
Token ID | 2792 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ILCS | +2.062 |
aten | +1.994 |
dayName | +1.968 |
otle | +1.871 |
UGC | +1.829 |
Neg logit contributions | |
...] | -1.429 |
Virtue | -1.358 |
…] | -1.319 |
gee | -1.248 |
Fu | -1.242 |
Token | for |
Token ID | 329 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
...] | +1.019 |
Virtue | +0.975 |
…] | +0.957 |
alog | +0.925 |
>] | +0.922 |
Neg logit contributions | |
ILCS | -1.011 |
aten | -1.004 |
dayName | -1.004 |
otle | -0.952 |
UGC | -0.898 |
Token | buying |
Token ID | 7067 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
ILCS | +0.295 |
aten | +0.291 |
dayName | +0.288 |
otle | +0.277 |
UGC | +0.264 |
Neg logit contributions | |
...] | -0.240 |
Virtue | -0.226 |
…] | -0.223 |
alog | -0.213 |
gee | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ILCS | +0.525 |
aten | +0.517 |
dayName | +0.515 |
otle | +0.487 |
ENTS | +0.467 |
Neg logit contributions | |
...] | -0.449 |
Virtue | -0.424 |
…] | -0.420 |
alog | -0.402 |
gee | -0.397 |
Token | second |
Token ID | 1218 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ILCS | +1.327 |
aten | +1.285 |
dayName | +1.274 |
otle | +1.204 |
UGC | +1.151 |
Neg logit contributions | |
...] | -1.303 |
Virtue | -1.231 |
…] | -1.223 |
alog | -1.169 |
Fu | -1.159 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
...] | +0.529 |
Virtue | +0.499 |
…] | +0.492 |
alog | +0.473 |
gee | +0.470 |
Neg logit contributions | |
ILCS | -0.594 |
aten | -0.587 |
dayName | -0.582 |
otle | -0.555 |
UGC | -0.531 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
...] | +0.581 |
Virtue | +0.551 |
…] | +0.545 |
gee | +0.522 |
alog | +0.521 |
Neg logit contributions | |
aten | -0.628 |
ILCS | -0.627 |
dayName | -0.615 |
otle | -0.592 |
ENTS | -0.561 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ILCS | +0.166 |
aten | +0.163 |
dayName | +0.162 |
otle | +0.154 |
UGC | +0.146 |
Neg logit contributions | |
...] | -0.192 |
Virtue | -0.183 |
…] | -0.181 |
alog | -0.174 |
gee | -0.174 |
Token | : |
Token ID | 25 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
...] | +0.472 |
Virtue | +0.448 |
…] | +0.444 |
alog | +0.428 |
gee | +0.426 |
Neg logit contributions | |
ILCS | -0.455 |
aten | -0.452 |
dayName | -0.447 |
otle | -0.428 |
UGC | -0.405 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
...] | +0.428 |
Virtue | +0.403 |
…] | +0.399 |
alog | +0.384 |
gee | +0.382 |
Neg logit contributions | |
ILCS | -0.480 |
aten | -0.477 |
dayName | -0.472 |
otle | -0.455 |
UGC | -0.431 |
Token | staff |
Token ID | 3085 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
...] | +0.340 |
Virtue | +0.321 |
…] | +0.318 |
alog | +0.306 |
gee | +0.305 |
Neg logit contributions | |
ILCS | -0.365 |
aten | -0.362 |
dayName | -0.356 |
otle | -0.343 |
UGC | -0.326 |
Token | are |
Token ID | 389 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ILCS | +1.840 |
aten | +1.793 |
dayName | +1.779 |
otle | +1.686 |
UGC | +1.607 |
Neg logit contributions | |
...] | -1.506 |
Virtue | -1.438 |
…] | -1.406 |
gee | -1.360 |
>] | -1.357 |
Token | ' |
Token ID | 705 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
...] | +0.790 |
Virtue | +0.735 |
…] | +0.723 |
alog | +0.697 |
gee | +0.690 |
Neg logit contributions | |
aten | -1.178 |
ILCS | -1.175 |
dayName | -1.153 |
otle | -1.115 |
UGC | -1.078 |
Token | big |
Token ID | 14261 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
...] | +0.406 |
Virtue | +0.373 |
…] | +0.362 |
alog | +0.342 |
gee | +0.336 |
Neg logit contributions | |
aten | -0.952 |
ILCS | -0.950 |
dayName | -0.941 |
otle | -0.909 |
UGC | -0.882 |
Token | gest |
Token ID | 3495 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
...] | +1.490 |
Virtue | +1.404 |
…] | +1.378 |
�� | +1.319 |
gee | +1.319 |
Neg logit contributions | |
ILCS | -1.345 |
aten | -1.344 |
dayName | -1.337 |
otle | -1.265 |
UGC | -1.212 |
Token | a |
Token ID | 257 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
...] | +1.146 |
Virtue | +1.064 |
…] | +1.062 |
alog | +1.019 |
gee | +1.008 |
Neg logit contributions | |
dayName | -1.206 |
aten | -1.204 |
ILCS | -1.203 |
otle | -1.149 |
UGC | -1.094 |
Token | fossil |
Token ID | 12584 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
...] | +0.189 |
Virtue | +0.178 |
…] | +0.176 |
alog | +0.169 |
gee | +0.168 |
Neg logit contributions | |
ILCS | -0.210 |
aten | -0.208 |
dayName | -0.206 |
otle | -0.198 |
UGC | -0.188 |
Token | fuel |
Token ID | 5252 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
...] | +0.074 |
Virtue | +0.070 |
…] | +0.070 |
alog | +0.067 |
gee | +0.067 |
Neg logit contributions | |
ILCS | -0.068 |
aten | -0.067 |
dayName | -0.066 |
otle | -0.063 |
UGC | -0.059 |
Token | interests |
Token ID | 5353 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
...] | +0.219 |
Virtue | +0.204 |
…] | +0.201 |
alog | +0.190 |
gee | +0.190 |
Neg logit contributions | |
ILCS | -0.338 |
aten | -0.336 |
dayName | -0.332 |
otle | -0.321 |
UGC | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
...] | +0.100 |
Virtue | +0.095 |
…] | +0.094 |
alog | +0.090 |
gee | +0.089 |
Neg logit contributions | |
ILCS | -0.104 |
aten | -0.102 |
dayName | -0.101 |
otle | -0.097 |
UGC | -0.092 |
Token | Senator |
Token ID | 8962 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
...] | +0.098 |
Virtue | +0.093 |
…] | +0.092 |
alog | +0.088 |
gee | +0.088 |
Neg logit contributions | |
ILCS | -0.106 |
aten | -0.105 |
dayName | -0.104 |
otle | -0.100 |
UGC | -0.095 |
Token | Sheldon |
Token ID | 34536 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
...] | +0.093 |
Virtue | +0.088 |
…] | +0.087 |
alog | +0.084 |
gee | +0.083 |
Neg logit contributions | |
ILCS | -0.096 |
aten | -0.095 |
dayName | -0.094 |
otle | -0.090 |
UGC | -0.085 |
Token | White |
Token ID | 2635 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
dayName | +1.781 |
ILCS | +1.781 |
aten | +1.763 |
otle | +1.673 |
utor | +1.587 |
Neg logit contributions | |
...] | -1.546 |
Virtue | -1.468 |
…] | -1.432 |
Lump | -1.362 |
Fu | -1.341 |
Token | house |
Token ID | 4803 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
...] | +0.378 |
Virtue | +0.359 |
…] | +0.356 |
alog | +0.343 |
gee | +0.342 |
Neg logit contributions | |
ILCS | -0.314 |
aten | -0.311 |
dayName | -0.306 |
otle | -0.292 |
UGC | -0.275 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
...] | +0.190 |
Virtue | +0.179 |
…] | +0.177 |
alog | +0.170 |
gee | +0.169 |
Neg logit contributions | |
ILCS | -0.217 |
aten | -0.215 |
dayName | -0.213 |
otle | -0.204 |
UGC | -0.194 |
Token | Democrat |
Token ID | 9755 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
...] | +0.150 |
Virtue | +0.142 |
…] | +0.141 |
alog | +0.135 |
gee | +0.135 |
Neg logit contributions | |
ILCS | -0.156 |
aten | -0.154 |
dayName | -0.153 |
otle | -0.146 |
UGC | -0.139 |
Token | of |
Token ID | 286 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
...] | +0.039 |
Virtue | +0.037 |
…] | +0.036 |
alog | +0.035 |
gee | +0.035 |
Neg logit contributions | |
ILCS | -0.042 |
aten | -0.042 |
dayName | -0.042 |
otle | -0.040 |
UGC | -0.038 |
Token | views |
Token ID | 5009 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
ILCS | +0.371 |
aten | +0.365 |
dayName | +0.362 |
otle | +0.344 |
UGC | +0.325 |
Neg logit contributions | |
...] | -0.419 |
Virtue | -0.400 |
…] | -0.396 |
alog | -0.381 |
gee | -0.379 |
Token | of |
Token ID | 286 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ILCS | +0.722 |
aten | +0.718 |
dayName | +0.711 |
otle | +0.688 |
UGC | +0.664 |
Neg logit contributions | |
...] | -0.336 |
Virtue | -0.306 |
…] | -0.303 |
alog | -0.282 |
gee | -0.280 |
Token | contributors |
Token ID | 20420 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ILCS | +0.434 |
aten | +0.428 |
dayName | +0.426 |
otle | +0.410 |
UGC | +0.393 |
Neg logit contributions | |
...] | -0.271 |
Virtue | -0.253 |
…] | -0.250 |
alog | -0.236 |
gee | -0.235 |
Token | are |
Token ID | 389 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ILCS | +0.379 |
aten | +0.375 |
dayName | +0.370 |
otle | +0.351 |
UGC | +0.333 |
Neg logit contributions | |
...] | -0.430 |
Virtue | -0.407 |
…] | -0.405 |
alog | -0.387 |
gee | -0.387 |
Token | their |
Token ID | 511 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ILCS | +0.958 |
aten | +0.952 |
dayName | +0.950 |
otle | +0.914 |
UGC | +0.862 |
Neg logit contributions | |
...] | -0.753 |
Virtue | -0.706 |
…] | -0.702 |
alog | -0.668 |
Fu | -0.663 |
Token | own |
Token ID | 898 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ILCS | +0.781 |
dayName | +0.767 |
aten | +0.766 |
otle | +0.734 |
UGC | +0.696 |
Neg logit contributions | |
...] | -0.666 |
Virtue | -0.631 |
…] | -0.626 |
alog | -0.600 |
gee | -0.600 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ILCS | +1.763 |
dayName | +1.748 |
aten | +1.733 |
otle | +1.666 |
UGC | +1.577 |
Neg logit contributions | |
...] | -1.551 |
…] | -1.456 |
Virtue | -1.445 |
gee | -1.398 |
alog | -1.363 |
Token | are |
Token ID | 389 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ILCS | +0.906 |
aten | +0.897 |
dayName | +0.893 |
otle | +0.846 |
UGC | +0.804 |
Neg logit contributions | |
...] | -0.884 |
…] | -0.829 |
Virtue | -0.826 |
alog | -0.790 |
gee | -0.784 |
Token | not |
Token ID | 407 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
ILCS | +1.178 |
dayName | +1.169 |
aten | +1.169 |
otle | +1.118 |
UGC | +1.055 |
Neg logit contributions | |
...] | -0.988 |
…] | -0.927 |
Virtue | -0.922 |
alog | -0.871 |
>] | -0.870 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ILCS | +0.528 |
aten | +0.523 |
dayName | +0.520 |
otle | +0.498 |
UGC | +0.473 |
Neg logit contributions | |
...] | -0.460 |
Virtue | -0.433 |
…] | -0.430 |
alog | -0.409 |
gee | -0.408 |
Token | views |
Token ID | 5009 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ILCS | +0.923 |
dayName | +0.906 |
aten | +0.896 |
otle | +0.857 |
UGC | +0.804 |
Neg logit contributions | |
...] | -1.071 |
…] | -1.018 |
Virtue | -1.018 |
alog | -0.977 |
gee | -0.970 |
Token | PT |
Token ID | 11571 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
...] | +0.548 |
Virtue | +0.522 |
…] | +0.517 |
alog | +0.496 |
gee | +0.495 |
Neg logit contributions | |
ILCS | -0.460 |
aten | -0.454 |
dayName | -0.448 |
otle | -0.428 |
UGC | -0.404 |
Token | PowerPoint |
Token ID | 43563 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ILCS | +0.050 |
aten | +0.050 |
dayName | +0.049 |
otle | +0.047 |
UGC | +0.044 |
Neg logit contributions | |
...] | -0.056 |
Virtue | -0.053 |
…] | -0.053 |
alog | -0.051 |
gee | -0.051 |
Token | slide |
Token ID | 10649 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ILCS | +0.061 |
aten | +0.060 |
dayName | +0.059 |
otle | +0.056 |
UGC | +0.052 |
Neg logit contributions | |
...] | -0.086 |
Virtue | -0.082 |
…] | -0.081 |
alog | -0.078 |
gee | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ILCS | +0.304 |
aten | +0.301 |
dayName | +0.297 |
otle | +0.284 |
UGC | +0.270 |
Neg logit contributions | |
...] | -0.293 |
Virtue | -0.277 |
…] | -0.274 |
alog | -0.263 |
gee | -0.261 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
...] | +0.131 |
Virtue | +0.124 |
…] | +0.123 |
alog | +0.118 |
gee | +0.118 |
Neg logit contributions | |
ILCS | -0.133 |
aten | -0.131 |
dayName | -0.130 |
otle | -0.124 |
UGC | -0.118 |
Token | Power |
Token ID | 13434 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
...] | +0.171 |
Virtue | +0.162 |
…] | +0.160 |
alog | +0.153 |
gee | +0.152 |
Neg logit contributions | |
ILCS | -0.198 |
aten | -0.196 |
dayName | -0.194 |
otle | -0.186 |
UGC | -0.177 |
Token | Point |
Token ID | 12727 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
aten | +1.124 |
ILCS | +1.109 |
dayName | +1.071 |
otle | +1.034 |
utor | +0.960 |
Neg logit contributions | |
...] | -2.131 |
Virtue | -2.080 |
…] | -2.049 |
Fu | -2.009 |
Lump | -2.006 |
Token | slide |
Token ID | 10649 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
...] | +0.514 |
Virtue | +0.493 |
…] | +0.488 |
alog | +0.472 |
gee | +0.471 |
Neg logit contributions | |
ILCS | -0.343 |
aten | -0.339 |
dayName | -0.334 |
otle | -0.316 |
UGC | -0.296 |
Token | PNG |
Token ID | 36182 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ILCS | +0.229 |
aten | +0.224 |
dayName | +0.221 |
otle | +0.211 |
UGC | +0.199 |
Neg logit contributions | |
...] | -0.284 |
Virtue | -0.270 |
…] | -0.268 |
alog | -0.258 |
Fu | -0.257 |
Token | larger |
Token ID | 4025 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
...] | +0.167 |
Virtue | +0.157 |
…] | +0.156 |
alog | +0.149 |
gee | +0.148 |
Neg logit contributions | |
ILCS | -0.193 |
aten | -0.191 |
dayName | -0.189 |
otle | -0.181 |
UGC | -0.172 |
Token | image |
Token ID | 2939 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ILCS | +0.214 |
aten | +0.211 |
dayName | +0.209 |
otle | +0.200 |
UGC | +0.190 |
Neg logit contributions | |
...] | -0.203 |
Virtue | -0.191 |
…] | -0.190 |
alog | -0.181 |
gee | -0.181 |
Token | claim |
Token ID | 6604 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ILCS | +0.092 |
aten | +0.090 |
dayName | +0.090 |
otle | +0.085 |
UGC | +0.081 |
Neg logit contributions | |
...] | -0.094 |
Virtue | -0.089 |
…] | -0.088 |
alog | -0.085 |
gee | -0.085 |
Token | ing |
Token ID | 278 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
ILCS | +1.303 |
dayName | +1.273 |
aten | +1.264 |
otle | +1.226 |
ENTS | +1.167 |
Neg logit contributions | |
...] | -0.741 |
Virtue | -0.705 |
…] | -0.680 |
alog | -0.650 |
Fu | -0.641 |
Token | the |
Token ID | 262 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ILCS | +0.343 |
dayName | +0.336 |
aten | +0.336 |
otle | +0.319 |
UGC | +0.304 |
Neg logit contributions | |
...] | -0.296 |
Virtue | -0.282 |
…] | -0.277 |
alog | -0.264 |
Fu | -0.264 |
Token | American |
Token ID | 1605 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +0.462 |
aten | +0.455 |
dayName | +0.453 |
otle | +0.427 |
UGC | +0.405 |
Neg logit contributions | |
...] | -0.541 |
Virtue | -0.524 |
…] | -0.512 |
alog | -0.495 |
Lump | -0.492 |
Token | Right |
Token ID | 6498 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
...] | +0.881 |
…] | +0.821 |
Virtue | +0.817 |
alog | +0.781 |
Fu | +0.780 |
Neg logit contributions | |
ILCS | -0.980 |
aten | -0.967 |
dayName | -0.952 |
otle | -0.923 |
UGC | -0.861 |
Token | : |
Token ID | 25 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
...] | +0.133 |
Virtue | +0.126 |
…] | +0.124 |
alog | +0.119 |
gee | +0.119 |
Neg logit contributions | |
ILCS | -0.135 |
aten | -0.134 |
dayName | -0.133 |
otle | -0.127 |
UGC | -0.120 |
Token | The |
Token ID | 383 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
ILCS | +1.649 |
aten | +1.600 |
dayName | +1.585 |
otle | +1.515 |
utor | +1.474 |
Neg logit contributions | |
...] | -1.668 |
Virtue | -1.631 |
…] | -1.552 |
Lump | -1.510 |
Fu | -1.509 |
Token | Lost |
Token ID | 9164 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
...] | +0.039 |
Virtue | +0.038 |
…] | +0.037 |
alog | +0.036 |
gee | +0.036 |
Neg logit contributions | |
ILCS | -0.032 |
aten | -0.031 |
dayName | -0.031 |
otle | -0.030 |
UGC | -0.028 |
Token | Legacy |
Token ID | 14843 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
...] | +0.109 |
Virtue | +0.104 |
…] | +0.103 |
alog | +0.099 |
gee | +0.099 |
Neg logit contributions | |
ILCS | -0.089 |
aten | -0.088 |
dayName | -0.087 |
otle | -0.083 |
UGC | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ILCS | +0.069 |
aten | +0.068 |
dayName | +0.068 |
otle | +0.065 |
UGC | +0.062 |
Neg logit contributions | |
...] | -0.063 |
Virtue | -0.059 |
…] | -0.059 |
alog | -0.056 |
gee | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
ILCS | +0.235 |
aten | +0.232 |
dayName | +0.230 |
otle | +0.220 |
UGC | +0.209 |
Neg logit contributions | |
...] | -0.206 |
Virtue | -0.195 |
…] | -0.192 |
alog | -0.184 |
gee | -0.184 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
...] | +0.599 |
Virtue | +0.564 |
…] | +0.557 |
alog | +0.535 |
gee | +0.531 |
Neg logit contributions | |
ILCS | -0.665 |
aten | -0.658 |
dayName | -0.651 |
otle | -0.622 |
ENTS | -0.595 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
...] | +0.531 |
Virtue | +0.503 |
…] | +0.498 |
gee | +0.477 |
alog | +0.476 |
Neg logit contributions | |
ILCS | -0.574 |
aten | -0.574 |
dayName | -0.563 |
otle | -0.542 |
ENTS | -0.513 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ILCS | +0.144 |
aten | +0.142 |
dayName | +0.141 |
otle | +0.134 |
UGC | +0.127 |
Neg logit contributions | |
...] | -0.163 |
Virtue | -0.155 |
…] | -0.153 |
alog | -0.148 |
gee | -0.147 |
Token | : |
Token ID | 25 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
...] | +0.393 |
Virtue | +0.372 |
…] | +0.369 |
alog | +0.356 |
gee | +0.354 |
Neg logit contributions | |
ILCS | -0.390 |
aten | -0.387 |
dayName | -0.383 |
otle | -0.367 |
UGC | -0.348 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
...] | +0.220 |
Virtue | +0.208 |
…] | +0.205 |
alog | +0.197 |
gee | +0.196 |
Neg logit contributions | |
ILCS | -0.252 |
aten | -0.249 |
dayName | -0.247 |
otle | -0.237 |
UGC | -0.225 |
Token | staff |
Token ID | 3085 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
...] | +0.308 |
Virtue | +0.291 |
…] | +0.288 |
alog | +0.277 |
gee | +0.276 |
Neg logit contributions | |
ILCS | -0.347 |
aten | -0.345 |
dayName | -0.339 |
otle | -0.327 |
UGC | -0.311 |
Token | are |
Token ID | 389 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ILCS | +1.814 |
aten | +1.768 |
dayName | +1.760 |
otle | +1.667 |
UGC | +1.588 |
Neg logit contributions | |
...] | -1.467 |
Virtue | -1.398 |
…] | -1.373 |
>] | -1.320 |
gee | -1.318 |
Token | ' |
Token ID | 705 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
...] | +0.556 |
Virtue | +0.517 |
…] | +0.507 |
alog | +0.486 |
gee | +0.482 |
Neg logit contributions | |
aten | -0.922 |
ILCS | -0.921 |
dayName | -0.907 |
otle | -0.876 |
UGC | -0.846 |
Token | big |
Token ID | 14261 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
...] | +0.364 |
Virtue | +0.335 |
…] | +0.324 |
alog | +0.306 |
gee | +0.301 |
Neg logit contributions | |
aten | -0.870 |
ILCS | -0.869 |
dayName | -0.860 |
otle | -0.832 |
UGC | -0.806 |
Token | gest |
Token ID | 3495 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
...] | +1.337 |
Virtue | +1.260 |
…] | +1.232 |
gee | +1.183 |
�� | +1.180 |
Neg logit contributions | |
aten | -1.305 |
ILCS | -1.303 |
dayName | -1.294 |
otle | -1.231 |
UGC | -1.180 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
...] | +1.001 |
Virtue | +0.930 |
…] | +0.925 |
alog | +0.886 |
gee | +0.878 |
Neg logit contributions | |
aten | -1.133 |
dayName | -1.132 |
ILCS | -1.132 |
otle | -1.084 |
UGC | -1.031 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
...] | +0.086 |
Virtue | +0.081 |
…] | +0.080 |
alog | +0.076 |
gee | +0.076 |
Neg logit contributions | |
ILCS | -0.109 |
aten | -0.108 |
dayName | -0.107 |
otle | -0.103 |
UGC | -0.098 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
...] | +0.349 |
Virtue | +0.332 |
…] | +0.328 |
alog | +0.316 |
gee | +0.314 |
Neg logit contributions | |
ILCS | -0.324 |
aten | -0.321 |
dayName | -0.317 |
otle | -0.303 |
UGC | -0.287 |
Token | : |
Token ID | 25 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
...] | +0.163 |
Virtue | +0.154 |
…] | +0.153 |
alog | +0.147 |
gee | +0.146 |
Neg logit contributions | |
ILCS | -0.169 |
aten | -0.168 |
dayName | -0.166 |
otle | -0.159 |
UGC | -0.151 |
Token | ' |
Token ID | 705 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
...] | +0.301 |
Virtue | +0.284 |
…] | +0.281 |
alog | +0.270 |
gee | +0.268 |
Neg logit contributions | |
ILCS | -0.313 |
aten | -0.309 |
dayName | -0.307 |
otle | -0.294 |
UGC | -0.278 |
Token | I |
Token ID | 40 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
...] | +0.816 |
Virtue | +0.774 |
…] | +0.761 |
alog | +0.736 |
�� | +0.730 |
Neg logit contributions | |
ILCS | -0.904 |
aten | -0.900 |
dayName | -0.893 |
otle | -0.852 |
UGC | -0.815 |
Token | fully |
Token ID | 3938 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ILCS | +0.018 |
aten | +0.017 |
dayName | +0.017 |
otle | +0.017 |
UGC | +0.016 |
Neg logit contributions | |
...] | -0.016 |
Virtue | -0.015 |
…] | -0.015 |
alog | -0.014 |
gee | -0.014 |
Token | expect |
Token ID | 1607 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ILCS | +1.694 |
aten | +1.685 |
dayName | +1.658 |
otle | +1.608 |
UGC | +1.520 |
Neg logit contributions | |
...] | -1.510 |
…] | -1.414 |
Virtue | -1.413 |
alog | -1.352 |
Fu | -1.322 |
Token | ' |
Token ID | 6 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ILCS | +0.218 |
aten | +0.215 |
dayName | +0.214 |
otle | +0.206 |
UGC | +0.197 |
Neg logit contributions | |
...] | -0.135 |
Virtue | -0.125 |
…] | -0.124 |
alog | -0.117 |
gee | -0.117 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ILCS | +0.227 |
aten | +0.223 |
dayName | +0.220 |
otle | +0.208 |
UGC | +0.196 |
Neg logit contributions | |
...] | -0.292 |
Virtue | -0.279 |
…] | -0.277 |
gee | -0.267 |
alog | -0.266 |
Token | treatment |
Token ID | 3513 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
ILCS | +0.823 |
aten | +0.812 |
dayName | +0.801 |
otle | +0.759 |
UGC | +0.733 |
Neg logit contributions | |
...] | -0.741 |
Virtue | -0.698 |
…] | -0.693 |
gee | -0.661 |
>] | -0.659 |
Token | by |
Token ID | 416 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ILCS | +0.043 |
aten | +0.042 |
dayName | +0.042 |
otle | +0.040 |
UGC | +0.038 |
Neg logit contributions | |
...] | -0.038 |
Virtue | -0.036 |
…] | -0.035 |
alog | -0.034 |
gee | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ILCS | +0.770 |
aten | +0.764 |
dayName | +0.757 |
otle | +0.722 |
UGC | +0.689 |
Neg logit contributions | |
...] | -0.671 |
Virtue | -0.636 |
…] | -0.630 |
Fu | -0.599 |
alog | -0.597 |
Token | London |
Token ID | 3576 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ILCS | +0.607 |
aten | +0.599 |
dayName | +0.598 |
otle | +0.559 |
UGC | +0.525 |
Neg logit contributions | |
...] | -0.841 |
Virtue | -0.804 |
…] | -0.802 |
alog | -0.771 |
Fu | -0.765 |
Token | School |
Token ID | 3961 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
...] | +0.395 |
Virtue | +0.373 |
…] | +0.370 |
gee | +0.356 |
alog | +0.355 |
Neg logit contributions | |
ILCS | -0.393 |
aten | -0.388 |
dayName | -0.383 |
otle | -0.365 |
UGC | -0.350 |
Token | of |
Token ID | 286 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ILCS | +0.647 |
aten | +0.645 |
dayName | +0.641 |
otle | +0.611 |
ENTS | +0.577 |
Neg logit contributions | |
...] | -0.564 |
…] | -0.529 |
Virtue | -0.529 |
alog | -0.504 |
gee | -0.499 |
Token | Economics |
Token ID | 18963 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ILCS | +1.118 |
aten | +1.089 |
dayName | +1.084 |
otle | +1.036 |
UGC | +0.978 |
Neg logit contributions | |
...] | -1.204 |
Virtue | -1.136 |
…] | -1.134 |
Lump | -1.079 |
Fu | -1.071 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ILCS | +0.759 |
aten | +0.758 |
dayName | +0.750 |
otle | +0.716 |
ENTS | +0.679 |
Neg logit contributions | |
...] | -0.706 |
Virtue | -0.666 |
…] | -0.662 |
alog | -0.633 |
gee | -0.625 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
aten | +1.679 |
ILCS | +1.669 |
dayName | +1.636 |
otle | +1.575 |
utor | +1.488 |
Neg logit contributions | |
...] | -1.475 |
Virtue | -1.412 |
…] | -1.409 |
gee | -1.343 |
>] | -1.343 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ILCS | +0.181 |
aten | +0.180 |
dayName | +0.177 |
otle | +0.170 |
UGC | +0.161 |
Neg logit contributions | |
...] | -0.176 |
Virtue | -0.166 |
…] | -0.165 |
alog | -0.157 |
gee | -0.157 |
Token | ________________________________ |
Token ID | 10221 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ILCS | +0.630 |
aten | +0.629 |
dayName | +0.616 |
otle | +0.584 |
UGC | +0.545 |
Neg logit contributions | |
...] | -0.824 |
Virtue | -0.786 |
…] | -0.785 |
Fu | -0.754 |
gee | -0.752 |
Token | _ |
Token ID | 62 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
ILCS | +0.078 |
aten | +0.077 |
dayName | +0.077 |
otle | +0.074 |
UGC | +0.070 |
Neg logit contributions | |
...] | -0.068 |
Virtue | -0.064 |
…] | -0.064 |
alog | -0.061 |
gee | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
ILCS | +0.055 |
aten | +0.055 |
dayName | +0.054 |
otle | +0.052 |
UGC | +0.049 |
Neg logit contributions | |
...] | -0.054 |
Virtue | -0.051 |
…] | -0.051 |
alog | -0.049 |
gee | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ILCS | +0.257 |
aten | +0.254 |
dayName | +0.251 |
otle | +0.241 |
UGC | +0.229 |
Neg logit contributions | |
...] | -0.239 |
Virtue | -0.226 |
…] | -0.223 |
alog | -0.214 |
gee | -0.213 |
Token | Rail |
Token ID | 12950 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
ILCS | +0.138 |
aten | +0.136 |
dayName | +0.135 |
otle | +0.129 |
UGC | +0.122 |
Neg logit contributions | |
...] | -0.135 |
Virtue | -0.128 |
…] | -0.127 |
alog | -0.121 |
gee | -0.121 |
Token | ways |
Token ID | 1322 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ILCS | +0.595 |
aten | +0.588 |
dayName | +0.583 |
otle | +0.558 |
UGC | +0.532 |
Neg logit contributions | |
...] | -0.489 |
Virtue | -0.460 |
…] | -0.455 |
alog | -0.437 |
gee | -0.434 |
Token | Minister |
Token ID | 4139 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ILCS | +0.216 |
aten | +0.214 |
dayName | +0.212 |
otle | +0.203 |
UGC | +0.192 |
Neg logit contributions | |
...] | -0.200 |
Virtue | -0.190 |
…] | -0.188 |
alog | -0.180 |
gee | -0.179 |
Token | S |
Token ID | 311 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ILCS | +0.012 |
aten | +0.012 |
dayName | +0.012 |
otle | +0.011 |
UGC | +0.011 |
Neg logit contributions | |
...] | -0.013 |
Virtue | -0.013 |
…] | -0.013 |
alog | -0.012 |
gee | -0.012 |
Token | ures |
Token ID | 942 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ILCS | +0.160 |
aten | +0.158 |
dayName | +0.157 |
otle | +0.150 |
UGC | +0.142 |
Neg logit contributions | |
...] | -0.157 |
Virtue | -0.149 |
…] | -0.147 |
alog | -0.141 |
gee | -0.141 |
Token | h |
Token ID | 71 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ILCS | +1.718 |
dayName | +1.708 |
aten | +1.689 |
otle | +1.611 |
ENTS | +1.549 |
Neg logit contributions | |
...] | -1.421 |
Virtue | -1.340 |
…] | -1.326 |
alog | -1.273 |
gee | -1.269 |
Token | Pr |
Token ID | 1736 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
...] | +0.443 |
Virtue | +0.417 |
…] | +0.415 |
alog | +0.397 |
Fu | +0.396 |
Neg logit contributions | |
ILCS | -0.429 |
aten | -0.423 |
dayName | -0.417 |
otle | -0.400 |
UGC | -0.379 |
Token | ab |
Token ID | 397 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
...] | +0.609 |
Virtue | +0.583 |
…] | +0.578 |
alog | +0.558 |
gee | +0.555 |
Neg logit contributions | |
ILCS | -0.400 |
aten | -0.400 |
dayName | -0.387 |
otle | -0.368 |
UGC | -0.344 |
Token | hu |
Token ID | 13415 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ILCS | +0.257 |
aten | +0.254 |
dayName | +0.253 |
otle | +0.242 |
UGC | +0.232 |
Neg logit contributions | |
...] | -0.191 |
Virtue | -0.179 |
…] | -0.177 |
alog | -0.169 |
gee | -0.169 |
Token | estimates |
Token ID | 7746 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
...] | +0.179 |
Virtue | +0.168 |
…] | +0.166 |
alog | +0.158 |
gee | +0.157 |
Neg logit contributions | |
ILCS | -0.237 |
aten | -0.234 |
dayName | -0.232 |
otle | -0.223 |
UGC | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
...] | +0.567 |
Virtue | +0.537 |
…] | +0.530 |
gee | +0.512 |
alog | +0.511 |
Neg logit contributions | |
ILCS | -0.604 |
aten | -0.599 |
dayName | -0.589 |
otle | -0.565 |
UGC | -0.538 |
Token | views |
Token ID | 5009 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ILCS | +0.225 |
aten | +0.221 |
dayName | +0.220 |
otle | +0.209 |
UGC | +0.196 |
Neg logit contributions | |
...] | -0.279 |
Virtue | -0.267 |
…] | -0.265 |
alog | -0.254 |
gee | -0.254 |
Token | of |
Token ID | 286 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
ILCS | +0.416 |
aten | +0.412 |
dayName | +0.407 |
otle | +0.390 |
UGC | +0.372 |
Neg logit contributions | |
...] | -0.371 |
Virtue | -0.349 |
…] | -0.347 |
alog | -0.331 |
gee | -0.330 |
Token | Town |
Token ID | 8329 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ILCS | +0.294 |
aten | +0.290 |
dayName | +0.289 |
otle | +0.276 |
UGC | +0.262 |
Neg logit contributions | |
...] | -0.271 |
Virtue | -0.257 |
…] | -0.254 |
alog | -0.242 |
gee | -0.242 |
Token | hall |
Token ID | 18323 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ILCS | +0.132 |
aten | +0.131 |
dayName | +0.130 |
otle | +0.125 |
UGC | +0.119 |
Neg logit contributions | |
...] | -0.108 |
Virtue | -0.101 |
…] | -0.100 |
alog | -0.096 |
gee | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ILCS | +0.384 |
aten | +0.381 |
dayName | +0.379 |
otle | +0.362 |
UGC | +0.344 |
Neg logit contributions | |
...] | -0.358 |
Virtue | -0.338 |
…] | -0.336 |
alog | -0.321 |
Fu | -0.321 |
Token | com |
Token ID | 785 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
ILCS | +1.455 |
aten | +1.427 |
dayName | +1.414 |
otle | +1.386 |
ENTS | +1.273 |
Neg logit contributions | |
...] | -1.662 |
…] | -1.581 |
Virtue | -1.570 |
gee | -1.538 |
Fu | -1.512 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ILCS | +0.617 |
aten | +0.609 |
dayName | +0.606 |
otle | +0.580 |
UGC | +0.550 |
Neg logit contributions | |
...] | -0.563 |
Virtue | -0.528 |
…] | -0.528 |
alog | -0.502 |
gee | -0.500 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ILCS | +1.023 |
aten | +1.021 |
dayName | +1.017 |
otle | +0.966 |
UGC | +0.914 |
Neg logit contributions | |
...] | -0.935 |
…] | -0.877 |
Virtue | -0.875 |
gee | -0.832 |
Lump | -0.826 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ILCS | +0.122 |
aten | +0.121 |
dayName | +0.120 |
otle | +0.114 |
UGC | +0.109 |
Neg logit contributions | |
...] | -0.119 |
Virtue | -0.113 |
…] | -0.112 |
alog | -0.107 |
gee | -0.107 |
Token | Bernie |
Token ID | 33433 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ILCS | +0.017 |
aten | +0.017 |
dayName | +0.017 |
otle | +0.016 |
UGC | +0.016 |
Neg logit contributions | |
...] | -0.014 |
Virtue | -0.013 |
…] | -0.013 |
alog | -0.013 |
gee | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
...] | +2.128 |
Virtue | +2.035 |
…] | +1.999 |
>] | +1.946 |
Lump | +1.942 |
Neg logit contributions | |
aten | -1.914 |
ILCS | -1.842 |
dayName | -1.837 |
otle | -1.782 |
ENTS | -1.683 |
Token | our |
Token ID | 674 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
...] | +1.189 |
Virtue | +1.125 |
…] | +1.115 |
Fu | +1.067 |
�� | +1.062 |
Neg logit contributions | |
ILCS | -1.245 |
aten | -1.244 |
dayName | -1.221 |
otle | -1.172 |
UGC | -1.101 |
Token | city |
Token ID | 1748 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
...] | +1.240 |
Virtue | +1.182 |
…] | +1.167 |
alog | +1.133 |
Fu | +1.125 |
Neg logit contributions | |
ILCS | -1.154 |
aten | -1.133 |
dayName | -1.106 |
otle | -1.064 |
ENTS | -1.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
...] | +0.151 |
Virtue | +0.144 |
…] | +0.142 |
alog | +0.137 |
gee | +0.136 |
Neg logit contributions | |
ILCS | -0.146 |
aten | -0.145 |
dayName | -0.143 |
otle | -0.137 |
UGC | -0.129 |
Token | state |
Token ID | 1181 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ILCS | +0.342 |
aten | +0.337 |
dayName | +0.336 |
otle | +0.320 |
UGC | +0.306 |
Neg logit contributions | |
...] | -0.303 |
Virtue | -0.287 |
…] | -0.284 |
gee | -0.271 |
alog | -0.271 |
Token | for |
Token ID | 329 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
...] | +0.378 |
Virtue | +0.358 |
…] | +0.353 |
alog | +0.339 |
gee | +0.338 |
Neg logit contributions | |
ILCS | -0.397 |
aten | -0.394 |
dayName | -0.390 |
otle | -0.373 |
UGC | -0.354 |
Token | free |
Token ID | 1479 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ILCS | +1.467 |
aten | +1.435 |
dayName | +1.411 |
otle | +1.338 |
utor | +1.286 |
Neg logit contributions | |
...] | -1.638 |
Virtue | -1.580 |
…] | -1.554 |
gee | -1.488 |
alog | -1.483 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
...] | +0.848 |
Virtue | +0.807 |
…] | +0.795 |
alog | +0.770 |
gee | +0.763 |
Neg logit contributions | |
ILCS | -0.828 |
aten | -0.816 |
dayName | -0.809 |
otle | -0.770 |
UGC | -0.727 |
Token | Any |
Token ID | 4377 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
...] | +0.766 |
…] | +0.704 |
Virtue | +0.703 |
alog | +0.668 |
Fu | +0.656 |
Neg logit contributions | |
ILCS | -1.212 |
aten | -1.188 |
dayName | -1.184 |
otle | -1.146 |
UGC | -1.103 |
Token | contribution |
Token ID | 10156 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ILCS | +0.031 |
aten | +0.031 |
dayName | +0.031 |
otle | +0.029 |
UGC | +0.028 |
Neg logit contributions | |
...] | -0.030 |
Virtue | -0.028 |
…] | -0.028 |
alog | -0.027 |
gee | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
ILCS | +0.262 |
aten | +0.260 |
dayName | +0.257 |
otle | +0.247 |
UGC | +0.234 |
Neg logit contributions | |
...] | -0.236 |
Virtue | -0.223 |
…] | -0.221 |
alog | -0.212 |
gee | -0.211 |
Token | as |
Token ID | 355 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ILCS | +0.183 |
aten | +0.181 |
dayName | +0.180 |
otle | +0.171 |
UGC | +0.163 |
Neg logit contributions | |
...] | -0.182 |
Virtue | -0.172 |
…] | -0.170 |
alog | -0.163 |
gee | -0.163 |
Token | Visa |
Token ID | 27645 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
...] | +0.128 |
Virtue | +0.121 |
…] | +0.120 |
alog | +0.115 |
gee | +0.115 |
Neg logit contributions | |
ILCS | -0.141 |
aten | -0.140 |
dayName | -0.138 |
otle | -0.133 |
UGC | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
...] | +0.026 |
Virtue | +0.025 |
…] | +0.024 |
alog | +0.023 |
gee | +0.023 |
Neg logit contributions | |
ILCS | -0.026 |
aten | -0.026 |
dayName | -0.025 |
otle | -0.024 |
UGC | -0.023 |
Token | Pro |
Token ID | 1041 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ILCS | +0.067 |
aten | +0.067 |
dayName | +0.066 |
otle | +0.063 |
UGC | +0.060 |
Neg logit contributions | |
...] | -0.061 |
Virtue | -0.058 |
…] | -0.057 |
alog | -0.055 |
gee | -0.055 |
Token | ctor |
Token ID | 2715 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ILCS | +0.137 |
aten | +0.135 |
dayName | +0.134 |
otle | +0.128 |
UGC | +0.122 |
Neg logit contributions | |
...] | -0.128 |
Virtue | -0.121 |
…] | -0.120 |
alog | -0.115 |
gee | -0.115 |
Token | & |
Token ID | 1222 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ILCS | +0.363 |
aten | +0.358 |
dayName | +0.354 |
otle | +0.330 |
UGC | +0.309 |
Neg logit contributions | |
...] | -0.607 |
Virtue | -0.582 |
…] | -0.576 |
alog | -0.558 |
gee | -0.558 |
Token | Gamble |
Token ID | 49318 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ILCS | +1.460 |
aten | +1.423 |
dayName | +1.399 |
otle | +1.359 |
UGC | +1.274 |
Neg logit contributions | |
...] | -1.677 |
Virtue | -1.600 |
…] | -1.574 |
gee | -1.511 |
alog | -1.507 |
Token | , |
Token ID | 11 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
ILCS | +0.099 |
aten | +0.097 |
dayName | +0.096 |
otle | +0.092 |
UGC | +0.087 |
Neg logit contributions | |
...] | -0.098 |
Virtue | -0.093 |
…] | -0.092 |
alog | -0.088 |
gee | -0.088 |
Token | Coca |
Token ID | 29803 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ILCS | +0.039 |
aten | +0.039 |
dayName | +0.038 |
otle | +0.036 |
UGC | +0.035 |
Neg logit contributions | |
...] | -0.038 |
Virtue | -0.036 |
…] | -0.035 |
alog | -0.034 |
gee | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
ILCS | +0.137 |
aten | +0.135 |
dayName | +0.134 |
otle | +0.128 |
UGC | +0.121 |
Neg logit contributions | |
...] | -0.136 |
Virtue | -0.129 |
…] | -0.128 |
alog | -0.122 |
gee | -0.122 |
Token | Cola |
Token ID | 28635 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ILCS | +0.559 |
aten | +0.551 |
dayName | +0.545 |
otle | +0.518 |
UGC | +0.487 |
Neg logit contributions | |
...] | -0.721 |
Virtue | -0.685 |
…] | -0.681 |
Fu | -0.659 |
alog | -0.656 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ILCS | +0.016 |
aten | +0.016 |
dayName | +0.015 |
otle | +0.015 |
UGC | +0.014 |
Neg logit contributions | |
...] | -0.012 |
Virtue | -0.012 |
…] | -0.011 |
alog | -0.011 |
gee | -0.011 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
...] | +0.160 |
Virtue | +0.151 |
…] | +0.150 |
alog | +0.144 |
gee | +0.143 |
Neg logit contributions | |
ILCS | -0.164 |
aten | -0.162 |
dayName | -0.160 |
otle | -0.153 |
UGC | -0.145 |
Token | : |
Token ID | 25 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
...] | +0.050 |
Virtue | +0.048 |
…] | +0.047 |
alog | +0.045 |
gee | +0.045 |
Neg logit contributions | |
ILCS | -0.052 |
aten | -0.051 |
dayName | -0.051 |
otle | -0.049 |
UGC | -0.046 |
Token | ' |
Token ID | 705 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
...] | +0.185 |
Virtue | +0.175 |
…] | +0.173 |
alog | +0.166 |
gee | +0.165 |
Neg logit contributions | |
ILCS | -0.194 |
aten | -0.192 |
dayName | -0.190 |
otle | -0.182 |
UGC | -0.173 |
Token | I |
Token ID | 40 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
...] | +0.626 |
Virtue | +0.592 |
…] | +0.582 |
alog | +0.562 |
gee | +0.555 |
Neg logit contributions | |
ILCS | -0.705 |
aten | -0.701 |
dayName | -0.695 |
otle | -0.664 |
UGC | -0.636 |
Token | fully |
Token ID | 3938 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ILCS | +0.082 |
aten | +0.081 |
dayName | +0.080 |
otle | +0.077 |
UGC | +0.073 |
Neg logit contributions | |
...] | -0.074 |
Virtue | -0.070 |
…] | -0.069 |
alog | -0.066 |
gee | -0.066 |
Token | expect |
Token ID | 1607 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ILCS | +1.543 |
aten | +1.537 |
dayName | +1.512 |
otle | +1.463 |
UGC | +1.379 |
Neg logit contributions | |
...] | -1.510 |
…] | -1.420 |
Virtue | -1.419 |
alog | -1.358 |
Fu | -1.332 |
Token | ' |
Token ID | 6 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
ILCS | +0.364 |
aten | +0.359 |
dayName | +0.358 |
otle | +0.344 |
UGC | +0.329 |
Neg logit contributions | |
...] | -0.226 |
Virtue | -0.210 |
…] | -0.208 |
alog | -0.196 |
gee | -0.195 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ILCS | +0.379 |
aten | +0.370 |
dayName | +0.363 |
otle | +0.339 |
UGC | +0.314 |
Neg logit contributions | |
...] | -0.666 |
Virtue | -0.638 |
…] | -0.636 |
gee | -0.615 |
alog | -0.612 |
Token | treatment |
Token ID | 3513 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ILCS | +1.027 |
aten | +1.014 |
dayName | +1.002 |
otle | +0.954 |
UGC | +0.924 |
Neg logit contributions | |
...] | -0.737 |
Virtue | -0.690 |
…] | -0.684 |
gee | -0.648 |
>] | -0.647 |
Token | by |
Token ID | 416 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
...] | +0.110 |
Virtue | +0.104 |
…] | +0.103 |
alog | +0.098 |
gee | +0.098 |
Neg logit contributions | |
ILCS | -0.121 |
aten | -0.120 |
dayName | -0.119 |
otle | -0.114 |
UGC | -0.108 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
...] | +0.007 |
Virtue | +0.007 |
…] | +0.006 |
alog | +0.006 |
gee | +0.006 |
Neg logit contributions | |
ILCS | -0.009 |
aten | -0.009 |
dayName | -0.009 |
otle | -0.008 |
UGC | -0.008 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
...] | +0.216 |
Virtue | +0.205 |
…] | +0.203 |
alog | +0.195 |
gee | +0.194 |
Neg logit contributions | |
ILCS | -0.209 |
aten | -0.207 |
dayName | -0.204 |
otle | -0.195 |
UGC | -0.185 |
Token | : |
Token ID | 25 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
...] | +0.041 |
Virtue | +0.039 |
…] | +0.038 |
alog | +0.037 |
gee | +0.036 |
Neg logit contributions | |
ILCS | -0.044 |
aten | -0.044 |
dayName | -0.043 |
otle | -0.041 |
UGC | -0.039 |
Token | ' |
Token ID | 705 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
...] | +0.136 |
Virtue | +0.129 |
…] | +0.127 |
alog | +0.122 |
gee | +0.122 |
Neg logit contributions | |
ILCS | -0.144 |
aten | -0.142 |
dayName | -0.141 |
otle | -0.135 |
UGC | -0.128 |
Token | I |
Token ID | 40 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
...] | +0.822 |
Virtue | +0.781 |
…] | +0.765 |
alog | +0.742 |
�� | +0.734 |
Neg logit contributions | |
ILCS | -0.915 |
aten | -0.906 |
dayName | -0.904 |
otle | -0.859 |
UGC | -0.823 |
Token | fully |
Token ID | 3938 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
...] | +0.146 |
Virtue | +0.138 |
…] | +0.136 |
alog | +0.131 |
gee | +0.130 |
Neg logit contributions | |
ILCS | -0.160 |
aten | -0.158 |
dayName | -0.157 |
otle | -0.150 |
UGC | -0.143 |
Token | expect |
Token ID | 1607 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ILCS | +1.531 |
aten | +1.528 |
dayName | +1.503 |
otle | +1.454 |
UGC | +1.369 |
Neg logit contributions | |
...] | -1.491 |
…] | -1.399 |
Virtue | -1.399 |
alog | -1.338 |
Fu | -1.316 |
Token | ' |
Token ID | 6 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ILCS | +0.288 |
aten | +0.285 |
dayName | +0.284 |
otle | +0.273 |
UGC | +0.261 |
Neg logit contributions | |
...] | -0.169 |
Virtue | -0.157 |
…] | -0.156 |
alog | -0.147 |
gee | -0.147 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ILCS | +0.280 |
aten | +0.275 |
dayName | +0.271 |
otle | +0.254 |
UGC | +0.236 |
Neg logit contributions | |
...] | -0.450 |
Virtue | -0.431 |
…] | -0.429 |
gee | -0.415 |
alog | -0.414 |
Token | treatment |
Token ID | 3513 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ILCS | +0.881 |
aten | +0.870 |
dayName | +0.858 |
otle | +0.816 |
UGC | +0.788 |
Neg logit contributions | |
...] | -0.735 |
Virtue | -0.689 |
…] | -0.685 |
gee | -0.654 |
>] | -0.652 |
Token | by |
Token ID | 416 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ILCS | +0.117 |
aten | +0.116 |
dayName | +0.115 |
otle | +0.110 |
UGC | +0.105 |
Neg logit contributions | |
...] | -0.104 |
Virtue | -0.099 |
…] | -0.098 |
alog | -0.093 |
gee | -0.093 |
Token | Non |
Token ID | 15419 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ILCS | +0.708 |
aten | +0.696 |
dayName | +0.694 |
otle | +0.659 |
UGC | +0.613 |
Neg logit contributions | |
...] | -0.887 |
Virtue | -0.840 |
…] | -0.839 |
gee | -0.807 |
Fu | -0.805 |
Token | Commercial |
Token ID | 48401 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
ILCS | +1.015 |
aten | +1.003 |
dayName | +0.999 |
otle | +0.959 |
UGC | +0.908 |
Neg logit contributions | |
...] | -0.818 |
Virtue | -0.768 |
…] | -0.764 |
gee | -0.726 |
Fu | -0.725 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ILCS | +0.559 |
aten | +0.553 |
dayName | +0.552 |
otle | +0.527 |
UGC | +0.498 |
Neg logit contributions | |
...] | -0.538 |
Virtue | -0.510 |
…] | -0.505 |
gee | -0.484 |
alog | -0.483 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ILCS | +0.433 |
aten | +0.432 |
dayName | +0.428 |
otle | +0.409 |
UGC | +0.388 |
Neg logit contributions | |
...] | -0.406 |
Virtue | -0.384 |
…] | -0.381 |
gee | -0.363 |
Fu | -0.363 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
...] | +0.136 |
Virtue | +0.128 |
…] | +0.126 |
alog | +0.120 |
gee | +0.119 |
Neg logit contributions | |
ILCS | -0.191 |
aten | -0.189 |
dayName | -0.187 |
otle | -0.180 |
UGC | -0.173 |
Token | Un |
Token ID | 791 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ILCS | +0.327 |
aten | +0.322 |
dayName | +0.321 |
otle | +0.301 |
UGC | +0.278 |
Neg logit contributions | |
...] | -0.509 |
Virtue | -0.488 |
…] | -0.483 |
gee | -0.467 |
alog | -0.466 |
Token | ported |
Token ID | 9213 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ILCS | +0.746 |
dayName | +0.721 |
aten | +0.717 |
otle | +0.667 |
UGC | +0.577 |
Neg logit contributions | |
...] | -2.242 |
Virtue | -2.168 |
…] | -2.164 |
gee | -2.106 |
alog | -2.096 |
Token | License |
Token ID | 13789 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ILCS | +1.023 |
dayName | +1.020 |
aten | +1.018 |
otle | +0.973 |
UGC | +0.935 |
Neg logit contributions | |
...] | -0.620 |
Virtue | -0.577 |
…] | -0.570 |
alog | -0.537 |
gee | -0.537 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ILCS | +0.079 |
aten | +0.078 |
dayName | +0.077 |
otle | +0.074 |
UGC | +0.070 |
Neg logit contributions | |
...] | -0.073 |
Virtue | -0.069 |
…] | -0.068 |
alog | -0.065 |
gee | -0.065 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
ILCS | +0.210 |
aten | +0.208 |
dayName | +0.206 |
otle | +0.197 |
UGC | +0.187 |
Neg logit contributions | |
...] | -0.193 |
Virtue | -0.183 |
…] | -0.181 |
alog | -0.173 |
gee | -0.172 |
Token | Image |
Token ID | 5159 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
...] | +0.048 |
Virtue | +0.045 |
…] | +0.045 |
alog | +0.043 |
gee | +0.043 |
Neg logit contributions | |
ILCS | -0.054 |
aten | -0.053 |
dayName | -0.053 |
otle | -0.051 |
UGC | -0.048 |
Token | a |
Token ID | 64 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ILCS | +0.349 |
aten | +0.342 |
dayName | +0.341 |
otle | +0.324 |
UGC | +0.309 |
Neg logit contributions | |
...] | -0.350 |
Virtue | -0.331 |
…] | -0.329 |
alog | -0.317 |
gee | -0.315 |
Token | commissioned |
Token ID | 20462 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ILCS | +0.439 |
aten | +0.433 |
dayName | +0.431 |
otle | +0.412 |
UGC | +0.393 |
Neg logit contributions | |
...] | -0.374 |
Virtue | -0.354 |
…] | -0.349 |
alog | -0.334 |
gee | -0.333 |
Token | aud |
Token ID | 2709 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
...] | +0.026 |
Virtue | +0.025 |
…] | +0.024 |
alog | +0.023 |
gee | +0.023 |
Neg logit contributions | |
ILCS | -0.028 |
aten | -0.028 |
dayName | -0.028 |
otle | -0.026 |
UGC | -0.025 |
Token | itors |
Token ID | 6742 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ILCS | +0.324 |
aten | +0.319 |
dayName | +0.317 |
otle | +0.302 |
UGC | +0.286 |
Neg logit contributions | |
...] | -0.358 |
Virtue | -0.340 |
…] | -0.336 |
alog | -0.325 |
gee | -0.324 |
Token | Ernst |
Token ID | 38129 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
...] | +0.136 |
Virtue | +0.128 |
…] | +0.127 |
alog | +0.122 |
gee | +0.121 |
Neg logit contributions | |
ILCS | -0.146 |
aten | -0.144 |
dayName | -0.143 |
otle | -0.137 |
UGC | -0.130 |
Token | & |
Token ID | 1222 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ILCS | +0.238 |
aten | +0.234 |
dayName | +0.232 |
otle | +0.219 |
UGC | +0.207 |
Neg logit contributions | |
...] | -0.309 |
Virtue | -0.295 |
…] | -0.292 |
alog | -0.282 |
gee | -0.281 |
Token | Young |
Token ID | 6960 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ILCS | +1.909 |
dayName | +1.902 |
aten | +1.886 |
otle | +1.817 |
UGC | +1.732 |
Neg logit contributions | |
...] | -1.087 |
Virtue | -1.015 |
…] | -0.997 |
alog | -0.937 |
Lump | -0.935 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
...] | +0.127 |
Virtue | +0.120 |
…] | +0.119 |
alog | +0.114 |
gee | +0.114 |
Neg logit contributions | |
ILCS | -0.132 |
aten | -0.130 |
dayName | -0.129 |
otle | -0.123 |
UGC | -0.117 |
Token | look |
Token ID | 804 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
...] | +0.287 |
Virtue | +0.269 |
…] | +0.266 |
alog | +0.253 |
gee | +0.252 |
Neg logit contributions | |
ILCS | -0.391 |
aten | -0.387 |
dayName | -0.384 |
otle | -0.370 |
UGC | -0.352 |
Token | into |
Token ID | 656 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
...] | +0.060 |
Virtue | +0.057 |
…] | +0.056 |
alog | +0.054 |
gee | +0.054 |
Neg logit contributions | |
ILCS | -0.070 |
aten | -0.069 |
dayName | -0.069 |
otle | -0.066 |
UGC | -0.063 |
Token | allegations |
Token ID | 7636 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
...] | +0.152 |
Virtue | +0.143 |
…] | +0.142 |
alog | +0.136 |
gee | +0.136 |
Neg logit contributions | |
ILCS | -0.162 |
aten | -0.160 |
dayName | -0.158 |
otle | -0.152 |
UGC | -0.144 |
Token | " |
Token ID | 366 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
...] | +0.355 |
Virtue | +0.337 |
…] | +0.334 |
alog | +0.322 |
gee | +0.322 |
Neg logit contributions | |
ILCS | -0.327 |
aten | -0.323 |
dayName | -0.319 |
otle | -0.305 |
UGC | -0.289 |
Token | 25 |
Token ID | 1495 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
...] | +0.453 |
Virtue | +0.427 |
…] | +0.421 |
alog | +0.406 |
gee | +0.403 |
Neg logit contributions | |
ILCS | -0.554 |
aten | -0.549 |
dayName | -0.542 |
otle | -0.522 |
UGC | -0.499 |
Token | 56 |
Token ID | 3980 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ILCS | +0.162 |
aten | +0.160 |
dayName | +0.159 |
otle | +0.152 |
UGC | +0.144 |
Neg logit contributions | |
...] | -0.150 |
Virtue | -0.141 |
…] | -0.140 |
alog | -0.134 |
gee | -0.134 |
Token | "] |
Token ID | 8973 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ILCS | +0.766 |
aten | +0.760 |
dayName | +0.756 |
otle | +0.733 |
UGC | +0.704 |
Neg logit contributions | |
...] | -0.322 |
Virtue | -0.292 |
…] | -0.289 |
alog | -0.265 |
gee | -0.265 |
Token | [ |
Token ID | 685 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ILCS | +0.262 |
aten | +0.260 |
dayName | +0.256 |
otle | +0.245 |
UGC | +0.232 |
Neg logit contributions | |
...] | -0.255 |
Virtue | -0.241 |
…] | -0.239 |
alog | -0.228 |
Fu | -0.228 |
Token | Black |
Token ID | 9915 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ILCS | +0.498 |
aten | +0.487 |
dayName | +0.482 |
otle | +0.454 |
utor | +0.423 |
Neg logit contributions | |
...] | -0.663 |
Virtue | -0.629 |
…] | -0.627 |
Fu | -0.603 |
alog | -0.601 |
Token | E |
Token ID | 36 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
...] | +0.773 |
Virtue | +0.729 |
…] | +0.709 |
alog | +0.678 |
Lump | +0.674 |
Neg logit contributions | |
ILCS | -1.385 |
aten | -1.369 |
dayName | -1.344 |
otle | -1.312 |
UGC | -1.272 |
Token | lo |
Token ID | 5439 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
...] | +0.266 |
Virtue | +0.255 |
…] | +0.253 |
alog | +0.245 |
gee | +0.244 |
Neg logit contributions | |
ILCS | -0.157 |
aten | -0.154 |
dayName | -0.152 |
otle | -0.143 |
UGC | -0.133 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ILCS | +0.105 |
aten | +0.104 |
dayName | +0.103 |
otle | +0.098 |
UGC | +0.093 |
Neg logit contributions | |
...] | -0.111 |
Virtue | -0.105 |
…] | -0.104 |
alog | -0.100 |
gee | -0.099 |
Token | 25 |
Token ID | 1495 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ILCS | +0.156 |
aten | +0.154 |
dayName | +0.153 |
otle | +0.146 |
UGC | +0.140 |
Neg logit contributions | |
...] | -0.123 |
Virtue | -0.115 |
…] | -0.114 |
alog | -0.108 |
gee | -0.108 |
Token | 67 |
Token ID | 3134 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ILCS | +0.023 |
aten | +0.023 |
dayName | +0.022 |
otle | +0.021 |
UGC | +0.020 |
Neg logit contributions | |
...] | -0.023 |
Virtue | -0.022 |
…] | -0.021 |
alog | -0.020 |
gee | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ILCS | +1.007 |
aten | +0.995 |
dayName | +0.994 |
otle | +0.943 |
UGC | +0.899 |
Neg logit contributions | |
...] | -0.900 |
Virtue | -0.853 |
…] | -0.844 |
alog | -0.801 |
Fu | -0.800 |
Token | news |
Token ID | 1705 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
ILCS | +0.123 |
aten | +0.121 |
dayName | +0.120 |
otle | +0.114 |
UGC | +0.107 |
Neg logit contributions | |
...] | -0.146 |
Virtue | -0.139 |
…] | -0.138 |
alog | -0.133 |
gee | -0.132 |
Token | organisation |
Token ID | 12684 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ILCS | +0.641 |
aten | +0.633 |
dayName | +0.630 |
otle | +0.598 |
UGC | +0.573 |
Neg logit contributions | |
...] | -0.674 |
…] | -0.636 |
Virtue | -0.634 |
alog | -0.614 |
gee | -0.608 |
Token | it |
Token ID | 340 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
...] | +0.147 |
Virtue | +0.140 |
…] | +0.138 |
alog | +0.133 |
gee | +0.132 |
Neg logit contributions | |
ILCS | -0.145 |
aten | -0.143 |
dayName | -0.142 |
otle | -0.136 |
UGC | -0.129 |
Token | offers |
Token ID | 4394 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
...] | +0.686 |
Virtue | +0.652 |
…] | +0.641 |
Fu | +0.613 |
>] | +0.612 |
Neg logit contributions | |
ILCS | -0.745 |
aten | -0.741 |
dayName | -0.731 |
otle | -0.701 |
UGC | -0.665 |
Token | an |
Token ID | 281 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
...] | +0.674 |
Virtue | +0.636 |
…] | +0.628 |
alog | +0.601 |
gee | +0.594 |
Neg logit contributions | |
ILCS | -0.893 |
aten | -0.889 |
dayName | -0.881 |
otle | -0.848 |
UGC | -0.808 |
Token | alternative |
Token ID | 5559 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
...] | +1.079 |
Virtue | +1.023 |
…] | +1.014 |
Fu | +0.963 |
alog | +0.961 |
Neg logit contributions | |
ILCS | -1.161 |
aten | -1.146 |
dayName | -1.134 |
otle | -1.084 |
UGC | -1.039 |
Token | to |
Token ID | 284 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
...] | +0.827 |
Virtue | +0.782 |
…] | +0.778 |
alog | +0.746 |
gee | +0.738 |
Neg logit contributions | |
ILCS | -0.838 |
aten | -0.829 |
dayName | -0.823 |
otle | -0.783 |
UGC | -0.749 |
Token | The |
Token ID | 383 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
...] | +0.570 |
Virtue | +0.542 |
…] | +0.538 |
alog | +0.518 |
gee | +0.516 |
Neg logit contributions | |
ILCS | -0.452 |
aten | -0.448 |
dayName | -0.443 |
otle | -0.420 |
UGC | -0.395 |
Token | Ad |
Token ID | 1215 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
...] | +0.331 |
Virtue | +0.314 |
…] | +0.310 |
alog | +0.297 |
gee | +0.296 |
Neg logit contributions | |
ILCS | -0.349 |
aten | -0.345 |
dayName | -0.340 |
otle | -0.326 |
UGC | -0.309 |
Token | vertis |
Token ID | 3346 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
...] | +0.293 |
Virtue | +0.282 |
…] | +0.280 |
alog | +0.272 |
gee | +0.271 |
Neg logit contributions | |
ILCS | -0.121 |
aten | -0.119 |
dayName | -0.117 |
otle | -0.108 |
UGC | -0.098 |
Token | report |
Token ID | 989 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
...] | +0.301 |
Virtue | +0.283 |
…] | +0.281 |
alog | +0.270 |
gee | +0.268 |
Neg logit contributions | |
ILCS | -0.330 |
aten | -0.326 |
dayName | -0.324 |
otle | -0.310 |
UGC | -0.295 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ILCS | +0.156 |
aten | +0.154 |
dayName | +0.153 |
otle | +0.147 |
UGC | +0.141 |
Neg logit contributions | |
...] | -0.111 |
Virtue | -0.104 |
…] | -0.103 |
alog | -0.098 |
gee | -0.097 |
Token | airline |
Token ID | 18091 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
...] | +0.900 |
Virtue | +0.844 |
…] | +0.837 |
alog | +0.813 |
Fu | +0.801 |
Neg logit contributions | |
ILCS | -0.997 |
dayName | -0.980 |
aten | -0.979 |
otle | -0.937 |
UGC | -0.891 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
...] | +0.392 |
Virtue | +0.371 |
…] | +0.368 |
alog | +0.354 |
gee | +0.352 |
Neg logit contributions | |
ILCS | -0.380 |
aten | -0.378 |
dayName | -0.374 |
otle | -0.357 |
UGC | -0.338 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
...] | +0.763 |
Virtue | +0.705 |
…] | +0.703 |
gee | +0.670 |
Fu | +0.669 |
Neg logit contributions | |
ILCS | -1.014 |
aten | -1.012 |
dayName | -1.004 |
otle | -0.965 |
UGC | -0.921 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
...] | +1.628 |
Virtue | +1.587 |
…] | +1.538 |
gee | +1.523 |
�� | +1.507 |
Neg logit contributions | |
ILCS | -1.534 |
aten | -1.524 |
dayName | -1.522 |
otle | -1.466 |
UGC | -1.390 |
Token | open |
Token ID | 1280 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
...] | +1.002 |
Virtue | +0.950 |
…] | +0.936 |
Fu | +0.905 |
alog | +0.897 |
Neg logit contributions | |
aten | -1.067 |
ILCS | -1.064 |
dayName | -1.056 |
otle | -1.022 |
UGC | -0.972 |
Token | flights |
Token ID | 13956 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
...] | +1.397 |
…] | +1.309 |
Virtue | +1.308 |
�� | +1.254 |
alog | +1.253 |
Neg logit contributions | |
aten | -1.528 |
ILCS | -1.504 |
dayName | -1.500 |
otle | -1.480 |
UGC | -1.382 |
Token | to |
Token ID | 284 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
...] | +0.379 |
Virtue | +0.360 |
…] | +0.355 |
alog | +0.342 |
gee | +0.341 |
Neg logit contributions | |
ILCS | -0.401 |
aten | -0.397 |
dayName | -0.396 |
otle | -0.377 |
UGC | -0.357 |
Token | US |
Token ID | 1294 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
...] | +0.214 |
Virtue | +0.201 |
…] | +0.199 |
alog | +0.190 |
gee | +0.189 |
Neg logit contributions | |
ILCS | -0.266 |
aten | -0.264 |
dayName | -0.261 |
otle | -0.251 |
UGC | -0.239 |
Token | on |
Token ID | 319 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
...] | +0.940 |
Virtue | +0.881 |
…] | +0.880 |
alog | +0.849 |
gee | +0.840 |
Neg logit contributions | |
dayName | -0.873 |
ILCS | -0.872 |
aten | -0.862 |
otle | -0.820 |
UGC | -0.775 |
Token | Console |
Token ID | 24371 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
...] | +0.403 |
Virtue | +0.378 |
…] | +0.375 |
alog | +0.358 |
gee | +0.356 |
Neg logit contributions | |
ILCS | -0.502 |
aten | -0.497 |
dayName | -0.493 |
otle | -0.472 |
UGC | -0.451 |
Token | service |
Token ID | 2139 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
...] | +0.200 |
Virtue | +0.185 |
…] | +0.183 |
alog | +0.173 |
gee | +0.171 |
Neg logit contributions | |
ILCS | -0.340 |
aten | -0.338 |
dayName | -0.335 |
otle | -0.322 |
UGC | -0.310 |
Token | , |
Token ID | 11 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
ILCS | +0.134 |
aten | +0.133 |
dayName | +0.132 |
otle | +0.126 |
UGC | +0.119 |
Neg logit contributions | |
...] | -0.131 |
Virtue | -0.124 |
…] | -0.123 |
alog | -0.117 |
gee | -0.117 |
Token | which |
Token ID | 543 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
...] | +0.729 |
Virtue | +0.693 |
…] | +0.690 |
gee | +0.664 |
alog | +0.664 |
Neg logit contributions | |
ILCS | -0.671 |
aten | -0.664 |
dayName | -0.656 |
otle | -0.624 |
UGC | -0.596 |
Token | brings |
Token ID | 6774 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ILCS | +0.087 |
aten | +0.086 |
dayName | +0.086 |
otle | +0.082 |
UGC | +0.078 |
Neg logit contributions | |
...] | -0.076 |
Virtue | -0.072 |
…] | -0.071 |
alog | -0.068 |
gee | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
...] | +0.304 |
Virtue | +0.288 |
…] | +0.284 |
alog | +0.273 |
gee | +0.272 |
Neg logit contributions | |
ILCS | -0.343 |
aten | -0.340 |
dayName | -0.336 |
otle | -0.322 |
UGC | -0.307 |
Token | great |
Token ID | 1049 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
...] | +1.114 |
Virtue | +1.049 |
…] | +1.046 |
>] | +1.008 |
alog | +0.999 |
Neg logit contributions | |
ILCS | -1.208 |
aten | -1.198 |
dayName | -1.180 |
otle | -1.132 |
UGC | -1.085 |
Token | games |
Token ID | 1830 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
...] | +0.576 |
Virtue | +0.545 |
…] | +0.541 |
alog | +0.519 |
gee | +0.515 |
Neg logit contributions | |
ILCS | -0.561 |
aten | -0.556 |
dayName | -0.552 |
otle | -0.524 |
UGC | -0.499 |
Token | created |
Token ID | 2727 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
ILCS | +0.217 |
aten | +0.215 |
dayName | +0.212 |
otle | +0.204 |
UGC | +0.193 |
Neg logit contributions | |
...] | -0.198 |
Virtue | -0.187 |
…] | -0.185 |
alog | -0.177 |
gee | -0.177 |
Token | for |
Token ID | 329 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
...] | +0.066 |
Virtue | +0.062 |
…] | +0.062 |
alog | +0.059 |
gee | +0.059 |
Neg logit contributions | |
ILCS | -0.072 |
aten | -0.071 |
dayName | -0.070 |
otle | -0.067 |
UGC | -0.064 |
Token | consoles |
Token ID | 22629 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
...] | +1.563 |
Virtue | +1.484 |
…] | +1.471 |
gee | +1.421 |
alog | +1.404 |
Neg logit contributions | |
aten | -1.636 |
ILCS | -1.632 |
dayName | -1.608 |
otle | -1.515 |
UGC | -1.456 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
...] | +0.312 |
Virtue | +0.296 |
…] | +0.293 |
alog | +0.281 |
gee | +0.280 |
Neg logit contributions | |
ILCS | -0.330 |
aten | -0.327 |
dayName | -0.323 |
otle | -0.309 |
UGC | -0.293 |
Token | this |
Token ID | 428 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
...] | +1.126 |
…] | +1.065 |
Virtue | +1.059 |
alog | +1.015 |
gee | +1.007 |
Neg logit contributions | |
ILCS | -1.066 |
aten | -1.058 |
dayName | -1.045 |
otle | -0.996 |
UGC | -0.950 |
Token | title |
Token ID | 3670 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
...] | +0.362 |
Virtue | +0.343 |
…] | +0.338 |
gee | +0.321 |
alog | +0.321 |
Neg logit contributions | |
ILCS | -0.457 |
aten | -0.454 |
dayName | -0.449 |
otle | -0.431 |
UGC | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ILCS | +0.155 |
aten | +0.153 |
dayName | +0.151 |
otle | +0.145 |
UGC | +0.138 |
Neg logit contributions | |
...] | -0.146 |
Virtue | -0.138 |
…] | -0.137 |
alog | -0.131 |
gee | -0.131 |
Token | See |
Token ID | 4091 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
...] | +0.348 |
Virtue | +0.326 |
…] | +0.324 |
alog | +0.308 |
gee | +0.306 |
Neg logit contributions | |
ILCS | -0.467 |
aten | -0.460 |
dayName | -0.457 |
otle | -0.438 |
UGC | -0.422 |
Token | more |
Token ID | 517 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
...] | +0.084 |
Virtue | +0.079 |
…] | +0.078 |
alog | +0.075 |
gee | +0.074 |
Neg logit contributions | |
ILCS | -0.105 |
aten | -0.104 |
dayName | -0.103 |
otle | -0.099 |
UGC | -0.095 |
Token | Virtual |
Token ID | 15595 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
...] | +0.653 |
Virtue | +0.586 |
…] | +0.579 |
alog | +0.558 |
gee | +0.549 |
Neg logit contributions | |
ILCS | -1.705 |
aten | -1.703 |
dayName | -1.687 |
otle | -1.630 |
UGC | -1.571 |
Token | Console |
Token ID | 24371 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
...] | +0.394 |
Virtue | +0.371 |
…] | +0.367 |
alog | +0.352 |
gee | +0.349 |
Neg logit contributions | |
ILCS | -0.500 |
aten | -0.493 |
dayName | -0.489 |
otle | -0.469 |
UGC | -0.448 |
Token | games |
Token ID | 1830 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
...] | +0.498 |
Virtue | +0.468 |
…] | +0.466 |
alog | +0.448 |
gee | +0.445 |
Neg logit contributions | |
ILCS | -0.483 |
aten | -0.478 |
dayName | -0.474 |
otle | -0.451 |
UGC | -0.428 |
Token | for |
Token ID | 329 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ILCS | +0.214 |
aten | +0.211 |
dayName | +0.209 |
otle | +0.200 |
UGC | +0.190 |
Neg logit contributions | |
...] | -0.192 |
Virtue | -0.182 |
…] | -0.180 |
alog | -0.172 |
gee | -0.171 |
Token | Wii |
Token ID | 16591 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
...] | +0.350 |
Virtue | +0.322 |
…] | +0.319 |
alog | +0.300 |
gee | +0.298 |
Neg logit contributions | |
ILCS | -0.677 |
aten | -0.672 |
dayName | -0.666 |
otle | -0.643 |
UGC | -0.618 |
Token | infrastructure |
Token ID | 6884 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
...] | +0.096 |
Virtue | +0.091 |
…] | +0.090 |
alog | +0.086 |
gee | +0.086 |
Neg logit contributions | |
ILCS | -0.099 |
aten | -0.098 |
dayName | -0.097 |
otle | -0.093 |
UGC | -0.088 |
Token | improvements |
Token ID | 8561 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ILCS | +0.237 |
aten | +0.235 |
dayName | +0.233 |
otle | +0.224 |
UGC | +0.214 |
Neg logit contributions | |
...] | -0.176 |
Virtue | -0.165 |
…] | -0.163 |
alog | -0.155 |
gee | -0.154 |
Token | or |
Token ID | 393 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ILCS | +0.171 |
aten | +0.169 |
dayName | +0.167 |
otle | +0.160 |
UGC | +0.152 |
Neg logit contributions | |
...] | -0.167 |
Virtue | -0.158 |
…] | -0.157 |
alog | -0.150 |
gee | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ILCS | +0.136 |
aten | +0.134 |
dayName | +0.133 |
otle | +0.127 |
UGC | +0.121 |
Neg logit contributions | |
...] | -0.127 |
Virtue | -0.120 |
…] | -0.119 |
alog | -0.114 |
gee | -0.113 |
Token | creation |
Token ID | 6282 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ILCS | +0.079 |
aten | +0.078 |
dayName | +0.077 |
otle | +0.074 |
UGC | +0.070 |
Neg logit contributions | |
...] | -0.073 |
Virtue | -0.069 |
…] | -0.068 |
alog | -0.065 |
gee | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
...] | +0.016 |
Virtue | +0.015 |
…] | +0.015 |
alog | +0.015 |
gee | +0.014 |
Neg logit contributions | |
ILCS | -0.018 |
aten | -0.017 |
dayName | -0.017 |
otle | -0.017 |
UGC | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
...] | +0.039 |
Virtue | +0.037 |
…] | +0.037 |
alog | +0.035 |
gee | +0.035 |
Neg logit contributions | |
ILCS | -0.042 |
aten | -0.041 |
dayName | -0.041 |
otle | -0.039 |
UGC | -0.037 |
Token | minimum |
Token ID | 5288 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
...] | +0.108 |
Virtue | +0.102 |
…] | +0.101 |
alog | +0.097 |
gee | +0.096 |
Neg logit contributions | |
ILCS | -0.113 |
aten | -0.112 |
dayName | -0.111 |
otle | -0.106 |
UGC | -0.100 |
Token | number |
Token ID | 1271 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ILCS | +0.208 |
aten | +0.206 |
dayName | +0.204 |
otle | +0.196 |
UGC | +0.187 |
Neg logit contributions | |
...] | -0.172 |
Virtue | -0.162 |
…] | -0.160 |
alog | -0.153 |
gee | -0.152 |
Token | of |
Token ID | 286 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
...] | +0.069 |
Virtue | +0.065 |
…] | +0.064 |
alog | +0.062 |
gee | +0.061 |
Neg logit contributions | |
ILCS | -0.075 |
aten | -0.074 |
dayName | -0.073 |
otle | -0.070 |
UGC | -0.067 |
Token | jobs |
Token ID | 3946 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
...] | +0.053 |
Virtue | +0.050 |
…] | +0.050 |
alog | +0.048 |
gee | +0.047 |
Neg logit contributions | |
ILCS | -0.056 |
aten | -0.056 |
dayName | -0.055 |
otle | -0.053 |
UGC | -0.050 |
Token | 're |
Token ID | 821 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
...] | +0.020 |
Virtue | +0.019 |
…] | +0.018 |
alog | +0.018 |
gee | +0.018 |
Neg logit contributions | |
ILCS | -0.019 |
aten | -0.019 |
dayName | -0.019 |
otle | -0.018 |
UGC | -0.017 |
Token | like |
Token ID | 588 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
...] | +0.259 |
Virtue | +0.245 |
…] | +0.242 |
alog | +0.232 |
gee | +0.232 |
Neg logit contributions | |
ILCS | -0.271 |
aten | -0.268 |
dayName | -0.265 |
otle | -0.253 |
UGC | -0.240 |
Token | , |
Token ID | 11 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
...] | +0.156 |
Virtue | +0.148 |
…] | +0.146 |
alog | +0.140 |
gee | +0.140 |
Neg logit contributions | |
ILCS | -0.163 |
aten | -0.161 |
dayName | -0.159 |
otle | -0.152 |
UGC | -0.144 |
Token | " |
Token ID | 366 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
...] | +0.063 |
Virtue | +0.059 |
…] | +0.058 |
alog | +0.056 |
gee | +0.056 |
Neg logit contributions | |
ILCS | -0.071 |
aten | -0.070 |
dayName | -0.070 |
otle | -0.067 |
UGC | -0.064 |
Token | OK |
Token ID | 11380 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
...] | +0.107 |
Virtue | +0.101 |
…] | +0.100 |
alog | +0.095 |
gee | +0.095 |
Neg logit contributions | |
ILCS | -0.122 |
aten | -0.120 |
dayName | -0.119 |
otle | -0.114 |
UGC | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
...] | +0.143 |
Virtue | +0.136 |
…] | +0.134 |
alog | +0.129 |
gee | +0.129 |
Neg logit contributions | |
ILCS | -0.144 |
aten | -0.143 |
dayName | -0.141 |
otle | -0.135 |
UGC | -0.128 |
Token | cool |
Token ID | 3608 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
...] | +0.269 |
Virtue | +0.255 |
…] | +0.252 |
alog | +0.242 |
gee | +0.241 |
Neg logit contributions | |
ILCS | -0.285 |
aten | -0.282 |
dayName | -0.278 |
otle | -0.267 |
UGC | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
...] | +0.037 |
Virtue | +0.035 |
…] | +0.035 |
alog | +0.033 |
gee | +0.033 |
Neg logit contributions | |
ILCS | -0.038 |
aten | -0.037 |
dayName | -0.037 |
otle | -0.035 |
UGC | -0.033 |
Token | but |
Token ID | 475 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
...] | +0.069 |
Virtue | +0.065 |
…] | +0.065 |
alog | +0.062 |
gee | +0.062 |
Neg logit contributions | |
ILCS | -0.071 |
aten | -0.070 |
dayName | -0.070 |
otle | -0.067 |
UGC | -0.063 |
Token | you |
Token ID | 345 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
...] | +0.205 |
Virtue | +0.194 |
…] | +0.192 |
alog | +0.184 |
gee | +0.184 |
Neg logit contributions | |
ILCS | -0.222 |
aten | -0.220 |
dayName | -0.217 |
otle | -0.208 |
UGC | -0.198 |
Token | 're |
Token ID | 821 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
...] | +0.293 |
Virtue | +0.278 |
…] | +0.275 |
alog | +0.264 |
gee | +0.263 |
Neg logit contributions | |
ILCS | -0.293 |
aten | -0.290 |
dayName | -0.287 |
otle | -0.275 |
UGC | -0.260 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
...] | +0.026 |
Virtue | +0.025 |
…] | +0.025 |
alog | +0.024 |
gee | +0.023 |
Neg logit contributions | |
ILCS | -0.029 |
aten | -0.029 |
dayName | -0.028 |
otle | -0.027 |
UGC | -0.026 |
Token | market |
Token ID | 1910 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ILCS | +0.014 |
aten | +0.014 |
dayName | +0.014 |
otle | +0.013 |
UGC | +0.012 |
Neg logit contributions | |
...] | -0.013 |
Virtue | -0.012 |
…] | -0.012 |
alog | -0.012 |
gee | -0.012 |
Token | when |
Token ID | 618 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ILCS | +0.183 |
aten | +0.181 |
dayName | +0.179 |
otle | +0.172 |
UGC | +0.163 |
Neg logit contributions | |
...] | -0.168 |
Virtue | -0.159 |
…] | -0.158 |
alog | -0.151 |
gee | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ILCS | +0.181 |
aten | +0.179 |
dayName | +0.178 |
otle | +0.170 |
UGC | +0.162 |
Neg logit contributions | |
...] | -0.166 |
Virtue | -0.157 |
…] | -0.155 |
alog | -0.148 |
gee | -0.148 |
Token | money |
Token ID | 1637 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ILCS | +0.383 |
aten | +0.378 |
dayName | +0.375 |
otle | +0.360 |
UGC | +0.342 |
Neg logit contributions | |
...] | -0.341 |
Virtue | -0.323 |
…] | -0.319 |
alog | -0.305 |
gee | -0.304 |
Token | 's |
Token ID | 338 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
...] | +0.268 |
Virtue | +0.254 |
…] | +0.252 |
alog | +0.242 |
gee | +0.241 |
Neg logit contributions | |
ILCS | -0.253 |
aten | -0.251 |
dayName | -0.248 |
otle | -0.237 |
UGC | -0.223 |
Token | flowing |
Token ID | 17609 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
...] | +0.055 |
Virtue | +0.052 |
…] | +0.051 |
alog | +0.049 |
gee | +0.049 |
Neg logit contributions | |
ILCS | -0.060 |
aten | -0.059 |
dayName | -0.058 |
otle | -0.056 |
UGC | -0.053 |
Token | more |
Token ID | 517 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
...] | +0.182 |
Virtue | +0.173 |
…] | +0.171 |
alog | +0.164 |
gee | +0.163 |
Neg logit contributions | |
ILCS | -0.196 |
aten | -0.194 |
dayName | -0.192 |
otle | -0.184 |
UGC | -0.175 |
Token | freely |
Token ID | 12748 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ILCS | +0.175 |
aten | +0.173 |
dayName | +0.171 |
otle | +0.165 |
UGC | +0.158 |
Neg logit contributions | |
...] | -0.125 |
Virtue | -0.117 |
…] | -0.115 |
alog | -0.110 |
gee | -0.109 |
Token | ? |
Token ID | 30 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
...] | +0.086 |
Virtue | +0.081 |
…] | +0.080 |
alog | +0.077 |
gee | +0.077 |
Neg logit contributions | |
ILCS | -0.085 |
aten | -0.084 |
dayName | -0.083 |
otle | -0.080 |
UGC | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
...] | +0.001 |
Virtue | +0.001 |
…] | +0.001 |
alog | +0.001 |
gee | +0.001 |
Neg logit contributions | |
ILCS | -0.001 |
aten | -0.001 |
dayName | -0.001 |
otle | -0.001 |
UGC | -0.001 |
Token | racial |
Token ID | 8425 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
...] | +0.121 |
Virtue | +0.114 |
…] | +0.113 |
alog | +0.108 |
gee | +0.108 |
Neg logit contributions | |
ILCS | -0.139 |
aten | -0.138 |
dayName | -0.136 |
otle | -0.131 |
UGC | -0.124 |
Token | lines |
Token ID | 3951 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
...] | +0.109 |
Virtue | +0.105 |
…] | +0.104 |
alog | +0.101 |
gee | +0.100 |
Neg logit contributions | |
ILCS | -0.067 |
aten | -0.066 |
dayName | -0.065 |
otle | -0.061 |
UGC | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ILCS | +0.204 |
aten | +0.202 |
dayName | +0.200 |
otle | +0.191 |
UGC | +0.182 |
Neg logit contributions | |
...] | -0.198 |
Virtue | -0.187 |
…] | -0.185 |
alog | -0.177 |
gee | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
...] | +0.027 |
Virtue | +0.026 |
…] | +0.025 |
alog | +0.024 |
gee | +0.024 |
Neg logit contributions | |
ILCS | -0.027 |
aten | -0.027 |
dayName | -0.027 |
otle | -0.026 |
UGC | -0.024 |
Token | C |
Token ID | 34 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ILCS | +0.061 |
aten | +0.060 |
dayName | +0.060 |
otle | +0.057 |
UGC | +0.054 |
Neg logit contributions | |
...] | -0.056 |
Virtue | -0.053 |
…] | -0.053 |
alog | -0.050 |
gee | -0.050 |
Token | ultural |
Token ID | 8596 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ILCS | +0.266 |
aten | +0.263 |
dayName | +0.261 |
otle | +0.250 |
UGC | +0.239 |
Neg logit contributions | |
...] | -0.209 |
Virtue | -0.196 |
…] | -0.194 |
alog | -0.186 |
gee | -0.184 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ILCS | +0.083 |
aten | +0.082 |
dayName | +0.082 |
otle | +0.078 |
UGC | +0.075 |
Neg logit contributions | |
...] | -0.071 |
Virtue | -0.067 |
…] | -0.066 |
alog | -0.064 |
gee | -0.063 |
Token | educational |
Token ID | 9856 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
...] | +0.199 |
Virtue | +0.186 |
…] | +0.184 |
alog | +0.174 |
gee | +0.174 |
Neg logit contributions | |
ILCS | -0.293 |
aten | -0.290 |
dayName | -0.288 |
otle | -0.277 |
UGC | -0.265 |
Token | representations |
Token ID | 24612 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ILCS | +0.060 |
aten | +0.059 |
dayName | +0.059 |
otle | +0.056 |
UGC | +0.053 |
Neg logit contributions | |
...] | -0.054 |
Virtue | -0.051 |
…] | -0.050 |
alog | -0.048 |
gee | -0.048 |
Token | continue |
Token ID | 2555 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
...] | +0.195 |
Virtue | +0.184 |
…] | +0.182 |
alog | +0.175 |
gee | +0.174 |
Neg logit contributions | |
ILCS | -0.207 |
aten | -0.205 |
dayName | -0.203 |
otle | -0.194 |
UGC | -0.184 |
Token | to |
Token ID | 284 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
...] | +0.075 |
Virtue | +0.071 |
…] | +0.070 |
alog | +0.067 |
gee | +0.067 |
Neg logit contributions | |
ILCS | -0.081 |
aten | -0.080 |
dayName | -0.079 |
otle | -0.076 |
UGC | -0.072 |
Token | consistently |
Token ID | 9835 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
...] | +0.140 |
Virtue | +0.132 |
…] | +0.131 |
alog | +0.125 |
gee | +0.125 |
Neg logit contributions | |
ILCS | -0.154 |
aten | -0.152 |
dayName | -0.151 |
otle | -0.144 |
UGC | -0.137 |
Token | polled |
Token ID | 37698 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ILCS | +0.175 |
aten | +0.173 |
dayName | +0.171 |
otle | +0.164 |
UGC | +0.156 |
Neg logit contributions | |
...] | -0.157 |
Virtue | -0.148 |
…] | -0.146 |
alog | -0.140 |
gee | -0.140 |
Token | under |
Token ID | 739 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ILCS | +0.403 |
aten | +0.398 |
dayName | +0.395 |
otle | +0.377 |
UGC | +0.359 |
Neg logit contributions | |
...] | -0.390 |
Virtue | -0.370 |
…] | -0.366 |
alog | -0.350 |
gee | -0.349 |
Token | 50 |
Token ID | 2026 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
...] | +0.268 |
Virtue | +0.254 |
…] | +0.251 |
alog | +0.240 |
gee | +0.240 |
Neg logit contributions | |
ILCS | -0.291 |
aten | -0.288 |
dayName | -0.285 |
otle | -0.273 |
UGC | -0.259 |
Token | percent |
Token ID | 1411 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ILCS | +0.352 |
aten | +0.349 |
dayName | +0.346 |
otle | +0.331 |
UGC | +0.314 |
Neg logit contributions | |
...] | -0.327 |
Virtue | -0.309 |
…] | -0.306 |
alog | -0.292 |
Fu | -0.291 |
Token | , |
Token ID | 11 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ILCS | +0.348 |
aten | +0.344 |
dayName | +0.342 |
otle | +0.326 |
UGC | +0.310 |
Neg logit contributions | |
...] | -0.350 |
Virtue | -0.332 |
…] | -0.328 |
alog | -0.315 |
Fu | -0.313 |
Token | is |
Token ID | 318 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ILCS | +0.026 |
aten | +0.026 |
dayName | +0.026 |
otle | +0.025 |
UGC | +0.024 |
Neg logit contributions | |
...] | -0.024 |
Virtue | -0.023 |
…] | -0.023 |
alog | -0.022 |
gee | -0.022 |
Token | one |
Token ID | 530 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
...] | +0.226 |
Virtue | +0.213 |
…] | +0.211 |
alog | +0.202 |
gee | +0.202 |
Neg logit contributions | |
ILCS | -0.243 |
aten | -0.241 |
dayName | -0.238 |
otle | -0.228 |
UGC | -0.217 |
Token | of |
Token ID | 286 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
...] | +0.185 |
Virtue | +0.175 |
…] | +0.173 |
alog | +0.165 |
gee | +0.165 |
Neg logit contributions | |
ILCS | -0.198 |
aten | -0.196 |
dayName | -0.194 |
otle | -0.185 |
UGC | -0.176 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
...] | +0.045 |
Virtue | +0.043 |
…] | +0.042 |
alog | +0.040 |
gee | +0.040 |
Neg logit contributions | |
ILCS | -0.049 |
aten | -0.049 |
dayName | -0.048 |
otle | -0.046 |
UGC | -0.044 |
Token | sleep |
Token ID | 3993 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
ILCS | +0.049 |
aten | +0.049 |
dayName | +0.048 |
otle | +0.046 |
UGC | +0.044 |
Neg logit contributions | |
...] | -0.040 |
Virtue | -0.038 |
…] | -0.038 |
alog | -0.036 |
gee | -0.036 |
Token | enemies |
Token ID | 5775 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ILCS | +0.275 |
aten | +0.273 |
dayName | +0.270 |
otle | +0.258 |
UGC | +0.245 |
Neg logit contributions | |
...] | -0.270 |
Virtue | -0.256 |
…] | -0.253 |
alog | -0.243 |
gee | -0.242 |
Token | � |
Token ID | 447 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ILCS | +0.198 |
aten | +0.196 |
dayName | +0.194 |
otle | +0.187 |
UGC | +0.179 |
Neg logit contributions | |
...] | -0.145 |
Virtue | -0.136 |
…] | -0.134 |
alog | -0.127 |
gee | -0.127 |
Token | � |
Token ID | 247 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ILCS | +0.275 |
aten | +0.272 |
dayName | +0.268 |
otle | +0.257 |
UGC | +0.244 |
Neg logit contributions | |
...] | -0.266 |
Virtue | -0.252 |
…] | -0.250 |
alog | -0.239 |
gee | -0.239 |
Token | powers |
Token ID | 5635 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ILCS | +0.226 |
aten | +0.224 |
dayName | +0.222 |
otle | +0.212 |
UGC | +0.202 |
Neg logit contributions | |
...] | -0.207 |
Virtue | -0.196 |
…] | -0.194 |
alog | -0.185 |
gee | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ILCS | +0.266 |
aten | +0.263 |
dayName | +0.261 |
otle | +0.249 |
UGC | +0.237 |
Neg logit contributions | |
...] | -0.251 |
Virtue | -0.238 |
…] | -0.235 |
alog | -0.226 |
gee | -0.225 |
Token | but |
Token ID | 475 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ILCS | +0.235 |
aten | +0.233 |
dayName | +0.231 |
otle | +0.221 |
UGC | +0.210 |
Neg logit contributions | |
...] | -0.212 |
Virtue | -0.200 |
…] | -0.198 |
alog | -0.190 |
gee | -0.189 |
Token | they |
Token ID | 484 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
ILCS | +0.130 |
aten | +0.128 |
dayName | +0.127 |
otle | +0.121 |
UGC | +0.115 |
Neg logit contributions | |
...] | -0.119 |
Virtue | -0.112 |
…] | -0.111 |
alog | -0.106 |
gee | -0.106 |
Token | can |
Token ID | 460 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
ILCS | +0.007 |
aten | +0.007 |
dayName | +0.006 |
otle | +0.006 |
UGC | +0.006 |
Neg logit contributions | |
...] | -0.006 |
Virtue | -0.006 |
…] | -0.006 |
alog | -0.006 |
gee | -0.006 |
Token | also |
Token ID | 635 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ILCS | +0.076 |
aten | +0.075 |
dayName | +0.075 |
otle | +0.072 |
UGC | +0.068 |
Neg logit contributions | |
...] | -0.062 |
Virtue | -0.059 |
…] | -0.058 |
alog | -0.055 |
gee | -0.055 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ILCS | +0.092 |
aten | +0.091 |
dayName | +0.090 |
otle | +0.086 |
UGC | +0.082 |
Neg logit contributions | |
...] | -0.085 |
Virtue | -0.080 |
…] | -0.080 |
alog | -0.076 |
gee | -0.076 |
Token | situation |
Token ID | 3074 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ILCS | +0.203 |
aten | +0.201 |
dayName | +0.199 |
otle | +0.190 |
UGC | +0.181 |
Neg logit contributions | |
...] | -0.187 |
Virtue | -0.177 |
…] | -0.175 |
alog | -0.168 |
gee | -0.167 |
Token | Woman |
Token ID | 14381 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
...] | +0.065 |
Virtue | +0.060 |
…] | +0.059 |
alog | +0.056 |
gee | +0.055 |
Neg logit contributions | |
ILCS | -0.121 |
aten | -0.120 |
dayName | -0.119 |
otle | -0.115 |
UGC | -0.110 |
Token | should |
Token ID | 815 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
...] | +0.197 |
Virtue | +0.186 |
…] | +0.184 |
alog | +0.176 |
gee | +0.176 |
Neg logit contributions | |
ILCS | -0.222 |
aten | -0.219 |
dayName | -0.217 |
otle | -0.208 |
UGC | -0.198 |
Token | be |
Token ID | 307 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
...] | +0.131 |
Virtue | +0.125 |
…] | +0.123 |
alog | +0.118 |
gee | +0.118 |
Neg logit contributions | |
ILCS | -0.135 |
aten | -0.133 |
dayName | -0.132 |
otle | -0.126 |
UGC | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
...] | +0.144 |
Virtue | +0.137 |
…] | +0.135 |
alog | +0.130 |
gee | +0.129 |
Neg logit contributions | |
ILCS | -0.151 |
aten | -0.149 |
dayName | -0.148 |
otle | -0.142 |
UGC | -0.134 |
Token | Because |
Token ID | 4362 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
...] | +0.029 |
Virtue | +0.027 |
…] | +0.027 |
alog | +0.026 |
gee | +0.026 |
Neg logit contributions | |
ILCS | -0.028 |
aten | -0.028 |
dayName | -0.028 |
otle | -0.027 |
UGC | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
...] | +0.232 |
Virtue | +0.219 |
…] | +0.217 |
alog | +0.209 |
gee | +0.208 |
Neg logit contributions | |
ILCS | -0.230 |
aten | -0.227 |
dayName | -0.224 |
otle | -0.215 |
UGC | -0.203 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ILCS | +0.242 |
aten | +0.239 |
dayName | +0.237 |
otle | +0.226 |
UGC | +0.215 |
Neg logit contributions | |
...] | -0.233 |
Virtue | -0.221 |
…] | -0.219 |
alog | -0.210 |
gee | -0.209 |
Token | T |
Token ID | 309 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
...] | +0.210 |
Virtue | +0.198 |
…] | +0.196 |
alog | +0.188 |
gee | +0.187 |
Neg logit contributions | |
ILCS | -0.230 |
aten | -0.228 |
dayName | -0.225 |
otle | -0.216 |
UGC | -0.205 |
Token | & |
Token ID | 5 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
...] | +0.235 |
Virtue | +0.223 |
…] | +0.221 |
alog | +0.212 |
gee | +0.211 |
Neg logit contributions | |
ILCS | -0.224 |
aten | -0.222 |
dayName | -0.219 |
otle | -0.210 |
UGC | -0.199 |
Token | A |
Token ID | 32 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
...] | +0.370 |
Virtue | +0.349 |
…] | +0.345 |
alog | +0.331 |
gee | +0.329 |
Neg logit contributions | |
ILCS | -0.429 |
aten | -0.424 |
dayName | -0.419 |
otle | -0.404 |
UGC | -0.384 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
...] | +0.153 |
Virtue | +0.145 |
…] | +0.143 |
alog | +0.137 |
gee | +0.137 |
Neg logit contributions | |
ILCS | -0.168 |
aten | -0.166 |
dayName | -0.164 |
otle | -0.157 |
UGC | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
...] | +0.208 |
Virtue | +0.197 |
…] | +0.195 |
alog | +0.187 |
gee | +0.186 |
Neg logit contributions | |
ILCS | -0.210 |
aten | -0.208 |
dayName | -0.205 |
otle | -0.197 |
UGC | -0.186 |
Token | Other |
Token ID | 3819 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
...] | +0.072 |
Virtue | +0.068 |
…] | +0.067 |
alog | +0.065 |
gee | +0.064 |
Neg logit contributions | |
ILCS | -0.077 |
aten | -0.076 |
dayName | -0.076 |
otle | -0.072 |
UGC | -0.069 |
Token | times |
Token ID | 1661 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
ILCS | +0.244 |
aten | +0.241 |
dayName | +0.239 |
otle | +0.227 |
UGC | +0.216 |
Neg logit contributions | |
...] | -0.253 |
Virtue | -0.240 |
…] | -0.237 |
alog | -0.228 |
gee | -0.227 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
...] | +0.064 |
Virtue | +0.061 |
…] | +0.060 |
alog | +0.058 |
gee | +0.058 |
Neg logit contributions | |
ILCS | -0.067 |
aten | -0.067 |
dayName | -0.066 |
otle | -0.063 |
UGC | -0.060 |
Token | I |
Token ID | 314 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
...] | +0.125 |
Virtue | +0.119 |
…] | +0.117 |
alog | +0.113 |
gee | +0.112 |
Neg logit contributions | |
ILCS | -0.133 |
aten | -0.131 |
dayName | -0.130 |
otle | -0.124 |
UGC | -0.118 |
Token | 'd |
Token ID | 1549 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ILCS | +0.205 |
aten | +0.202 |
dayName | +0.200 |
otle | +0.190 |
UGC | +0.181 |
Neg logit contributions | |
...] | -0.220 |
Virtue | -0.208 |
…] | -0.206 |
alog | -0.198 |
gee | -0.198 |
Token | go |
Token ID | 467 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ILCS | +0.112 |
aten | +0.111 |
dayName | +0.110 |
otle | +0.105 |
UGC | +0.100 |
Neg logit contributions | |
...] | -0.105 |
Virtue | -0.099 |
…] | -0.098 |
alog | -0.094 |
gee | -0.093 |
Token | some |
Token ID | 617 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ILCS | +0.119 |
aten | +0.118 |
dayName | +0.117 |
otle | +0.112 |
UGC | +0.107 |
Neg logit contributions | |
...] | -0.111 |
Virtue | -0.105 |
…] | -0.104 |
alog | -0.099 |
gee | -0.099 |
Token | place |
Token ID | 5372 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
...] | +0.299 |
Virtue | +0.287 |
…] | +0.285 |
alog | +0.275 |
gee | +0.275 |
Neg logit contributions | |
ILCS | -0.185 |
aten | -0.182 |
dayName | -0.179 |
otle | -0.169 |
UGC | -0.157 |
Token | and |
Token ID | 290 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
...] | +0.346 |
Virtue | +0.328 |
…] | +0.325 |
alog | +0.312 |
gee | +0.312 |
Neg logit contributions | |
ILCS | -0.335 |
aten | -0.331 |
dayName | -0.327 |
otle | -0.313 |
UGC | -0.295 |
Token | masturb |
Token ID | 22938 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ILCS | +0.068 |
aten | +0.067 |
dayName | +0.066 |
otle | +0.063 |
UGC | +0.060 |
Neg logit contributions | |
...] | -0.062 |
Virtue | -0.059 |
…] | -0.058 |
alog | -0.056 |
gee | -0.056 |
Token | then |
Token ID | 788 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
...] | +0.230 |
Virtue | +0.218 |
…] | +0.215 |
alog | +0.206 |
gee | +0.206 |
Neg logit contributions | |
ILCS | -0.251 |
aten | -0.248 |
dayName | -0.246 |
otle | -0.236 |
UGC | -0.224 |
Token | people |
Token ID | 661 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
...] | +0.253 |
Virtue | +0.239 |
…] | +0.237 |
alog | +0.227 |
gee | +0.227 |
Neg logit contributions | |
ILCS | -0.259 |
aten | -0.256 |
dayName | -0.253 |
otle | -0.243 |
UGC | -0.230 |
Token | came |
Token ID | 1625 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
ILCS | +0.066 |
aten | +0.065 |
dayName | +0.065 |
otle | +0.062 |
UGC | +0.059 |
Neg logit contributions | |
...] | -0.061 |
Virtue | -0.058 |
…] | -0.057 |
alog | -0.055 |
gee | -0.055 |
Token | up |
Token ID | 510 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
...] | +0.505 |
Virtue | +0.478 |
…] | +0.470 |
alog | +0.452 |
gee | +0.451 |
Neg logit contributions | |
ILCS | -0.585 |
aten | -0.580 |
dayName | -0.572 |
otle | -0.552 |
UGC | -0.521 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
...] | +0.115 |
Virtue | +0.108 |
…] | +0.107 |
alog | +0.103 |
gee | +0.103 |
Neg logit contributions | |
ILCS | -0.120 |
aten | -0.118 |
dayName | -0.117 |
otle | -0.112 |
UGC | -0.106 |
Token | I |
Token ID | 314 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
...] | +0.245 |
Virtue | +0.231 |
…] | +0.229 |
alog | +0.220 |
gee | +0.219 |
Neg logit contributions | |
ILCS | -0.256 |
aten | -0.253 |
dayName | -0.250 |
otle | -0.240 |
UGC | -0.228 |
Token | got |
Token ID | 1392 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ILCS | +0.117 |
aten | +0.116 |
dayName | +0.115 |
otle | +0.110 |
UGC | +0.105 |
Neg logit contributions | |
...] | -0.105 |
Virtue | -0.099 |
…] | -0.098 |
alog | -0.094 |
gee | -0.093 |
Token | into |
Token ID | 656 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
...] | +0.090 |
Virtue | +0.085 |
…] | +0.084 |
alog | +0.081 |
gee | +0.081 |
Neg logit contributions | |
ILCS | -0.098 |
aten | -0.097 |
dayName | -0.096 |
otle | -0.092 |
UGC | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
...] | +0.230 |
Virtue | +0.217 |
…] | +0.215 |
alog | +0.206 |
gee | +0.206 |
Neg logit contributions | |
ILCS | -0.253 |
aten | -0.250 |
dayName | -0.247 |
otle | -0.237 |
UGC | -0.225 |
Token | position |
Token ID | 2292 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
...] | +0.053 |
Virtue | +0.050 |
…] | +0.050 |
alog | +0.048 |
gee | +0.048 |
Neg logit contributions | |
ILCS | -0.057 |
aten | -0.056 |
dayName | -0.055 |
otle | -0.053 |
UGC | -0.050 |
Token | where |
Token ID | 810 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
...] | +0.184 |
Virtue | +0.174 |
…] | +0.172 |
alog | +0.165 |
gee | +0.165 |
Neg logit contributions | |
ILCS | -0.197 |
aten | -0.195 |
dayName | -0.193 |
otle | -0.185 |
UGC | -0.175 |
Token | it |
Token ID | 340 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ILCS | +0.296 |
aten | +0.292 |
dayName | +0.290 |
otle | +0.277 |
UGC | +0.263 |
Neg logit contributions | |
...] | -0.291 |
Virtue | -0.276 |
…] | -0.274 |
alog | -0.261 |
gee | -0.261 |
Token | comes |
Token ID | 2058 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
...] | +0.208 |
Virtue | +0.199 |
…] | +0.197 |
alog | +0.190 |
gee | +0.190 |
Neg logit contributions | |
ILCS | -0.152 |
aten | -0.151 |
dayName | -0.149 |
otle | -0.141 |
UGC | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ILCS | +0.224 |
aten | +0.221 |
dayName | +0.219 |
otle | +0.209 |
UGC | +0.199 |
Neg logit contributions | |
...] | -0.203 |
Virtue | -0.192 |
…] | -0.190 |
alog | -0.181 |
gee | -0.181 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ILCS | +0.091 |
aten | +0.090 |
dayName | +0.089 |
otle | +0.085 |
UGC | +0.080 |
Neg logit contributions | |
...] | -0.090 |
Virtue | -0.085 |
…] | -0.084 |
alog | -0.081 |
gee | -0.081 |
Token | food |
Token ID | 2057 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
...] | +0.125 |
Virtue | +0.119 |
…] | +0.117 |
alog | +0.112 |
gee | +0.112 |
Neg logit contributions | |
ILCS | -0.132 |
aten | -0.131 |
dayName | -0.129 |
otle | -0.124 |
UGC | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ILCS | +0.011 |
aten | +0.011 |
dayName | +0.011 |
otle | +0.010 |
UGC | +0.010 |
Neg logit contributions | |
...] | -0.010 |
Virtue | -0.010 |
…] | -0.010 |
alog | -0.009 |
gee | -0.009 |
Token | � |
Token ID | 564 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ILCS | +0.173 |
aten | +0.171 |
dayName | +0.170 |
otle | +0.162 |
UGC | +0.154 |
Neg logit contributions | |
...] | -0.166 |
Virtue | -0.157 |
…] | -0.156 |
alog | -0.149 |
gee | -0.149 |
Token | � |
Token ID | 250 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
...] | +0.094 |
Virtue | +0.088 |
…] | +0.087 |
alog | +0.083 |
gee | +0.083 |
Neg logit contributions | |
ILCS | -0.111 |
aten | -0.109 |
dayName | -0.108 |
otle | -0.104 |
UGC | -0.099 |
Token | So |
Token ID | 2396 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
ILCS | +0.070 |
aten | +0.069 |
dayName | +0.069 |
otle | +0.066 |
UGC | +0.062 |
Neg logit contributions | |
...] | -0.062 |
Virtue | -0.058 |
…] | -0.058 |
alog | -0.055 |
gee | -0.055 |
Token | when |
Token ID | 618 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
...] | +0.001 |
Virtue | +0.001 |
…] | +0.001 |
alog | +0.001 |
gee | +0.001 |
Neg logit contributions | |
ILCS | -0.001 |
aten | -0.001 |
dayName | -0.001 |
otle | -0.001 |
UGC | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ILCS | +0.231 |
aten | +0.228 |
dayName | +0.227 |
otle | +0.216 |
UGC | +0.206 |
Neg logit contributions | |
...] | -0.215 |
Virtue | -0.203 |
…] | -0.201 |
alog | -0.193 |
gee | -0.192 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ILCS | +0.798 |
dayName | +0.788 |
aten | +0.788 |
otle | +0.750 |
ENTS | +0.710 |
Neg logit contributions | |
...] | -0.733 |
Virtue | -0.702 |
…] | -0.688 |
gee | -0.665 |
alog | -0.665 |
Token | here |
Token ID | 994 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ILCS | +0.125 |
aten | +0.123 |
dayName | +0.122 |
otle | +0.115 |
UGC | +0.109 |
Neg logit contributions | |
...] | -0.146 |
Virtue | -0.139 |
…] | -0.137 |
alog | -0.132 |
gee | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ILCS | +0.426 |
aten | +0.422 |
dayName | +0.418 |
otle | +0.399 |
UGC | +0.380 |
Neg logit contributions | |
...] | -0.395 |
Virtue | -0.374 |
…] | -0.370 |
gee | -0.352 |
alog | -0.352 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ILCS | +0.494 |
aten | +0.488 |
dayName | +0.485 |
otle | +0.462 |
UGC | +0.438 |
Neg logit contributions | |
...] | -0.463 |
Virtue | -0.443 |
…] | -0.434 |
gee | -0.416 |
alog | -0.414 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
...] | +0.020 |
Virtue | +0.019 |
…] | +0.018 |
alog | +0.018 |
gee | +0.018 |
Neg logit contributions | |
ILCS | -0.020 |
aten | -0.020 |
dayName | -0.020 |
otle | -0.019 |
UGC | -0.018 |
Token | Read |
Token ID | 5569 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ILCS | +0.931 |
aten | +0.919 |
dayName | +0.915 |
otle | +0.880 |
utor | +0.839 |
Neg logit contributions | |
...] | -0.557 |
Virtue | -0.519 |
…] | -0.514 |
gee | -0.483 |
Fu | -0.483 |
Token | more |
Token ID | 517 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
ILCS | +1.552 |
aten | +1.517 |
dayName | +1.516 |
otle | +1.441 |
UGC | +1.380 |
Neg logit contributions | |
...] | -1.070 |
Virtue | -1.037 |
…] | -0.996 |
Lump | -0.949 |
Fu | -0.943 |
Token | by |
Token ID | 416 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ILCS | +0.552 |
aten | +0.544 |
dayName | +0.539 |
otle | +0.515 |
UGC | +0.493 |
Neg logit contributions | |
...] | -0.458 |
Virtue | -0.431 |
…] | -0.427 |
gee | -0.402 |
Fu | -0.402 |
Token | Justin |
Token ID | 10799 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ILCS | +0.354 |
aten | +0.350 |
dayName | +0.348 |
otle | +0.327 |
UGC | +0.311 |
Neg logit contributions | |
...] | -0.411 |
Virtue | -0.391 |
…] | -0.388 |
gee | -0.370 |
alog | -0.370 |
Token | R |
Token ID | 371 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
...] | +0.237 |
Virtue | +0.223 |
…] | +0.221 |
alog | +0.211 |
gee | +0.211 |
Neg logit contributions | |
ILCS | -0.270 |
aten | -0.267 |
dayName | -0.264 |
otle | -0.254 |
UGC | -0.241 |
Token | aim |
Token ID | 1385 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
...] | +0.109 |
Virtue | +0.103 |
…] | +0.102 |
alog | +0.098 |
gee | +0.098 |
Neg logit contributions | |
ILCS | -0.111 |
aten | -0.110 |
dayName | -0.109 |
otle | -0.104 |
UGC | -0.099 |
Token | Mind |
Token ID | 10175 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ILCS | +0.425 |
aten | +0.419 |
dayName | +0.417 |
otle | +0.399 |
UGC | +0.381 |
Neg logit contributions | |
...] | -0.363 |
Virtue | -0.344 |
…] | -0.338 |
alog | -0.324 |
gee | -0.322 |
Token | y |
Token ID | 88 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ILCS | +0.118 |
aten | +0.116 |
dayName | +0.115 |
otle | +0.108 |
UGC | +0.101 |
Neg logit contributions | |
...] | -0.191 |
Virtue | -0.183 |
…] | -0.181 |
alog | -0.176 |
gee | -0.175 |
Token | Project |
Token ID | 4935 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
...] | +0.473 |
Virtue | +0.444 |
…] | +0.443 |
Fu | +0.422 |
alog | +0.422 |
Neg logit contributions | |
ILCS | -0.518 |
aten | -0.510 |
dayName | -0.503 |
otle | -0.484 |
ENTS | -0.459 |
Token | Fox |
Token ID | 5426 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ILCS | +0.020 |
aten | +0.020 |
dayName | +0.019 |
otle | +0.019 |
UGC | +0.018 |
Neg logit contributions | |
...] | -0.020 |
Virtue | -0.019 |
…] | -0.018 |
alog | -0.018 |
gee | -0.018 |
Token | Julia |
Token ID | 22300 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ILCS | +0.083 |
aten | +0.082 |
dayName | +0.081 |
otle | +0.077 |
UGC | +0.073 |
Neg logit contributions | |
...] | -0.081 |
Virtue | -0.077 |
…] | -0.076 |
alog | -0.073 |
gee | -0.073 |
Token | Louis |
Token ID | 5593 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ILCS | +0.279 |
aten | +0.276 |
dayName | +0.273 |
otle | +0.258 |
UGC | +0.245 |
Neg logit contributions | |
...] | -0.329 |
Virtue | -0.313 |
…] | -0.309 |
alog | -0.299 |
gee | -0.297 |
Token | - |
Token ID | 12 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ILCS | +1.575 |
aten | +1.569 |
dayName | +1.552 |
otle | +1.478 |
UGC | +1.412 |
Neg logit contributions | |
...] | -1.378 |
Virtue | -1.309 |
…] | -1.286 |
alog | -1.243 |
>] | -1.236 |
Token | D |
Token ID | 35 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ILCS | +0.586 |
dayName | +0.578 |
aten | +0.578 |
otle | +0.554 |
UGC | +0.531 |
Neg logit contributions | |
...] | -0.362 |
Virtue | -0.337 |
…] | -0.334 |
Fu | -0.318 |
gee | -0.316 |
Token | rey |
Token ID | 4364 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
...] | +0.225 |
Virtue | +0.215 |
…] | +0.213 |
alog | +0.205 |
gee | +0.205 |
Neg logit contributions | |
ILCS | -0.184 |
aten | -0.182 |
dayName | -0.180 |
otle | -0.171 |
UGC | -0.161 |
Token | f |
Token ID | 69 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
...] | +0.449 |
Virtue | +0.424 |
…] | +0.422 |
gee | +0.405 |
alog | +0.404 |
Neg logit contributions | |
ILCS | -0.413 |
aten | -0.408 |
dayName | -0.403 |
otle | -0.385 |
UGC | -0.363 |
Token | us |
Token ID | 385 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
...] | +0.715 |
Virtue | +0.679 |
…] | +0.674 |
gee | +0.648 |
Fu | +0.645 |
Neg logit contributions | |
ILCS | -0.614 |
aten | -0.610 |
dayName | -0.597 |
otle | -0.571 |
utor | -0.538 |
Token | Non |
Token ID | 15419 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ILCS | +0.708 |
aten | +0.696 |
dayName | +0.694 |
otle | +0.659 |
UGC | +0.613 |
Neg logit contributions | |
...] | -0.887 |
Virtue | -0.840 |
…] | -0.839 |
gee | -0.807 |
Fu | -0.805 |
Token | Commercial |
Token ID | 48401 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
ILCS | +1.015 |
aten | +1.003 |
dayName | +0.999 |
otle | +0.959 |
UGC | +0.908 |
Neg logit contributions | |
...] | -0.818 |
Virtue | -0.768 |
…] | -0.764 |
gee | -0.726 |
Fu | -0.725 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ILCS | +0.559 |
aten | +0.553 |
dayName | +0.552 |
otle | +0.527 |
UGC | +0.498 |
Neg logit contributions | |
...] | -0.538 |
Virtue | -0.510 |
…] | -0.505 |
gee | -0.484 |
alog | -0.483 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ILCS | +0.433 |
aten | +0.432 |
dayName | +0.428 |
otle | +0.409 |
UGC | +0.388 |
Neg logit contributions | |
...] | -0.406 |
Virtue | -0.384 |
…] | -0.381 |
gee | -0.363 |
Fu | -0.363 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
...] | +0.136 |
Virtue | +0.128 |
…] | +0.126 |
alog | +0.120 |
gee | +0.119 |
Neg logit contributions | |
ILCS | -0.191 |
aten | -0.189 |
dayName | -0.187 |
otle | -0.180 |
UGC | -0.173 |
Token | Un |
Token ID | 791 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ILCS | +0.327 |
aten | +0.322 |
dayName | +0.321 |
otle | +0.301 |
UGC | +0.278 |
Neg logit contributions | |
...] | -0.509 |
Virtue | -0.488 |
…] | -0.483 |
gee | -0.467 |
alog | -0.466 |
Token | ported |
Token ID | 9213 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ILCS | +0.746 |
dayName | +0.721 |
aten | +0.717 |
otle | +0.667 |
UGC | +0.577 |
Neg logit contributions | |
...] | -2.242 |
Virtue | -2.168 |
…] | -2.164 |
gee | -2.106 |
alog | -2.096 |
Token | License |
Token ID | 13789 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ILCS | +1.023 |
dayName | +1.020 |
aten | +1.018 |
otle | +0.973 |
UGC | +0.935 |
Neg logit contributions | |
...] | -0.620 |
Virtue | -0.577 |
…] | -0.570 |
alog | -0.537 |
gee | -0.537 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ILCS | +0.079 |
aten | +0.078 |
dayName | +0.077 |
otle | +0.074 |
UGC | +0.070 |
Neg logit contributions | |
...] | -0.073 |
Virtue | -0.069 |
…] | -0.068 |
alog | -0.065 |
gee | -0.065 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
ILCS | +0.210 |
aten | +0.208 |
dayName | +0.206 |
otle | +0.197 |
UGC | +0.187 |
Neg logit contributions | |
...] | -0.193 |
Virtue | -0.183 |
…] | -0.181 |
alog | -0.173 |
gee | -0.172 |
Token | Image |
Token ID | 5159 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
...] | +0.048 |
Virtue | +0.045 |
…] | +0.045 |
alog | +0.043 |
gee | +0.043 |
Neg logit contributions | |
ILCS | -0.054 |
aten | -0.053 |
dayName | -0.053 |
otle | -0.051 |
UGC | -0.048 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ILCS | +0.360 |
aten | +0.353 |
dayName | +0.353 |
otle | +0.334 |
UGC | +0.319 |
Neg logit contributions | |
...] | -0.337 |
Virtue | -0.319 |
…] | -0.315 |
alog | -0.302 |
gee | -0.301 |
Token | J |
Token ID | 449 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
...] | +1.265 |
…] | +1.201 |
Virtue | +1.181 |
>] | +1.150 |
�� | +1.141 |
Neg logit contributions | |
aten | -0.965 |
ILCS | -0.959 |
dayName | -0.927 |
otle | -0.911 |
UGC | -0.837 |
Token | . |
Token ID | 13 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ILCS | +0.891 |
aten | +0.878 |
dayName | +0.874 |
otle | +0.825 |
UGC | +0.795 |
Neg logit contributions | |
...] | -0.781 |
Virtue | -0.741 |
…] | -0.725 |
alog | -0.711 |
gee | -0.708 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
...] | +0.296 |
…] | +0.267 |
Virtue | +0.267 |
alog | +0.248 |
gee | +0.243 |
Neg logit contributions | |
ILCS | -0.730 |
aten | -0.723 |
dayName | -0.716 |
otle | -0.699 |
UGC | -0.671 |
Token | , |
Token ID | 11 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
...] | +0.164 |
Virtue | +0.155 |
…] | +0.154 |
alog | +0.147 |
gee | +0.147 |
Neg logit contributions | |
ILCS | -0.164 |
aten | -0.162 |
dayName | -0.160 |
otle | -0.153 |
UGC | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ILCS | +0.623 |
aten | +0.612 |
dayName | +0.607 |
otle | +0.576 |
UGC | +0.550 |
Neg logit contributions | |
...] | -0.599 |
Virtue | -0.572 |
…] | -0.562 |
gee | -0.538 |
alog | -0.535 |
Token | critical |
Token ID | 4688 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ILCS | +1.530 |
aten | +1.487 |
dayName | +1.486 |
otle | +1.418 |
UGC | +1.361 |
Neg logit contributions | |
...] | -1.033 |
Virtue | -0.982 |
…] | -0.954 |
alog | -0.897 |
gee | -0.890 |
Token | essays |
Token ID | 27126 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
...] | +0.161 |
Virtue | +0.152 |
…] | +0.151 |
alog | +0.144 |
gee | +0.144 |
Neg logit contributions | |
ILCS | -0.182 |
aten | -0.180 |
dayName | -0.179 |
otle | -0.171 |
UGC | -0.163 |
Token | by |
Token ID | 416 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
...] | +0.124 |
Virtue | +0.117 |
…] | +0.116 |
alog | +0.111 |
gee | +0.111 |
Neg logit contributions | |
ILCS | -0.141 |
aten | -0.140 |
dayName | -0.138 |
otle | -0.133 |
UGC | -0.126 |
Token | Scott |
Token ID | 4746 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ILCS | +0.312 |
aten | +0.307 |
dayName | +0.305 |
otle | +0.289 |
UGC | +0.275 |
Neg logit contributions | |
...] | -0.312 |
Virtue | -0.296 |
…] | -0.293 |
gee | -0.281 |
alog | -0.281 |
Token | Ric |
Token ID | 15868 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ILCS | +0.907 |
aten | +0.893 |
dayName | +0.885 |
otle | +0.817 |
UGC | +0.783 |
Neg logit contributions | |
...] | -1.115 |
Virtue | -1.071 |
…] | -1.045 |
alog | -1.018 |
Lump | -1.016 |
Token | � |
Token ID | 250 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
ILCS | +0.119 |
aten | +0.118 |
dayName | +0.117 |
otle | +0.112 |
UGC | +0.106 |
Neg logit contributions | |
...] | -0.117 |
Virtue | -0.111 |
…] | -0.110 |
alog | -0.105 |
gee | -0.105 |
Token | When |
Token ID | 2215 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ILCS | +0.037 |
aten | +0.036 |
dayName | +0.036 |
otle | +0.035 |
UGC | +0.033 |
Neg logit contributions | |
...] | -0.034 |
Virtue | -0.032 |
…] | -0.032 |
alog | -0.031 |
gee | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ILCS | +0.167 |
aten | +0.165 |
dayName | +0.164 |
otle | +0.157 |
UGC | +0.149 |
Neg logit contributions | |
...] | -0.153 |
Virtue | -0.145 |
…] | -0.143 |
alog | -0.137 |
gee | -0.136 |
Token | watch |
Token ID | 2342 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ILCS | +0.140 |
aten | +0.138 |
dayName | +0.137 |
otle | +0.131 |
UGC | +0.124 |
Neg logit contributions | |
...] | -0.141 |
Virtue | -0.133 |
…] | -0.132 |
alog | -0.127 |
gee | -0.126 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
...] | +0.019 |
Virtue | +0.018 |
…] | +0.018 |
alog | +0.017 |
gee | +0.017 |
Neg logit contributions | |
ILCS | -0.021 |
aten | -0.020 |
dayName | -0.020 |
otle | -0.019 |
UGC | -0.018 |
Token | Huckabee |
Token ID | 38253 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ILCS | +0.648 |
aten | +0.642 |
dayName | +0.637 |
otle | +0.604 |
UGC | +0.578 |
Neg logit contributions | |
...] | -0.620 |
Virtue | -0.588 |
…] | -0.581 |
alog | -0.554 |
gee | -0.553 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ILCS | +1.603 |
aten | +1.575 |
dayName | +1.561 |
otle | +1.486 |
UGC | +1.456 |
Neg logit contributions | |
...] | -1.208 |
Virtue | -1.137 |
…] | -1.124 |
gee | -1.066 |
alog | -1.064 |
Token | right |
Token ID | 826 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ILCS | +0.108 |
aten | +0.107 |
dayName | +0.106 |
otle | +0.102 |
UGC | +0.097 |
Neg logit contributions | |
...] | -0.099 |
Virtue | -0.093 |
…] | -0.092 |
alog | -0.088 |
gee | -0.088 |
Token | now |
Token ID | 783 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
...] | +0.189 |
Virtue | +0.176 |
…] | +0.173 |
alog | +0.164 |
gee | +0.163 |
Neg logit contributions | |
ILCS | -0.322 |
aten | -0.319 |
dayName | -0.316 |
otle | -0.305 |
UGC | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ILCS | +0.124 |
aten | +0.122 |
dayName | +0.121 |
otle | +0.116 |
UGC | +0.110 |
Neg logit contributions | |
...] | -0.121 |
Virtue | -0.115 |
…] | -0.114 |
alog | -0.109 |
gee | -0.109 |
Token | you |
Token ID | 345 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
ILCS | +0.158 |
aten | +0.156 |
dayName | +0.155 |
otle | +0.148 |
UGC | +0.141 |
Neg logit contributions | |
...] | -0.152 |
Virtue | -0.144 |
…] | -0.143 |
alog | -0.137 |
gee | -0.136 |