Token | of |
Token ID | 286 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
romy | +0.278 |
apeake | +0.248 |
odan | +0.248 |
inx | +0.240 |
antis | +0.235 |
Neg logit contributions | |
isers | -0.278 |
Agenda | -0.251 |
| -0.246 |
ERA | -0.221 |
palp | -0.210 |
Token | Israel |
Token ID | 2692 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
isers | +0.278 |
Agenda | +0.250 |
| +0.243 |
ERA | +0.219 |
palp | +0.209 |
Neg logit contributions | |
romy | -0.289 |
apeake | -0.258 |
odan | -0.257 |
inx | -0.250 |
antis | -0.245 |
Token | 's |
Token ID | 338 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
isers | +0.815 |
Agenda | +0.738 |
| +0.717 |
ERA | +0.654 |
palp | +0.626 |
Neg logit contributions | |
romy | -0.771 |
apeake | -0.680 |
odan | -0.676 |
inx | -0.658 |
antis | -0.648 |
Token | Daily |
Token ID | 6714 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
isers | +0.520 |
Agenda | +0.461 |
| +0.448 |
ERA | +0.402 |
palp | +0.382 |
Neg logit contributions | |
romy | -0.609 |
odan | -0.547 |
apeake | -0.545 |
inx | -0.529 |
antis | -0.522 |
Token | Edition |
Token ID | 5061 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
isers | +0.462 |
Agenda | +0.413 |
| +0.405 |
ERA | +0.364 |
palp | +0.348 |
Neg logit contributions | |
romy | -0.461 |
odan | -0.412 |
apeake | -0.411 |
inx | -0.399 |
antis | -0.391 |
Token | by |
Token ID | 416 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
isers | +0.170 |
Agenda | +0.154 |
| +0.150 |
ERA | +0.135 |
palp | +0.129 |
Neg logit contributions | |
romy | -0.167 |
apeake | -0.149 |
odan | -0.149 |
inx | -0.144 |
antis | -0.142 |
Token | email |
Token ID | 3053 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
isers | +1.324 |
Agenda | +1.105 |
| +1.005 |
ERA | +0.839 |
palp | +0.759 |
Neg logit contributions | |
romy | -3.317 |
apeake | -3.056 |
odan | -3.022 |
inx | -2.995 |
antis | -2.942 |
Token | and |
Token ID | 290 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
romy | +0.407 |
apeake | +0.363 |
odan | +0.363 |
inx | +0.351 |
antis | +0.344 |
Neg logit contributions | |
isers | -0.409 |
Agenda | -0.369 |
| -0.363 |
ERA | -0.325 |
palp | -0.309 |
Token | never |
Token ID | 1239 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
romy | +0.392 |
apeake | +0.357 |
odan | +0.357 |
inx | +0.348 |
antis | +0.342 |
Neg logit contributions | |
isers | -0.255 |
Agenda | -0.223 |
| -0.218 |
ERA | -0.188 |
palp | -0.176 |
Token | miss |
Token ID | 2051 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
romy | +0.733 |
odan | +0.649 |
apeake | +0.644 |
inx | +0.618 |
antis | +0.613 |
Neg logit contributions | |
isers | -0.854 |
Agenda | -0.773 |
| -0.767 |
ERA | -0.691 |
palp | -0.655 |
Token | our |
Token ID | 674 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
isers | +0.143 |
Agenda | +0.127 |
| +0.124 |
ERA | +0.110 |
palp | +0.104 |
Neg logit contributions | |
romy | -0.180 |
apeake | -0.162 |
odan | -0.162 |
inx | -0.158 |
antis | -0.155 |
Token | CPUs |
Token ID | 32340 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
isers | +0.166 |
Agenda | +0.150 |
| +0.147 |
ERA | +0.133 |
palp | +0.127 |
Neg logit contributions | |
romy | -0.159 |
odan | -0.141 |
apeake | -0.141 |
inx | -0.137 |
antis | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
romy | +0.076 |
apeake | +0.068 |
odan | +0.068 |
inx | +0.065 |
antis | +0.064 |
Neg logit contributions | |
isers | -0.077 |
Agenda | -0.069 |
| -0.068 |
ERA | -0.061 |
palp | -0.058 |
Token | memory |
Token ID | 4088 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
isers | +0.088 |
Agenda | +0.079 |
| +0.078 |
ERA | +0.070 |
palp | +0.067 |
Neg logit contributions | |
romy | -0.087 |
odan | -0.078 |
apeake | -0.077 |
inx | -0.075 |
antis | -0.074 |
Token | ( |
Token ID | 357 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
romy | +0.381 |
apeake | +0.339 |
odan | +0.339 |
inx | +0.328 |
antis | +0.322 |
Neg logit contributions | |
isers | -0.391 |
Agenda | -0.352 |
| -0.346 |
ERA | -0.311 |
palp | -0.295 |
Token | Intel |
Token ID | 24123 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
romy | +0.161 |
apeake | +0.144 |
odan | +0.144 |
inx | +0.139 |
antis | +0.137 |
Neg logit contributions | |
isers | -0.158 |
Agenda | -0.143 |
| -0.140 |
ERA | -0.125 |
palp | -0.119 |
Token | VT |
Token ID | 32751 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
isers | +0.121 |
Agenda | +0.109 |
| +0.107 |
ERA | +0.096 |
palp | +0.092 |
Neg logit contributions | |
romy | -0.118 |
apeake | -0.105 |
odan | -0.104 |
inx | -0.101 |
antis | -0.099 |
Token | - |
Token ID | 12 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
isers | +2.345 |
Agenda | +2.137 |
| +2.049 |
ERA | +1.879 |
palp | +1.818 |
Neg logit contributions | |
romy | -1.972 |
apeake | -1.781 |
odan | -1.777 |
inx | -1.730 |
antis | -1.674 |
Token | x |
Token ID | 87 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
isers | +0.921 |
Agenda | +0.841 |
| +0.809 |
ERA | +0.730 |
palp | +0.696 |
Neg logit contributions | |
romy | -1.039 |
apeake | -0.944 |
odan | -0.938 |
inx | -0.925 |
antis | -0.905 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
isers | +0.413 |
Agenda | +0.376 |
| +0.368 |
ERA | +0.331 |
palp | +0.318 |
Neg logit contributions | |
romy | -0.391 |
odan | -0.348 |
apeake | -0.347 |
inx | -0.338 |
antis | -0.330 |
Token | AMD |
Token ID | 10324 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
isers | +0.060 |
Agenda | +0.054 |
| +0.053 |
ERA | +0.048 |
palp | +0.046 |
Neg logit contributions | |
romy | -0.051 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.043 |
antis | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
isers | +0.425 |
Agenda | +0.381 |
| +0.374 |
ERA | +0.333 |
palp | +0.318 |
Neg logit contributions | |
romy | -0.463 |
apeake | -0.414 |
odan | -0.414 |
inx | -0.402 |
antis | -0.395 |
Token | ials |
Token ID | 8231 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
isers | +0.628 |
Agenda | +0.549 |
| +0.529 |
ERA | +0.461 |
palp | +0.432 |
Neg logit contributions | |
romy | -0.994 |
apeake | -0.912 |
odan | -0.903 |
inx | -0.879 |
antis | -0.870 |
Token | are |
Token ID | 389 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
romy | +0.108 |
apeake | +0.095 |
odan | +0.095 |
inx | +0.092 |
antis | +0.090 |
Neg logit contributions | |
isers | -0.119 |
Agenda | -0.107 |
| -0.105 |
ERA | -0.095 |
palp | -0.091 |
Token | decided |
Token ID | 3066 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
isers | +0.379 |
Agenda | +0.341 |
| +0.335 |
ERA | +0.302 |
palp | +0.288 |
Neg logit contributions | |
romy | -0.363 |
apeake | -0.324 |
odan | -0.323 |
inx | -0.312 |
antis | -0.307 |
Token | by |
Token ID | 416 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
isers | +0.667 |
Agenda | +0.597 |
| +0.583 |
ERA | +0.529 |
palp | +0.503 |
Neg logit contributions | |
romy | -0.632 |
apeake | -0.560 |
odan | -0.558 |
inx | -0.537 |
antis | -0.530 |
Token | its |
Token ID | 663 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
isers | +1.135 |
Agenda | +1.013 |
| +0.999 |
ERA | +0.904 |
palp | +0.876 |
Neg logit contributions | |
romy | -0.946 |
apeake | -0.840 |
odan | -0.836 |
inx | -0.805 |
antis | -0.793 |
Token | Editorial |
Token ID | 39525 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
isers | +0.505 |
Agenda | +0.445 |
| +0.438 |
ERA | +0.390 |
palp | +0.373 |
Neg logit contributions | |
romy | -0.563 |
odan | -0.508 |
apeake | -0.504 |
inx | -0.489 |
antis | -0.482 |
Token | Board |
Token ID | 5926 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
isers | +1.640 |
| +1.367 |
Agenda | +1.328 |
ERA | +1.147 |
palp | +1.130 |
Neg logit contributions | |
romy | -2.611 |
odan | -2.361 |
inx | -2.348 |
apeake | -2.341 |
antis | -2.300 |
Token | , |
Token ID | 11 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
isers | +0.105 |
Agenda | +0.094 |
| +0.092 |
ERA | +0.083 |
palp | +0.079 |
Neg logit contributions | |
romy | -0.104 |
apeake | -0.092 |
odan | -0.092 |
inx | -0.089 |
antis | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
isers | +1.709 |
Agenda | +1.526 |
| +1.475 |
ERA | +1.358 |
palp | +1.303 |
Neg logit contributions | |
romy | -1.435 |
odan | -1.268 |
apeake | -1.265 |
inx | -1.212 |
antis | -1.187 |
Token | dem |
Token ID | 1357 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
isers | +0.818 |
Agenda | +0.733 |
| +0.713 |
ERA | +0.656 |
palp | +0.624 |
Neg logit contributions | |
romy | -0.734 |
apeake | -0.642 |
odan | -0.640 |
inx | -0.616 |
antis | -0.601 |
Token | ographically |
Token ID | 33145 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
isers | +0.062 |
Agenda | +0.056 |
| +0.054 |
ERA | +0.049 |
palp | +0.046 |
Neg logit contributions | |
romy | -0.068 |
odan | -0.060 |
apeake | -0.060 |
inx | -0.059 |
antis | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
romy | +0.024 |
apeake | +0.022 |
odan | +0.022 |
inx | +0.021 |
antis | +0.021 |
Neg logit contributions | |
isers | -0.024 |
Agenda | -0.021 |
| -0.021 |
ERA | -0.019 |
palp | -0.018 |
Token | A |
Token ID | 317 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
romy | +0.105 |
apeake | +0.094 |
odan | +0.094 |
inx | +0.091 |
antis | +0.089 |
Neg logit contributions | |
isers | -0.098 |
Agenda | -0.088 |
| -0.086 |
ERA | -0.077 |
palp | -0.073 |
Token | US |
Token ID | 2937 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
isers | +0.405 |
Agenda | +0.360 |
| +0.349 |
ERA | +0.309 |
palp | +0.294 |
Neg logit contributions | |
romy | -0.516 |
apeake | -0.466 |
odan | -0.465 |
inx | -0.452 |
antis | -0.446 |
Token | 16 |
Token ID | 1467 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
romy | +0.238 |
odan | +0.206 |
apeake | +0.206 |
inx | +0.198 |
antis | +0.194 |
Neg logit contributions | |
isers | -0.337 |
Agenda | -0.308 |
| -0.303 |
ERA | -0.278 |
palp | -0.266 |
Token | Steele |
Token ID | 28549 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
romy | +0.297 |
apeake | +0.264 |
odan | +0.264 |
inx | +0.256 |
antis | +0.251 |
Neg logit contributions | |
isers | -0.300 |
Agenda | -0.270 |
| -0.265 |
ERA | -0.238 |
palp | -0.226 |
Token | Von |
Token ID | 26985 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
isers | +0.116 |
Agenda | +0.108 |
| +0.106 |
ERA | +0.099 |
palp | +0.096 |
Neg logit contributions | |
romy | -0.043 |
apeake | -0.034 |
odan | -0.034 |
inx | -0.032 |
antis | -0.030 |
Token | Hoff |
Token ID | 21890 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
isers | +1.464 |
Agenda | +1.239 |
| +1.166 |
ERA | +0.994 |
palp | +0.968 |
Neg logit contributions | |
romy | -2.678 |
odan | -2.486 |
apeake | -2.442 |
inx | -2.440 |
Polk | -2.393 |
Token | ( |
Token ID | 357 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
isers | +0.315 |
Agenda | +0.283 |
| +0.276 |
ERA | +0.248 |
palp | +0.235 |
Neg logit contributions | |
romy | -0.329 |
odan | -0.295 |
apeake | -0.294 |
inx | -0.287 |
antis | -0.280 |
Token | Team |
Token ID | 15592 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
isers | +0.041 |
Agenda | +0.037 |
| +0.036 |
ERA | +0.033 |
palp | +0.031 |
Neg logit contributions | |
romy | -0.040 |
apeake | -0.035 |
odan | -0.035 |
inx | -0.034 |
antis | -0.034 |
Token | Chip |
Token ID | 17869 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
isers | +0.426 |
Agenda | +0.388 |
| +0.381 |
ERA | +0.348 |
palp | +0.336 |
Neg logit contributions | |
romy | -0.300 |
apeake | -0.262 |
odan | -0.261 |
inx | -0.250 |
antis | -0.245 |
Token | otle |
Token ID | 23556 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
romy | +0.395 |
apeake | +0.361 |
odan | +0.361 |
inx | +0.351 |
antis | +0.347 |
Neg logit contributions | |
isers | -0.242 |
Agenda | -0.210 |
| -0.205 |
ERA | -0.176 |
palp | -0.164 |
Token | valuable |
Token ID | 8119 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
romy | +0.197 |
apeake | +0.178 |
odan | +0.178 |
inx | +0.173 |
antis | +0.170 |
Neg logit contributions | |
isers | -0.160 |
Agenda | -0.142 |
| -0.139 |
ERA | -0.123 |
palp | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
isers | +0.188 |
Agenda | +0.169 |
| +0.165 |
ERA | +0.149 |
palp | +0.142 |
Neg logit contributions | |
romy | -0.185 |
apeake | -0.164 |
odan | -0.164 |
inx | -0.159 |
antis | -0.156 |
Token | local |
Token ID | 1957 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
isers | +1.626 |
Agenda | +1.474 |
| +1.440 |
ERA | +1.335 |
palp | +1.298 |
Neg logit contributions | |
romy | -1.020 |
odan | -0.901 |
apeake | -0.891 |
inx | -0.856 |
antis | -0.848 |
Token | independent |
Token ID | 4795 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
isers | +1.413 |
Agenda | +1.277 |
| +1.245 |
ERA | +1.140 |
palp | +1.124 |
Neg logit contributions | |
romy | -1.013 |
odan | -0.893 |
apeake | -0.890 |
inx | -0.860 |
antis | -0.853 |
Token | journalism |
Token ID | 14033 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
isers | +0.933 |
Agenda | +0.841 |
| +0.815 |
ERA | +0.739 |
palp | +0.720 |
Neg logit contributions | |
romy | -0.824 |
odan | -0.730 |
apeake | -0.719 |
inx | -0.705 |
antis | -0.692 |
Token | in |
Token ID | 287 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
isers | +1.364 |
Agenda | +1.223 |
| +1.180 |
ERA | +1.075 |
palp | +1.043 |
Neg logit contributions | |
romy | -1.176 |
odan | -1.036 |
apeake | -1.030 |
inx | -1.025 |
antis | -1.007 |
Token | South |
Token ID | 2520 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
isers | +1.656 |
Agenda | +1.419 |
| +1.353 |
ERA | +1.193 |
palp | +1.171 |
Neg logit contributions | |
romy | -2.235 |
apeake | -1.991 |
Polk | -1.983 |
odan | -1.966 |
inx | -1.965 |
Token | Australia |
Token ID | 4505 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
isers | +0.798 |
Agenda | +0.701 |
| +0.684 |
ERA | +0.618 |
palp | +0.590 |
Neg logit contributions | |
romy | -0.869 |
odan | -0.787 |
apeake | -0.787 |
inx | -0.767 |
antis | -0.762 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
isers | +0.317 |
Agenda | +0.285 |
| +0.277 |
ERA | +0.250 |
palp | +0.240 |
Neg logit contributions | |
romy | -0.311 |
apeake | -0.278 |
odan | -0.278 |
inx | -0.269 |
antis | -0.264 |
Token | As |
Token ID | 1081 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
isers | +0.861 |
Agenda | +0.755 |
| +0.733 |
ERA | +0.660 |
palp | +0.643 |
Neg logit contributions | |
romy | -0.952 |
apeake | -0.865 |
odan | -0.855 |
inx | -0.833 |
antis | -0.825 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
isers | +0.816 |
Agenda | +0.726 |
| +0.710 |
ERA | +0.651 |
palp | +0.628 |
Neg logit contributions | |
romy | -0.717 |
odan | -0.644 |
apeake | -0.639 |
inx | -0.614 |
antis | -0.609 |
Token | is |
Token ID | 318 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
isers | +0.306 |
Agenda | +0.275 |
| +0.270 |
ERA | +0.243 |
palp | +0.231 |
Neg logit contributions | |
romy | -0.301 |
odan | -0.267 |
apeake | -0.267 |
inx | -0.258 |
antis | -0.254 |
Token | hell |
Token ID | 5968 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
isers | +0.107 |
Agenda | +0.096 |
| +0.094 |
ERA | +0.085 |
palp | +0.081 |
Neg logit contributions | |
romy | -0.108 |
apeake | -0.096 |
odan | -0.096 |
inx | -0.093 |
antis | -0.091 |
Token | ," |
Token ID | 553 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
isers | +0.089 |
Agenda | +0.080 |
| +0.078 |
ERA | +0.070 |
palp | +0.067 |
Neg logit contributions | |
romy | -0.091 |
apeake | -0.081 |
odan | -0.081 |
inx | -0.079 |
antis | -0.078 |
Token | William |
Token ID | 3977 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
romy | +0.028 |
apeake | +0.025 |
odan | +0.025 |
inx | +0.025 |
antis | +0.024 |
Neg logit contributions | |
isers | -0.028 |
Agenda | -0.025 |
| -0.024 |
ERA | -0.022 |
palp | -0.021 |
Token | Tec |
Token ID | 48257 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
romy | +0.401 |
apeake | +0.358 |
odan | +0.357 |
inx | +0.346 |
antis | +0.340 |
Neg logit contributions | |
isers | -0.385 |
Agenda | -0.346 |
| -0.339 |
ERA | -0.303 |
palp | -0.288 |
Token | um |
Token ID | 388 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
isers | +0.191 |
Agenda | +0.173 |
| +0.169 |
ERA | +0.153 |
palp | +0.146 |
Neg logit contributions | |
romy | -0.177 |
apeake | -0.157 |
odan | -0.157 |
inx | -0.151 |
antis | -0.149 |
Token | se |
Token ID | 325 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
isers | +1.451 |
Agenda | +1.263 |
| +1.222 |
ERA | +1.092 |
palp | +0.978 |
Neg logit contributions | |
romy | -2.341 |
apeake | -2.167 |
inx | -2.115 |
odan | -2.112 |
antis | -2.086 |
Token | h |
Token ID | 71 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
isers | +0.263 |
Agenda | +0.231 |
| +0.224 |
ERA | +0.197 |
palp | +0.185 |
Neg logit contributions | |
romy | -0.381 |
apeake | -0.346 |
odan | -0.344 |
inx | -0.337 |
antis | -0.332 |
Token | Sherman |
Token ID | 23198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
romy | +0.080 |
apeake | +0.071 |
odan | +0.070 |
inx | +0.068 |
antis | +0.067 |
Neg logit contributions | |
isers | -0.093 |
Agenda | -0.084 |
| -0.083 |
ERA | -0.075 |
palp | -0.072 |
Token | once |
Token ID | 1752 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
romy | +0.095 |
apeake | +0.084 |
odan | +0.084 |
inx | +0.082 |
antis | +0.080 |
Neg logit contributions | |
isers | -0.101 |
Agenda | -0.091 |
| -0.089 |
ERA | -0.080 |
palp | -0.077 |
Token | said |
Token ID | 531 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
romy | +0.450 |
odan | +0.402 |
apeake | +0.402 |
inx | +0.389 |
antis | +0.383 |
Neg logit contributions | |
isers | -0.423 |
Agenda | -0.380 |
| -0.373 |
ERA | -0.333 |
palp | -0.317 |
Token | , |
Token ID | 11 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
isers | +0.939 |
Agenda | +0.838 |
| +0.819 |
ERA | +0.749 |
palp | +0.720 |
Neg logit contributions | |
romy | -0.864 |
apeake | -0.766 |
odan | -0.764 |
inx | -0.743 |
antis | -0.729 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
romy | +0.295 |
odan | +0.262 |
apeake | +0.262 |
inx | +0.254 |
antis | +0.249 |
Neg logit contributions | |
isers | -0.305 |
Agenda | -0.276 |
| -0.271 |
ERA | -0.244 |
palp | -0.232 |
Token | different |
Token ID | 1180 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
isers | +1.247 |
Agenda | +1.123 |
| +1.077 |
ERA | +0.979 |
palp | +0.939 |
Neg logit contributions | |
romy | -1.444 |
apeake | -1.312 |
odan | -1.308 |
inx | -1.260 |
antis | -1.252 |
Token | voice |
Token ID | 3809 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
isers | +0.654 |
Agenda | +0.557 |
| +0.536 |
ERA | +0.462 |
palp | +0.438 |
Neg logit contributions | |
romy | -1.103 |
apeake | -1.009 |
odan | -1.009 |
inx | -0.987 |
antis | -0.970 |
Token | and |
Token ID | 290 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
isers | +0.299 |
Agenda | +0.270 |
| +0.264 |
ERA | +0.238 |
palp | +0.228 |
Neg logit contributions | |
romy | -0.281 |
apeake | -0.250 |
odan | -0.249 |
inx | -0.242 |
antis | -0.237 |
Token | a |
Token ID | 257 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
isers | +0.244 |
Agenda | +0.220 |
| +0.215 |
ERA | +0.194 |
palp | +0.186 |
Neg logit contributions | |
romy | -0.224 |
apeake | -0.199 |
odan | -0.199 |
inx | -0.192 |
antis | -0.188 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
isers | +1.743 |
Agenda | +1.549 |
| +1.483 |
ERA | +1.354 |
palp | +1.303 |
Neg logit contributions | |
romy | -1.906 |
apeake | -1.784 |
odan | -1.732 |
inx | -1.668 |
antis | -1.662 |
Token | look |
Token ID | 804 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
isers | +1.454 |
Agenda | +1.330 |
| +1.277 |
ERA | +1.181 |
palp | +1.132 |
Neg logit contributions | |
romy | -1.077 |
apeake | -0.952 |
odan | -0.915 |
inx | -0.905 |
antis | -0.884 |
Token | at |
Token ID | 379 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
isers | +0.911 |
Agenda | +0.813 |
| +0.790 |
ERA | +0.716 |
palp | +0.689 |
Neg logit contributions | |
romy | -0.897 |
apeake | -0.802 |
odan | -0.801 |
inx | -0.785 |
antis | -0.769 |
Token | what |
Token ID | 644 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
isers | +0.445 |
Agenda | +0.399 |
| +0.390 |
ERA | +0.353 |
palp | +0.337 |
Neg logit contributions | |
romy | -0.430 |
apeake | -0.385 |
odan | -0.383 |
inx | -0.368 |
antis | -0.364 |
Token | is |
Token ID | 318 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
isers | +0.629 |
Agenda | +0.561 |
| +0.549 |
ERA | +0.496 |
palp | +0.474 |
Neg logit contributions | |
romy | -0.626 |
odan | -0.556 |
apeake | -0.555 |
inx | -0.537 |
antis | -0.531 |
Token | Nations |
Token ID | 7973 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
isers | +0.389 |
Agenda | +0.349 |
| +0.342 |
ERA | +0.308 |
palp | +0.294 |
Neg logit contributions | |
romy | -0.380 |
apeake | -0.338 |
odan | -0.337 |
inx | -0.327 |
antis | -0.321 |
Token | Educational |
Token ID | 30038 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
romy | +0.165 |
apeake | +0.148 |
odan | +0.147 |
inx | +0.143 |
antis | +0.140 |
Neg logit contributions | |
isers | -0.154 |
Agenda | -0.138 |
| -0.135 |
ERA | -0.121 |
palp | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
isers | +0.688 |
Agenda | +0.614 |
| +0.602 |
ERA | +0.546 |
palp | +0.523 |
Neg logit contributions | |
romy | -0.655 |
odan | -0.585 |
apeake | -0.580 |
inx | -0.567 |
antis | -0.555 |
Token | Scientific |
Token ID | 22060 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
romy | +0.637 |
odan | +0.563 |
apeake | +0.563 |
inx | +0.543 |
antis | +0.532 |
Neg logit contributions | |
isers | -0.715 |
Agenda | -0.658 |
| -0.644 |
ERA | -0.578 |
palp | -0.550 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
isers | +0.716 |
Agenda | +0.643 |
| +0.627 |
ERA | +0.572 |
palp | +0.547 |
Neg logit contributions | |
romy | -0.663 |
odan | -0.587 |
apeake | -0.584 |
inx | -0.572 |
antis | -0.557 |
Token | Cultural |
Token ID | 23897 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
isers | +0.315 |
Agenda | +0.287 |
| +0.282 |
ERA | +0.259 |
palp | +0.249 |
Neg logit contributions | |
romy | -0.213 |
apeake | -0.184 |
odan | -0.184 |
inx | -0.177 |
antis | -0.172 |
Token | Organisation |
Token ID | 30801 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
isers | +1.587 |
Agenda | +1.325 |
| +1.285 |
ERA | +1.164 |
palp | +1.119 |
Neg logit contributions | |
romy | -1.970 |
odan | -1.849 |
apeake | -1.825 |
inx | -1.795 |
antis | -1.753 |
Token | ) |
Token ID | 8 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
isers | +0.173 |
Agenda | +0.156 |
| +0.153 |
ERA | +0.138 |
palp | +0.132 |
Neg logit contributions | |
romy | -0.166 |
odan | -0.148 |
apeake | -0.148 |
inx | -0.143 |
antis | -0.140 |
Token | designated |
Token ID | 11032 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
romy | +0.004 |
apeake | +0.004 |
odan | +0.004 |
inx | +0.004 |
antis | +0.004 |
Neg logit contributions | |
isers | -0.004 |
Agenda | -0.004 |
| -0.004 |
ERA | -0.003 |
palp | -0.003 |
Token | Lake |
Token ID | 6233 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
isers | +0.055 |
Agenda | +0.050 |
| +0.049 |
ERA | +0.044 |
palp | +0.042 |
Neg logit contributions | |
romy | -0.051 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.044 |
antis | -0.043 |
Token | Ur |
Token ID | 8799 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
romy | +0.075 |
apeake | +0.068 |
odan | +0.068 |
inx | +0.066 |
antis | +0.065 |
Neg logit contributions | |
isers | -0.057 |
Agenda | -0.051 |
| -0.049 |
ERA | -0.043 |
palp | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
romy | +0.159 |
apeake | +0.142 |
odan | +0.142 |
inx | +0.137 |
antis | +0.134 |
Neg logit contributions | |
isers | -0.165 |
Agenda | -0.149 |
| -0.146 |
ERA | -0.131 |
palp | -0.125 |
Token | Conservative |
Token ID | 11132 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
isers | +0.733 |
Agenda | +0.650 |
| +0.641 |
ERA | +0.572 |
palp | +0.557 |
Neg logit contributions | |
romy | -0.720 |
apeake | -0.643 |
odan | -0.639 |
antis | -0.615 |
inx | -0.615 |
Token | Movement |
Token ID | 15477 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
isers | +0.034 |
Agenda | +0.025 |
| +0.024 |
ERA | +0.017 |
palp | +0.014 |
Neg logit contributions | |
romy | -0.134 |
apeake | -0.125 |
odan | -0.125 |
inx | -0.123 |
antis | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
isers | +0.542 |
Agenda | +0.487 |
| +0.476 |
ERA | +0.428 |
palp | +0.414 |
Neg logit contributions | |
romy | -0.517 |
apeake | -0.459 |
odan | -0.458 |
inx | -0.445 |
antis | -0.440 |
Token | with |
Token ID | 351 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
isers | +0.051 |
Agenda | +0.046 |
| +0.045 |
ERA | +0.040 |
palp | +0.039 |
Neg logit contributions | |
romy | -0.050 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.043 |
antis | -0.042 |
Token | an |
Token ID | 281 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
romy | +0.673 |
odan | +0.606 |
apeake | +0.605 |
inx | +0.590 |
antis | +0.577 |
Neg logit contributions | |
isers | -0.536 |
Agenda | -0.478 |
| -0.469 |
ERA | -0.414 |
palp | -0.386 |
Token | Introduction |
Token ID | 22395 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
isers | +1.827 |
Agenda | +1.587 |
| +1.577 |
palp | +1.397 |
ERA | +1.390 |
Neg logit contributions | |
romy | -1.749 |
odan | -1.569 |
apeake | -1.550 |
inx | -1.502 |
antis | -1.479 |
Token | by |
Token ID | 416 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
isers | +0.525 |
Agenda | +0.472 |
| +0.462 |
ERA | +0.414 |
palp | +0.399 |
Neg logit contributions | |
romy | -0.500 |
apeake | -0.443 |
odan | -0.443 |
inx | -0.431 |
antis | -0.423 |
Token | Prof |
Token ID | 4415 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
isers | +0.913 |
Agenda | +0.770 |
| +0.749 |
ERA | +0.625 |
palp | +0.604 |
Neg logit contributions | |
romy | -1.639 |
odan | -1.509 |
apeake | -1.485 |
inx | -1.454 |
antis | -1.449 |
Token | . |
Token ID | 13 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
isers | +1.323 |
Agenda | +1.201 |
| +1.177 |
ERA | +1.064 |
palp | +1.033 |
Neg logit contributions | |
romy | -1.234 |
odan | -1.088 |
apeake | -1.079 |
inx | -1.055 |
antis | -1.039 |
Token | George |
Token ID | 4502 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
isers | +0.657 |
Agenda | +0.583 |
| +0.570 |
ERA | +0.508 |
palp | +0.488 |
Neg logit contributions | |
romy | -0.725 |
apeake | -0.649 |
odan | -0.647 |
inx | -0.626 |
antis | -0.626 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
romy | +0.172 |
apeake | +0.152 |
odan | +0.152 |
inx | +0.146 |
antis | +0.143 |
Neg logit contributions | |
isers | -0.198 |
Agenda | -0.180 |
| -0.177 |
ERA | -0.160 |
palp | -0.153 |
Token | The |
Token ID | 464 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
isers | +0.079 |
Agenda | +0.071 |
| +0.069 |
ERA | +0.062 |
palp | +0.059 |
Neg logit contributions | |
romy | -0.082 |
apeake | -0.073 |
odan | -0.073 |
inx | -0.071 |
antis | -0.070 |
Token | opinions |
Token ID | 9317 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
isers | +0.077 |
Agenda | +0.070 |
| +0.068 |
ERA | +0.061 |
palp | +0.059 |
Neg logit contributions | |
romy | -0.074 |
apeake | -0.066 |
odan | -0.066 |
inx | -0.063 |
antis | -0.062 |
Token | expressed |
Token ID | 6241 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
isers | +0.322 |
Agenda | +0.280 |
| +0.272 |
ERA | +0.236 |
palp | +0.221 |
Neg logit contributions | |
romy | -0.493 |
odan | -0.448 |
apeake | -0.447 |
inx | -0.437 |
antis | -0.431 |
Token | by |
Token ID | 416 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
isers | +0.423 |
Agenda | +0.382 |
| +0.373 |
ERA | +0.337 |
palp | +0.320 |
Neg logit contributions | |
romy | -0.411 |
odan | -0.364 |
apeake | -0.364 |
inx | -0.354 |
antis | -0.347 |
Token | column |
Token ID | 5721 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
isers | +1.092 |
Agenda | +0.967 |
| +0.953 |
ERA | +0.857 |
palp | +0.819 |
Neg logit contributions | |
romy | -1.105 |
apeake | -0.983 |
odan | -0.979 |
inx | -0.943 |
antis | -0.936 |
Token | ists |
Token ID | 1023 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
isers | +1.146 |
Agenda | +1.017 |
| +0.976 |
ERA | +0.838 |
palp | +0.751 |
Neg logit contributions | |
romy | -2.372 |
odan | -2.181 |
apeake | -2.169 |
inx | -2.124 |
antis | -2.116 |
Token | are |
Token ID | 389 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
isers | +0.799 |
Agenda | +0.722 |
| +0.707 |
ERA | +0.647 |
palp | +0.620 |
Neg logit contributions | |
romy | -0.667 |
odan | -0.588 |
apeake | -0.586 |
inx | -0.566 |
antis | -0.553 |
Token | their |
Token ID | 511 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
isers | +1.170 |
Agenda | +1.057 |
| +1.038 |
ERA | +0.949 |
palp | +0.906 |
Neg logit contributions | |
romy | -0.937 |
apeake | -0.824 |
odan | -0.818 |
inx | -0.786 |
antis | -0.774 |
Token | own |
Token ID | 898 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
isers | +1.517 |
Agenda | +1.387 |
| +1.355 |
ERA | +1.260 |
palp | +1.235 |
Neg logit contributions | |
romy | -0.947 |
odan | -0.804 |
apeake | -0.798 |
inx | -0.768 |
antis | -0.755 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
isers | +1.250 |
Agenda | +1.137 |
| +1.105 |
ERA | +1.021 |
palp | +0.983 |
Neg logit contributions | |
romy | -1.085 |
odan | -0.949 |
apeake | -0.946 |
inx | -0.921 |
antis | -0.891 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
isers | +0.346 |
Agenda | +0.316 |
| +0.309 |
ERA | +0.285 |
palp | +0.275 |
Neg logit contributions | |
romy | -0.228 |
apeake | -0.198 |
odan | -0.196 |
inx | -0.189 |
antis | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
isers | +0.362 |
Agenda | +0.325 |
| +0.317 |
ERA | +0.285 |
palp | +0.274 |
Neg logit contributions | |
romy | -0.353 |
odan | -0.315 |
apeake | -0.314 |
inx | -0.303 |
antis | -0.298 |
Token | and |
Token ID | 290 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
romy | +0.037 |
odan | +0.032 |
apeake | +0.032 |
inx | +0.031 |
antis | +0.031 |
Neg logit contributions | |
isers | -0.038 |
Agenda | -0.034 |
| -0.033 |
ERA | -0.030 |
palp | -0.029 |
Token | critical |
Token ID | 4688 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
romy | +0.209 |
apeake | +0.174 |
odan | +0.173 |
inx | +0.165 |
antis | +0.160 |
Neg logit contributions | |
isers | -0.429 |
Agenda | -0.398 |
| -0.393 |
ERA | -0.364 |
palp | -0.350 |
Token | essays |
Token ID | 27126 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
romy | +0.254 |
apeake | +0.228 |
odan | +0.228 |
inx | +0.221 |
antis | +0.218 |
Neg logit contributions | |
isers | -0.215 |
Agenda | -0.192 |
| -0.187 |
ERA | -0.166 |
palp | -0.157 |
Token | by |
Token ID | 416 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
isers | +0.251 |
Agenda | +0.227 |
| +0.220 |
ERA | +0.199 |
palp | +0.190 |
Neg logit contributions | |
romy | -0.244 |
odan | -0.217 |
apeake | -0.217 |
inx | -0.210 |
antis | -0.206 |
Token | Scott |
Token ID | 4746 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
isers | +2.101 |
Agenda | +1.902 |
| +1.854 |
ERA | +1.722 |
palp | +1.682 |
Neg logit contributions | |
romy | -1.456 |
odan | -1.263 |
apeake | -1.219 |
inx | -1.189 |
Polk | -1.189 |
Token | Ric |
Token ID | 15868 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
romy | +0.840 |
apeake | +0.726 |
odan | +0.722 |
inx | +0.696 |
antis | +0.685 |
Neg logit contributions | |
isers | -1.145 |
Agenda | -1.055 |
| -1.041 |
ERA | -0.953 |
Gospel | -0.903 |
Token | her |
Token ID | 372 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
isers | +0.292 |
Agenda | +0.268 |
| +0.263 |
ERA | +0.241 |
palp | +0.232 |
Neg logit contributions | |
romy | -0.201 |
odan | -0.175 |
apeake | -0.174 |
inx | -0.167 |
antis | -0.164 |
Token | t |
Token ID | 83 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
romy | +0.219 |
apeake | +0.200 |
odan | +0.200 |
inx | +0.195 |
antis | +0.192 |
Neg logit contributions | |
isers | -0.126 |
Agenda | -0.109 |
| -0.105 |
ERA | -0.090 |
palp | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
romy | +0.104 |
apeake | +0.093 |
odan | +0.093 |
inx | +0.090 |
antis | +0.088 |
Neg logit contributions | |
isers | -0.108 |
Agenda | -0.097 |
| -0.095 |
ERA | -0.086 |
palp | -0.082 |
Token | own |
Token ID | 898 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
isers | +1.517 |
Agenda | +1.387 |
| +1.355 |
ERA | +1.260 |
palp | +1.235 |
Neg logit contributions | |
romy | -0.947 |
odan | -0.804 |
apeake | -0.798 |
inx | -0.768 |
antis | -0.755 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
isers | +1.250 |
Agenda | +1.137 |
| +1.105 |
ERA | +1.021 |
palp | +0.983 |
Neg logit contributions | |
romy | -1.085 |
odan | -0.949 |
apeake | -0.946 |
inx | -0.921 |
antis | -0.891 |
Token | do |
Token ID | 466 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
isers | +0.198 |
Agenda | +0.179 |
| +0.175 |
ERA | +0.158 |
palp | +0.151 |
Neg logit contributions | |
romy | -0.189 |
odan | -0.168 |
apeake | -0.168 |
inx | -0.162 |
antis | -0.159 |
Token | not |
Token ID | 407 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
romy | +0.195 |
apeake | +0.175 |
odan | +0.175 |
inx | +0.169 |
antis | +0.166 |
Neg logit contributions | |
isers | -0.178 |
Agenda | -0.160 |
| -0.157 |
ERA | -0.140 |
palp | -0.133 |
Token | represent |
Token ID | 2380 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
isers | +0.494 |
Agenda | +0.455 |
| +0.448 |
ERA | +0.416 |
palp | +0.403 |
Neg logit contributions | |
romy | -0.246 |
apeake | -0.207 |
odan | -0.205 |
inx | -0.196 |
antis | -0.190 |
Token | the |
Token ID | 262 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
isers | +0.690 |
Agenda | +0.616 |
| +0.610 |
ERA | +0.551 |
palp | +0.531 |
Neg logit contributions | |
romy | -0.621 |
apeake | -0.553 |
odan | -0.545 |
inx | -0.532 |
antis | -0.522 |
Token | views |
Token ID | 5009 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
isers | +1.158 |
| +0.923 |
Agenda | +0.909 |
ERA | +0.752 |
palp | +0.716 |
Neg logit contributions | |
romy | -2.388 |
apeake | -2.245 |
odan | -2.207 |
inx | -2.188 |
antis | -2.160 |
Token | of |
Token ID | 286 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
isers | +0.137 |
Agenda | +0.123 |
| +0.121 |
ERA | +0.109 |
palp | +0.104 |
Neg logit contributions | |
romy | -0.133 |
apeake | -0.119 |
odan | -0.119 |
inx | -0.115 |
antis | -0.113 |
Token | Town |
Token ID | 8329 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
isers | +0.276 |
Agenda | +0.242 |
| +0.238 |
ERA | +0.210 |
palp | +0.198 |
Neg logit contributions | |
romy | -0.353 |
apeake | -0.320 |
odan | -0.318 |
inx | -0.311 |
antis | -0.306 |
Token | hall |
Token ID | 18323 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
romy | +0.230 |
odan | +0.199 |
apeake | +0.198 |
inx | +0.191 |
antis | +0.186 |
Neg logit contributions | |
isers | -0.344 |
Agenda | -0.316 |
| -0.311 |
ERA | -0.284 |
palp | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
romy | +0.400 |
odan | +0.359 |
apeake | +0.357 |
inx | +0.346 |
antis | +0.341 |
Neg logit contributions | |
isers | -0.383 |
Agenda | -0.344 |
| -0.337 |
ERA | -0.301 |
palp | -0.286 |
Token | of |
Token ID | 286 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
romy | +0.036 |
apeake | +0.032 |
odan | +0.032 |
inx | +0.031 |
antis | +0.030 |
Neg logit contributions | |
isers | -0.039 |
Agenda | -0.035 |
| -0.035 |
ERA | -0.031 |
palp | -0.030 |
Token | Sync |
Token ID | 35908 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
romy | +0.017 |
apeake | +0.016 |
odan | +0.016 |
inx | +0.015 |
antis | +0.015 |
Neg logit contributions | |
isers | -0.018 |
Agenda | -0.016 |
| -0.016 |
ERA | -0.014 |
palp | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
romy | +0.398 |
apeake | +0.353 |
odan | +0.353 |
inx | +0.341 |
antis | +0.334 |
Neg logit contributions | |
isers | -0.434 |
Agenda | -0.393 |
| -0.386 |
ERA | -0.348 |
palp | -0.332 |
Token |
|
Token ID | 198 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
romy | +0.009 |
apeake | +0.008 |
odan | +0.008 |
inx | +0.007 |
antis | +0.007 |
Neg logit contributions | |
isers | -0.009 |
Agenda | -0.008 |
| -0.008 |
ERA | -0.007 |
palp | -0.007 |
Token | This |
Token ID | 1212 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
isers | +0.058 |
Agenda | +0.052 |
| +0.051 |
ERA | +0.046 |
palp | +0.044 |
Neg logit contributions | |
romy | -0.060 |
apeake | -0.053 |
odan | -0.053 |
inx | -0.052 |
antis | -0.051 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
romy | +0.248 |
apeake | +0.221 |
odan | +0.220 |
inx | +0.213 |
antis | +0.210 |
Neg logit contributions | |
isers | -0.246 |
Agenda | -0.222 |
| -0.217 |
ERA | -0.195 |
palp | -0.186 |
Token | requires |
Token ID | 4433 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
isers | +1.574 |
Agenda | +1.409 |
| +1.364 |
ERA | +1.204 |
palp | +1.162 |
Neg logit contributions | |
romy | -1.918 |
odan | -1.743 |
apeake | -1.738 |
inx | -1.719 |
antis | -1.671 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
isers | +0.838 |
Agenda | +0.753 |
| +0.734 |
ERA | +0.662 |
palp | +0.637 |
Neg logit contributions | |
romy | -0.849 |
odan | -0.760 |
apeake | -0.758 |
inx | -0.746 |
antis | -0.712 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
romy | +0.045 |
apeake | +0.041 |
odan | +0.041 |
inx | +0.039 |
antis | +0.039 |
Neg logit contributions | |
isers | -0.045 |
Agenda | -0.040 |
| -0.039 |
ERA | -0.035 |
palp | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
isers | +0.144 |
Agenda | +0.130 |
| +0.127 |
ERA | +0.115 |
palp | +0.110 |
Neg logit contributions | |
romy | -0.135 |
apeake | -0.120 |
odan | -0.120 |
inx | -0.116 |
antis | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
isers | +0.047 |
Agenda | +0.042 |
| +0.041 |
ERA | +0.037 |
palp | +0.036 |
Neg logit contributions | |
romy | -0.045 |
apeake | -0.040 |
odan | -0.040 |
inx | -0.039 |
antis | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
isers | +1.188 |
Agenda | +1.072 |
| +1.054 |
ERA | +0.947 |
palp | +0.925 |
Neg logit contributions | |
romy | -1.036 |
odan | -0.923 |
apeake | -0.919 |
inx | -0.895 |
antis | -0.874 |
Token | London |
Token ID | 3576 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
isers | +0.669 |
Agenda | +0.595 |
| +0.584 |
ERA | +0.525 |
palp | +0.511 |
Neg logit contributions | |
romy | -0.643 |
odan | -0.576 |
apeake | -0.576 |
inx | -0.558 |
antis | -0.547 |
Token | School |
Token ID | 3961 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
romy | +0.437 |
odan | +0.400 |
apeake | +0.400 |
inx | +0.391 |
antis | +0.385 |
Neg logit contributions | |
isers | -0.225 |
Agenda | -0.193 |
| -0.187 |
ERA | -0.157 |
palp | -0.143 |
Token | of |
Token ID | 286 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
isers | +0.345 |
Agenda | +0.312 |
| +0.303 |
ERA | +0.274 |
palp | +0.263 |
Neg logit contributions | |
romy | -0.328 |
apeake | -0.293 |
odan | -0.291 |
inx | -0.283 |
antis | -0.278 |
Token | Economics |
Token ID | 18963 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
romy | +0.255 |
odan | +0.228 |
apeake | +0.228 |
inx | +0.221 |
antis | +0.217 |
Neg logit contributions | |
isers | -0.234 |
Agenda | -0.210 |
| -0.205 |
ERA | -0.183 |
palp | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
isers | +0.679 |
Agenda | +0.618 |
| +0.595 |
ERA | +0.540 |
palp | +0.524 |
Neg logit contributions | |
romy | -0.646 |
apeake | -0.575 |
odan | -0.569 |
inx | -0.558 |
antis | -0.547 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
isers | +1.821 |
Agenda | +1.631 |
| +1.561 |
ERA | +1.419 |
palp | +1.410 |
Neg logit contributions | |
romy | -1.550 |
apeake | -1.420 |
odan | -1.360 |
inx | -1.353 |
antis | -1.316 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
isers | +0.046 |
Agenda | +0.042 |
| +0.041 |
ERA | +0.037 |
palp | +0.035 |
Neg logit contributions | |
romy | -0.045 |
apeake | -0.040 |
odan | -0.040 |
inx | -0.038 |
antis | -0.038 |
Token | ________________________________ |
Token ID | 10221 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
isers | +0.988 |
Agenda | +0.901 |
| +0.874 |
ERA | +0.806 |
palp | +0.784 |
Neg logit contributions | |
romy | -0.795 |
apeake | -0.708 |
odan | -0.693 |
inx | -0.680 |
antis | -0.672 |
Token | _ |
Token ID | 62 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
isers | +0.066 |
Agenda | +0.060 |
| +0.059 |
ERA | +0.054 |
palp | +0.052 |
Neg logit contributions | |
romy | -0.048 |
apeake | -0.042 |
odan | -0.042 |
inx | -0.040 |
antis | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
isers | +0.220 |
Agenda | +0.198 |
| +0.194 |
ERA | +0.175 |
palp | +0.168 |
Neg logit contributions | |
romy | -0.209 |
apeake | -0.187 |
odan | -0.186 |
inx | -0.180 |
antis | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
romy | +0.137 |
apeake | +0.121 |
odan | +0.121 |
inx | +0.117 |
antis | +0.115 |
Neg logit contributions | |
isers | -0.141 |
Agenda | -0.127 |
| -0.125 |
ERA | -0.112 |
palp | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
isers | +0.088 |
Agenda | +0.079 |
| +0.077 |
ERA | +0.070 |
palp | +0.067 |
Neg logit contributions | |
romy | -0.085 |
apeake | -0.075 |
odan | -0.075 |
inx | -0.073 |
antis | -0.072 |
Token | You |
Token ID | 1639 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
isers | +1.271 |
Agenda | +1.145 |
| +1.109 |
ERA | +1.019 |
palp | +0.981 |
Neg logit contributions | |
romy | -1.175 |
apeake | -1.057 |
odan | -1.036 |
antis | -1.017 |
inx | -1.015 |
Token | can |
Token ID | 460 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
isers | +0.014 |
Agenda | +0.013 |
| +0.012 |
ERA | +0.011 |
palp | +0.011 |
Neg logit contributions | |
romy | -0.013 |
apeake | -0.012 |
odan | -0.012 |
inx | -0.011 |
antis | -0.011 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
isers | +1.789 |
Agenda | +1.620 |
| +1.562 |
ERA | +1.455 |
palp | +1.408 |
Neg logit contributions | |
romy | -1.172 |
odan | -1.026 |
apeake | -1.012 |
inx | -0.968 |
antis | -0.960 |
Token | An |
Token ID | 1052 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
isers | +0.828 |
Agenda | +0.730 |
| +0.722 |
ERA | +0.645 |
palp | +0.623 |
Neg logit contributions | |
romy | -0.838 |
odan | -0.755 |
apeake | -0.751 |
inx | -0.725 |
antis | -0.723 |
Token | Enemy |
Token ID | 21785 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
isers | +1.531 |
| +1.295 |
Agenda | +1.287 |
ERA | +1.129 |
palp | +1.105 |
Neg logit contributions | |
romy | -1.839 |
apeake | -1.663 |
odan | -1.658 |
inx | -1.629 |
antis | -1.611 |
Token | of |
Token ID | 286 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
isers | +0.506 |
Agenda | +0.453 |
| +0.443 |
ERA | +0.401 |
palp | +0.386 |
Neg logit contributions | |
romy | -0.473 |
odan | -0.422 |
apeake | -0.422 |
inx | -0.408 |
antis | -0.401 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
isers | +0.216 |
Agenda | +0.195 |
| +0.191 |
ERA | +0.172 |
palp | +0.165 |
Neg logit contributions | |
romy | -0.202 |
apeake | -0.180 |
odan | -0.179 |
inx | -0.173 |
antis | -0.171 |
Token | State |
Token ID | 1812 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
isers | +1.266 |
Agenda | +1.143 |
| +1.130 |
ERA | +1.033 |
palp | +1.013 |
Neg logit contributions | |
romy | -0.899 |
apeake | -0.789 |
odan | -0.769 |
inx | -0.744 |
antis | -0.726 |
Token | : |
Token ID | 25 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
isers | +0.706 |
Agenda | +0.633 |
| +0.619 |
ERA | +0.562 |
palp | +0.540 |
Neg logit contributions | |
romy | -0.627 |
apeake | -0.559 |
odan | -0.553 |
inx | -0.534 |
antis | -0.522 |
Token | feed |
Token ID | 3745 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
isers | +1.272 |
Agenda | +1.152 |
| +1.119 |
ERA | +1.018 |
palp | +0.971 |
Neg logit contributions | |
romy | -1.134 |
apeake | -1.027 |
odan | -1.022 |
inx | -0.985 |
antis | -0.969 |
Token | by |
Token ID | 416 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
isers | +1.164 |
Agenda | +1.050 |
| +1.018 |
ERA | +0.923 |
palp | +0.896 |
Neg logit contributions | |
romy | -1.034 |
apeake | -0.922 |
odan | -0.920 |
inx | -0.885 |
antis | -0.872 |
Token | going |
Token ID | 1016 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
isers | +1.857 |
Agenda | +1.669 |
| +1.628 |
ERA | +1.502 |
palp | +1.439 |
Neg logit contributions | |
romy | -1.317 |
apeake | -1.178 |
odan | -1.149 |
inx | -1.123 |
antis | -1.083 |
Token | here |
Token ID | 994 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
romy | +0.091 |
apeake | +0.082 |
odan | +0.082 |
inx | +0.080 |
antis | +0.078 |
Neg logit contributions | |
isers | -0.076 |
Agenda | -0.068 |
| -0.066 |
ERA | -0.059 |
palp | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
isers | +0.131 |
Agenda | +0.118 |
| +0.115 |
ERA | +0.103 |
palp | +0.099 |
Neg logit contributions | |
romy | -0.131 |
apeake | -0.117 |
odan | -0.117 |
inx | -0.113 |
antis | -0.111 |
Token | But |
Token ID | 887 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
isers | +0.230 |
Agenda | +0.203 |
| +0.198 |
ERA | +0.175 |
palp | +0.167 |
Neg logit contributions | |
romy | -0.277 |
apeake | -0.250 |
odan | -0.249 |
inx | -0.243 |
antis | -0.239 |
Token | please |
Token ID | 3387 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
isers | +1.632 |
Agenda | +1.422 |
| +1.400 |
ERA | +1.274 |
palp | +1.215 |
Neg logit contributions | |
romy | -1.655 |
odan | -1.502 |
apeake | -1.493 |
inx | -1.468 |
antis | -1.427 |
Token | note |
Token ID | 3465 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
isers | +0.196 |
Agenda | +0.169 |
| +0.164 |
ERA | +0.142 |
palp | +0.131 |
Neg logit contributions | |
romy | -0.320 |
odan | -0.294 |
apeake | -0.292 |
inx | -0.285 |
antis | -0.281 |
Token | that |
Token ID | 326 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
romy | +1.008 |
odan | +0.909 |
apeake | +0.900 |
inx | +0.875 |
antis | +0.855 |
Neg logit contributions | |
isers | -0.986 |
Agenda | -0.892 |
| -0.872 |
ERA | -0.784 |
palp | -0.738 |
Token | my |
Token ID | 616 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
romy | +0.512 |
odan | +0.450 |
apeake | +0.449 |
inx | +0.433 |
antis | +0.426 |
Neg logit contributions | |
isers | -0.619 |
Agenda | -0.568 |
| -0.556 |
ERA | -0.505 |
palp | -0.480 |
Token | tweets |
Token ID | 12665 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
isers | +0.921 |
Agenda | +0.816 |
| +0.792 |
ERA | +0.705 |
palp | +0.664 |
Neg logit contributions | |
romy | -1.164 |
odan | -1.056 |
apeake | -1.055 |
inx | -1.010 |
Polk | -0.994 |
Token | is |
Token ID | 318 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
romy | +0.134 |
apeake | +0.120 |
odan | +0.120 |
inx | +0.116 |
antis | +0.114 |
Neg logit contributions | |
isers | -0.131 |
Agenda | -0.117 |
| -0.115 |
ERA | -0.103 |
palp | -0.098 |
Token | separate |
Token ID | 4553 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
isers | +0.860 |
Agenda | +0.768 |
| +0.749 |
ERA | +0.681 |
palp | +0.646 |
Neg logit contributions | |
romy | -0.848 |
apeake | -0.757 |
odan | -0.752 |
inx | -0.731 |
antis | -0.720 |
Token | from |
Token ID | 422 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
romy | +0.035 |
apeake | +0.031 |
odan | +0.031 |
inx | +0.030 |
antis | +0.030 |
Neg logit contributions | |
isers | -0.040 |
Agenda | -0.036 |
| -0.036 |
ERA | -0.032 |
palp | -0.031 |
Token | USA |
Token ID | 4916 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
isers | +0.365 |
Agenda | +0.323 |
| +0.317 |
ERA | +0.281 |
palp | +0.268 |
Neg logit contributions | |
romy | -0.425 |
apeake | -0.382 |
odan | -0.382 |
inx | -0.372 |
antis | -0.365 |
Token | TODAY |
Token ID | 20092 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
isers | +0.020 |
Agenda | +0.019 |
| +0.018 |
ERA | +0.017 |
palp | +0.016 |
Neg logit contributions | |
romy | -0.012 |
apeake | -0.010 |
odan | -0.010 |
inx | -0.009 |
antis | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
isers | +1.676 |
Agenda | +1.503 |
| +1.456 |
ERA | +1.335 |
palp | +1.294 |
Neg logit contributions | |
romy | -1.468 |
apeake | -1.317 |
odan | -1.276 |
inx | -1.266 |
Polk | -1.225 |
Token | news |
Token ID | 1705 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
isers | +1.905 |
Agenda | +1.689 |
| +1.665 |
ERA | +1.523 |
palp | +1.497 |
Neg logit contributions | |
romy | -1.346 |
apeake | -1.166 |
odan | -1.156 |
inx | -1.116 |
Polk | -1.113 |
Token | staff |
Token ID | 3085 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
isers | +0.461 |
Agenda | +0.416 |
| +0.406 |
ERA | +0.369 |
palp | +0.356 |
Neg logit contributions | |
romy | -0.393 |
odan | -0.344 |
apeake | -0.344 |
inx | -0.333 |
antis | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
isers | +0.184 |
Agenda | +0.165 |
| +0.161 |
ERA | +0.146 |
palp | +0.140 |
Neg logit contributions | |
romy | -0.176 |
apeake | -0.157 |
odan | -0.157 |
inx | -0.152 |
antis | -0.149 |
Token | Most |
Token ID | 4042 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
isers | +0.720 |
Agenda | +0.640 |
| +0.626 |
ERA | +0.565 |
palp | +0.544 |
Neg logit contributions | |
romy | -0.672 |
apeake | -0.602 |
odan | -0.600 |
inx | -0.580 |
antis | -0.567 |
Token | editor |
Token ID | 5464 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
isers | +0.526 |
Agenda | +0.450 |
| +0.435 |
ERA | +0.372 |
palp | +0.347 |
Neg logit contributions | |
romy | -0.936 |
odan | -0.860 |
apeake | -0.860 |
inx | -0.835 |
antis | -0.821 |
Token | their |
Token ID | 511 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
romy | +0.417 |
odan | +0.369 |
apeake | +0.369 |
inx | +0.357 |
antis | +0.350 |
Neg logit contributions | |
isers | -0.457 |
Agenda | -0.414 |
| -0.407 |
ERA | -0.367 |
palp | -0.350 |
Token | own |
Token ID | 898 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
isers | +0.399 |
Agenda | +0.366 |
| +0.358 |
ERA | +0.329 |
palp | +0.318 |
Neg logit contributions | |
romy | -0.271 |
apeake | -0.234 |
odan | -0.234 |
inx | -0.224 |
antis | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
isers | +0.796 |
Agenda | +0.721 |
| +0.701 |
ERA | +0.641 |
palp | +0.615 |
Neg logit contributions | |
romy | -0.720 |
odan | -0.636 |
apeake | -0.635 |
inx | -0.616 |
antis | -0.598 |
Token | are |
Token ID | 389 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
romy | +0.134 |
apeake | +0.119 |
odan | +0.119 |
inx | +0.115 |
antis | +0.113 |
Neg logit contributions | |
isers | -0.137 |
Agenda | -0.123 |
| -0.121 |
ERA | -0.109 |
palp | -0.103 |
Token | not |
Token ID | 407 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
isers | +0.109 |
Agenda | +0.098 |
| +0.096 |
ERA | +0.086 |
palp | +0.081 |
Neg logit contributions | |
romy | -0.116 |
apeake | -0.104 |
odan | -0.104 |
inx | -0.101 |
antis | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
isers | +0.274 |
Agenda | +0.247 |
| +0.242 |
ERA | +0.219 |
palp | +0.209 |
Neg logit contributions | |
romy | -0.255 |
apeake | -0.227 |
odan | -0.226 |
inx | -0.220 |
antis | -0.215 |
Token | views |
Token ID | 5009 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
isers | +0.999 |
Agenda | +0.835 |
| +0.798 |
ERA | +0.662 |
palp | +0.633 |
Neg logit contributions | |
romy | -2.184 |
apeake | -2.046 |
odan | -2.024 |
inx | -2.005 |
antis | -1.961 |
Token | of |
Token ID | 286 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
romy | +0.162 |
apeake | +0.144 |
odan | +0.144 |
inx | +0.139 |
antis | +0.137 |
Neg logit contributions | |
isers | -0.163 |
Agenda | -0.147 |
| -0.144 |
ERA | -0.129 |
palp | -0.123 |
Token | The |
Token ID | 383 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
romy | +0.032 |
apeake | +0.028 |
odan | +0.028 |
inx | +0.027 |
antis | +0.026 |
Neg logit contributions | |
isers | -0.038 |
Agenda | -0.035 |
| -0.034 |
ERA | -0.031 |
palp | -0.030 |
Token | Hill |
Token ID | 3327 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
isers | +0.699 |
Agenda | +0.631 |
| +0.620 |
ERA | +0.566 |
palp | +0.547 |
Neg logit contributions | |
romy | -0.586 |
apeake | -0.519 |
odan | -0.516 |
inx | -0.499 |
antis | -0.485 |
Token | . |
Token ID | 13 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
isers | +0.043 |
Agenda | +0.039 |
| +0.038 |
ERA | +0.034 |
palp | +0.032 |
Neg logit contributions | |
romy | -0.044 |
odan | -0.039 |
apeake | -0.039 |
inx | -0.038 |
antis | -0.037 |
Token | help |
Token ID | 1037 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
romy | +0.295 |
apeake | +0.260 |
odan | +0.260 |
inx | +0.251 |
antis | +0.245 |
Neg logit contributions | |
isers | -0.338 |
Agenda | -0.308 |
| -0.302 |
ERA | -0.273 |
palp | -0.260 |
Token | fund |
Token ID | 1814 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
isers | +0.202 |
Agenda | +0.184 |
| +0.180 |
ERA | +0.165 |
palp | +0.158 |
Neg logit contributions | |
romy | -0.158 |
odan | -0.139 |
apeake | -0.139 |
inx | -0.133 |
antis | -0.131 |
Token | our |
Token ID | 674 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
romy | +0.311 |
apeake | +0.281 |
odan | +0.280 |
inx | +0.273 |
antis | +0.268 |
Neg logit contributions | |
isers | -0.240 |
Agenda | -0.213 |
| -0.208 |
ERA | -0.183 |
palp | -0.172 |
Token | work |
Token ID | 670 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
romy | +0.680 |
apeake | +0.585 |
odan | +0.574 |
inx | +0.561 |
antis | +0.543 |
Neg logit contributions | |
isers | -0.962 |
Agenda | -0.893 |
| -0.880 |
ERA | -0.800 |
palp | -0.765 |
Token | is |
Token ID | 318 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
romy | +0.143 |
apeake | +0.128 |
odan | +0.128 |
inx | +0.124 |
antis | +0.122 |
Neg logit contributions | |
isers | -0.131 |
Agenda | -0.118 |
| -0.115 |
ERA | -0.103 |
palp | -0.097 |
Token | appreciated |
Token ID | 16373 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
isers | +0.338 |
Agenda | +0.302 |
| +0.295 |
ERA | +0.267 |
palp | +0.254 |
Neg logit contributions | |
romy | -0.329 |
odan | -0.295 |
apeake | -0.294 |
inx | -0.284 |
antis | -0.280 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
isers | +1.722 |
Agenda | +1.527 |
| +1.474 |
ERA | +1.353 |
palp | +1.309 |
Neg logit contributions | |
romy | -1.470 |
odan | -1.332 |
apeake | -1.315 |
inx | -1.292 |
antis | -1.285 |
Token | Please |
Token ID | 4222 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
isers | +1.178 |
Agenda | +1.031 |
| +1.010 |
ERA | +0.930 |
palp | +0.897 |
Neg logit contributions | |
romy | -1.075 |
apeake | -0.973 |
odan | -0.969 |
inx | -0.942 |
antis | -0.942 |
Token | click |
Token ID | 3904 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
isers | +0.963 |
Agenda | +0.856 |
| +0.824 |
ERA | +0.763 |
palp | +0.726 |
Neg logit contributions | |
romy | -0.838 |
odan | -0.755 |
apeake | -0.750 |
inx | -0.730 |
antis | -0.724 |
Token | below |
Token ID | 2174 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
romy | +0.112 |
apeake | +0.098 |
odan | +0.098 |
inx | +0.095 |
antis | +0.093 |
Neg logit contributions | |
isers | -0.128 |
Agenda | -0.116 |
| -0.114 |
ERA | -0.103 |
palp | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
romy | +0.459 |
apeake | +0.408 |
odan | +0.407 |
inx | +0.395 |
antis | +0.388 |
Neg logit contributions | |
isers | -0.438 |
Agenda | -0.395 |
| -0.387 |
ERA | -0.345 |
palp | -0.327 |
Token | check |
Token ID | 2198 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
romy | +0.081 |
apeake | +0.071 |
odan | +0.071 |
inx | +0.068 |
antis | +0.067 |
Neg logit contributions | |
isers | -0.103 |
Agenda | -0.094 |
| -0.092 |
ERA | -0.084 |
palp | -0.081 |
Token | out |
Token ID | 503 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
romy | +0.450 |
apeake | +0.400 |
odan | +0.399 |
inx | +0.387 |
antis | +0.380 |
Neg logit contributions | |
isers | -0.457 |
Agenda | -0.415 |
| -0.405 |
ERA | -0.365 |
palp | -0.346 |
Token | my |
Token ID | 616 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
isers | +0.814 |
Agenda | +0.735 |
| +0.724 |
ERA | +0.659 |
palp | +0.636 |
Neg logit contributions | |
romy | -0.603 |
apeake | -0.527 |
odan | -0.525 |
inx | -0.503 |
antis | -0.492 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
isers | +0.279 |
Agenda | +0.246 |
| +0.239 |
ERA | +0.211 |
palp | +0.198 |
Neg logit contributions | |
romy | -0.370 |
apeake | -0.335 |
odan | -0.335 |
inx | -0.324 |
antis | -0.320 |
Token | feed |
Token ID | 3745 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
isers | +1.272 |
Agenda | +1.152 |
| +1.119 |
ERA | +1.018 |
palp | +0.971 |
Neg logit contributions | |
romy | -1.134 |
apeake | -1.027 |
odan | -1.022 |
inx | -0.985 |
antis | -0.969 |
Token | by |
Token ID | 416 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
isers | +1.164 |
Agenda | +1.050 |
| +1.018 |
ERA | +0.923 |
palp | +0.896 |
Neg logit contributions | |
romy | -1.034 |
apeake | -0.922 |
odan | -0.920 |
inx | -0.885 |
antis | -0.872 |
Token | going |
Token ID | 1016 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
isers | +1.857 |
Agenda | +1.669 |
| +1.628 |
ERA | +1.502 |
palp | +1.439 |
Neg logit contributions | |
romy | -1.317 |
apeake | -1.178 |
odan | -1.149 |
inx | -1.123 |
antis | -1.083 |
Token | here |
Token ID | 994 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
romy | +0.091 |
apeake | +0.082 |
odan | +0.082 |
inx | +0.080 |
antis | +0.078 |
Neg logit contributions | |
isers | -0.076 |
Agenda | -0.068 |
| -0.066 |
ERA | -0.059 |
palp | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
isers | +0.131 |
Agenda | +0.118 |
| +0.115 |
ERA | +0.103 |
palp | +0.099 |
Neg logit contributions | |
romy | -0.131 |
apeake | -0.117 |
odan | -0.117 |
inx | -0.113 |
antis | -0.111 |
Token | But |
Token ID | 887 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
isers | +0.230 |
Agenda | +0.203 |
| +0.198 |
ERA | +0.175 |
palp | +0.167 |
Neg logit contributions | |
romy | -0.277 |
apeake | -0.250 |
odan | -0.249 |
inx | -0.243 |
antis | -0.239 |
Token | please |
Token ID | 3387 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
isers | +1.632 |
Agenda | +1.422 |
| +1.400 |
ERA | +1.274 |
palp | +1.215 |
Neg logit contributions | |
romy | -1.655 |
odan | -1.502 |
apeake | -1.493 |
inx | -1.468 |
antis | -1.427 |
Token | Your |
Token ID | 3406 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
romy | +0.625 |
apeake | +0.529 |
odan | +0.527 |
inx | +0.507 |
antis | +0.491 |
Neg logit contributions | |
isers | -1.130 |
Agenda | -1.046 |
| -1.033 |
ERA | -0.945 |
palp | -0.912 |
Token | Name |
Token ID | 6530 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
isers | +0.610 |
Agenda | +0.530 |
| +0.515 |
ERA | +0.450 |
palp | +0.422 |
Neg logit contributions | |
romy | -1.006 |
odan | -0.918 |
apeake | -0.914 |
inx | -0.885 |
antis | -0.875 |
Token | Add |
Token ID | 3060 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
romy | +0.522 |
odan | +0.461 |
apeake | +0.460 |
inx | +0.444 |
antis | +0.437 |
Neg logit contributions | |
isers | -0.578 |
Agenda | -0.524 |
| -0.515 |
ERA | -0.464 |
palp | -0.441 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
isers | +0.131 |
Agenda | +0.119 |
| +0.116 |
ERA | +0.105 |
palp | +0.100 |
Neg logit contributions | |
romy | -0.122 |
apeake | -0.108 |
odan | -0.108 |
inx | -0.105 |
antis | -0.102 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
isers | +0.400 |
Agenda | +0.371 |
| +0.365 |
ERA | +0.340 |
palp | +0.329 |
Neg logit contributions | |
romy | -0.194 |
odan | -0.162 |
apeake | -0.161 |
inx | -0.152 |
antis | -0.146 |
Token | here |
Token ID | 994 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
romy | +0.908 |
apeake | +0.821 |
odan | +0.820 |
inx | +0.796 |
antis | +0.787 |
Neg logit contributions | |
isers | -0.715 |
Agenda | -0.641 |
| -0.623 |
ERA | -0.547 |
palp | -0.512 |
Token | Ver |
Token ID | 4643 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
romy | +2.384 |
odan | +2.081 |
apeake | +2.061 |
inx | +2.028 |
antis | +2.021 |
Neg logit contributions | |
isers | -2.138 |
Agenda | -1.951 |
| -1.933 |
ERA | -1.728 |
Gospel | -1.624 |
Token | ification |
Token ID | 2649 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
isers | +0.861 |
Agenda | +0.787 |
| +0.765 |
ERA | +0.701 |
palp | +0.665 |
Neg logit contributions | |
romy | -0.832 |
apeake | -0.735 |
odan | -0.731 |
inx | -0.716 |
antis | -0.705 |
Token | Send |
Token ID | 16290 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
isers | +0.104 |
Agenda | +0.093 |
| +0.090 |
ERA | +0.080 |
palp | +0.076 |
Neg logit contributions | |
romy | -0.125 |
apeake | -0.112 |
odan | -0.112 |
inx | -0.109 |
antis | -0.107 |
Token | Email |
Token ID | 9570 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
isers | +0.218 |
Agenda | +0.168 |
| +0.159 |
ERA | +0.116 |
palp | +0.099 |
Neg logit contributions | |
romy | -0.738 |
apeake | -0.686 |
odan | -0.686 |
inx | -0.670 |
antis | -0.665 |
Token | Cancel |
Token ID | 27910 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
romy | +0.493 |
apeake | +0.456 |
odan | +0.456 |
inx | +0.447 |
antis | +0.441 |
Neg logit contributions | |
isers | -0.172 |
Agenda | -0.139 |
| -0.133 |
ERA | -0.103 |
palp | -0.090 |
Token | up |
Token ID | 510 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
isers | +0.200 |
Agenda | +0.179 |
| +0.175 |
ERA | +0.157 |
palp | +0.149 |
Neg logit contributions | |
romy | -0.217 |
apeake | -0.194 |
odan | -0.194 |
inx | -0.188 |
antis | -0.185 |
Token | for |
Token ID | 329 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
romy | +0.281 |
apeake | +0.247 |
odan | +0.247 |
inx | +0.238 |
antis | +0.233 |
Neg logit contributions | |
isers | -0.335 |
Agenda | -0.305 |
| -0.300 |
ERA | -0.272 |
palp | -0.260 |
Token | BRE |
Token ID | 29377 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
isers | +0.032 |
Agenda | +0.029 |
| +0.028 |
ERA | +0.025 |
palp | +0.024 |
Neg logit contributions | |
romy | -0.036 |
apeake | -0.032 |
odan | -0.032 |
inx | -0.031 |
antis | -0.031 |
Token | AKING |
Token ID | 43602 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
romy | +0.220 |
odan | +0.186 |
apeake | +0.185 |
inx | +0.177 |
antis | +0.173 |
Neg logit contributions | |
isers | -0.390 |
Agenda | -0.360 |
| -0.355 |
ERA | -0.328 |
palp | -0.315 |
Token | NEWS |
Token ID | 28840 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
romy | +0.230 |
odan | +0.201 |
apeake | +0.201 |
inx | +0.194 |
antis | +0.190 |
Neg logit contributions | |
isers | -0.293 |
Agenda | -0.268 |
| -0.263 |
ERA | -0.239 |
palp | -0.229 |
Token | Emails |
Token ID | 39617 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
romy | +0.271 |
odan | +0.247 |
apeake | +0.247 |
inx | +0.241 |
antis | +0.237 |
Neg logit contributions | |
isers | -0.162 |
Agenda | -0.141 |
| -0.137 |
ERA | -0.117 |
palp | -0.109 |
Token | privacy |
Token ID | 6782 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
romy | +2.025 |
odan | +1.811 |
apeake | +1.763 |
inx | +1.682 |
antis | +1.658 |
Neg logit contributions | |
isers | -2.246 |
Agenda | -2.106 |
| -2.058 |
ERA | -1.841 |
SA | -1.735 |
Token | policy |
Token ID | 2450 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
romy | +0.547 |
apeake | +0.480 |
odan | +0.476 |
inx | +0.459 |
antis | +0.448 |
Neg logit contributions | |
isers | -0.735 |
Agenda | -0.675 |
| -0.664 |
ERA | -0.602 |
palp | -0.575 |
Token | Thanks |
Token ID | 6930 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
romy | +0.473 |
apeake | +0.428 |
odan | +0.427 |
inx | +0.416 |
antis | +0.408 |
Neg logit contributions | |
isers | -0.371 |
Agenda | -0.330 |
| -0.323 |
ERA | -0.284 |
palp | -0.266 |
Token | for |
Token ID | 329 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
romy | +0.173 |
apeake | +0.154 |
odan | +0.154 |
inx | +0.149 |
antis | +0.146 |
Neg logit contributions | |
isers | -0.180 |
Agenda | -0.163 |
| -0.159 |
ERA | -0.143 |
palp | -0.137 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
isers | +0.520 |
Agenda | +0.477 |
| +0.468 |
ERA | +0.435 |
palp | +0.421 |
Neg logit contributions | |
romy | -0.289 |
apeake | -0.244 |
odan | -0.244 |
inx | -0.234 |
antis | -0.226 |
Token | : |
Token ID | 25 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
isers | +0.257 |
Agenda | +0.230 |
| +0.224 |
ERA | +0.199 |
palp | +0.188 |
Neg logit contributions | |
romy | -0.306 |
apeake | -0.276 |
odan | -0.274 |
inx | -0.267 |
antis | -0.263 |
Token | ' |
Token ID | 705 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
romy | +0.186 |
apeake | +0.163 |
odan | +0.163 |
inx | +0.157 |
antis | +0.154 |
Neg logit contributions | |
isers | -0.235 |
Agenda | -0.214 |
| -0.210 |
ERA | -0.191 |
palp | -0.183 |
Token | I |
Token ID | 40 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
romy | +0.866 |
odan | +0.775 |
apeake | +0.773 |
inx | +0.743 |
antis | +0.721 |
Neg logit contributions | |
isers | -0.878 |
Agenda | -0.790 |
| -0.780 |
ERA | -0.699 |
palp | -0.662 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
romy | +1.064 |
odan | +0.950 |
apeake | +0.948 |
inx | +0.916 |
antis | +0.886 |
Neg logit contributions | |
isers | -1.187 |
Agenda | -1.082 |
| -1.081 |
ERA | -0.965 |
palp | -0.919 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
romy | +0.775 |
apeake | +0.689 |
odan | +0.687 |
inx | +0.658 |
antis | +0.652 |
Neg logit contributions | |
isers | -0.890 |
Agenda | -0.808 |
| -0.802 |
ERA | -0.716 |
palp | -0.685 |
Token | ' |
Token ID | 6 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
romy | +0.726 |
apeake | +0.649 |
odan | +0.648 |
inx | +0.617 |
antis | +0.604 |
Neg logit contributions | |
isers | -0.832 |
Agenda | -0.758 |
| -0.748 |
ERA | -0.674 |
palp | -0.642 |
Token | fair |
Token ID | 3148 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
romy | +2.125 |
apeake | +1.923 |
odan | +1.913 |
inx | +1.846 |
antis | +1.780 |
Neg logit contributions | |
isers | -1.583 |
| -1.451 |
Agenda | -1.448 |
ERA | -1.253 |
SA | -1.155 |
Token | treatment |
Token ID | 3513 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
romy | +1.420 |
apeake | +1.286 |
odan | +1.285 |
inx | +1.224 |
antis | +1.203 |
Neg logit contributions | |
isers | -1.655 |
Agenda | -1.495 |
| -1.473 |
ERA | -1.328 |
palp | -1.248 |
Token | by |
Token ID | 416 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
romy | +0.314 |
apeake | +0.280 |
odan | +0.280 |
inx | +0.271 |
antis | +0.265 |
Neg logit contributions | |
isers | -0.316 |
Agenda | -0.286 |
| -0.280 |
ERA | -0.252 |
palp | -0.238 |
Token | DNC |
Token ID | 17824 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
isers | +0.573 |
Agenda | +0.513 |
| +0.498 |
ERA | +0.442 |
palp | +0.428 |
Neg logit contributions | |
romy | -0.644 |
apeake | -0.579 |
odan | -0.577 |
inx | -0.563 |
antis | -0.558 |
Token | in |
Token ID | 287 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
romy | +0.549 |
apeake | +0.499 |
odan | +0.497 |
inx | +0.483 |
antis | +0.474 |
Neg logit contributions | |
isers | -0.400 |
Agenda | -0.353 |
| -0.346 |
ERA | -0.301 |
palp | -0.282 |
Token | D |
Token ID | 35 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
isers | +0.069 |
Agenda | +0.062 |
| +0.060 |
ERA | +0.054 |
palp | +0.051 |
Neg logit contributions | |
romy | -0.076 |
apeake | -0.068 |
odan | -0.068 |
inx | -0.066 |
antis | -0.065 |
Token | ahl |
Token ID | 15668 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
romy | +0.045 |
apeake | +0.040 |
odan | +0.040 |
inx | +0.039 |
antis | +0.038 |
Neg logit contributions | |
isers | -0.056 |
Agenda | -0.051 |
| -0.050 |
ERA | -0.045 |
palp | -0.043 |
Token | ia |
Token ID | 544 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
romy | +0.675 |
odan | +0.597 |
apeake | +0.596 |
inx | +0.576 |
antis | +0.565 |
Neg logit contributions | |
isers | -0.732 |
Agenda | -0.664 |
| -0.655 |
ERA | -0.587 |
palp | -0.559 |
Token | Lith |
Token ID | 19730 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
isers | +0.075 |
Agenda | +0.069 |
| +0.068 |
ERA | +0.062 |
palp | +0.059 |
Neg logit contributions | |
romy | -0.056 |
odan | -0.049 |
apeake | -0.049 |
inx | -0.047 |
antis | -0.046 |
Token | wick |
Token ID | 16239 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
isers | +1.026 |
Agenda | +0.916 |
| +0.890 |
ERA | +0.794 |
palp | +0.745 |
Neg logit contributions | |
romy | -1.368 |
odan | -1.247 |
apeake | -1.241 |
inx | -1.218 |
antis | -1.188 |
Token | has |
Token ID | 468 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
romy | +0.258 |
odan | +0.230 |
apeake | +0.230 |
inx | +0.222 |
antis | +0.218 |
Neg logit contributions | |
isers | -0.266 |
Agenda | -0.240 |
| -0.236 |
ERA | -0.212 |
palp | -0.202 |
Token | a |
Token ID | 257 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
romy | +1.724 |
odan | +1.518 |
apeake | +1.501 |
inx | +1.460 |
antis | +1.440 |
Neg logit contributions | |
isers | -1.893 |
| -1.740 |
Agenda | -1.704 |
ERA | -1.534 |
Gospel | -1.464 |
Token | rundown |
Token ID | 45602 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
isers | +0.215 |
Agenda | +0.194 |
| +0.189 |
ERA | +0.170 |
palp | +0.162 |
Neg logit contributions | |
romy | -0.219 |
apeake | -0.196 |
odan | -0.196 |
inx | -0.189 |
antis | -0.186 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
romy | +0.264 |
odan | +0.235 |
apeake | +0.235 |
inx | +0.227 |
antis | +0.223 |
Neg logit contributions | |
isers | -0.264 |
Agenda | -0.238 |
| -0.233 |
ERA | -0.209 |
palp | -0.199 |
Token | the |
Token ID | 262 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
romy | +1.035 |
apeake | +0.927 |
odan | +0.923 |
inx | +0.892 |
antis | +0.882 |
Neg logit contributions | |
isers | -1.005 |
Agenda | -0.902 |
| -0.898 |
ERA | -0.798 |
palp | -0.750 |
Token | theory |
Token ID | 4583 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
romy | +0.622 |
odan | +0.553 |
apeake | +0.552 |
inx | +0.533 |
antis | +0.527 |
Neg logit contributions | |
isers | -0.664 |
Agenda | -0.599 |
| -0.590 |
ERA | -0.531 |
palp | -0.506 |
Token | Obama |
Token ID | 2486 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
romy | +0.013 |
apeake | +0.011 |
odan | +0.011 |
inx | +0.011 |
antis | +0.011 |
Neg logit contributions | |
isers | -0.012 |
Agenda | -0.010 |
| -0.010 |
ERA | -0.009 |
palp | -0.009 |
Token | Barack |
Token ID | 8732 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
romy | +0.069 |
apeake | +0.062 |
odan | +0.062 |
inx | +0.060 |
antis | +0.059 |
Neg logit contributions | |
isers | -0.071 |
Agenda | -0.064 |
| -0.062 |
ERA | -0.056 |
palp | -0.054 |
Token | Hussein |
Token ID | 22983 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
isers | +0.459 |
Agenda | +0.413 |
| +0.404 |
ERA | +0.362 |
palp | +0.347 |
Neg logit contributions | |
romy | -0.470 |
apeake | -0.419 |
odan | -0.419 |
inx | -0.408 |
antis | -0.397 |
Token | Obama |
Token ID | 2486 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
isers | +1.126 |
Agenda | +1.013 |
| +0.981 |
ERA | +0.880 |
palp | +0.855 |
Neg logit contributions | |
romy | -1.126 |
odan | -1.004 |
apeake | -1.000 |
inx | -0.978 |
antis | -0.954 |
Token | With |
Token ID | 3152 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
romy | +0.082 |
apeake | +0.073 |
odan | +0.073 |
inx | +0.071 |
antis | +0.069 |
Neg logit contributions | |
isers | -0.079 |
Agenda | -0.071 |
| -0.070 |
ERA | -0.063 |
palp | -0.059 |
Token | low |
Token ID | 1877 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
isers | +0.697 |
Agenda | +0.625 |
| +0.616 |
ERA | +0.562 |
palp | +0.538 |
Neg logit contributions | |
romy | -0.610 |
apeake | -0.539 |
odan | -0.539 |
inx | -0.517 |
antis | -0.511 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
romy | +1.682 |
apeake | +1.512 |
odan | +1.467 |
inx | +1.467 |
antis | +1.388 |
Neg logit contributions | |
isers | -1.884 |
Agenda | -1.761 |
| -1.726 |
ERA | -1.538 |
Gospel | -1.446 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
romy | +0.012 |
apeake | +0.011 |
odan | +0.011 |
inx | +0.010 |
antis | +0.010 |
Neg logit contributions | |
isers | -0.014 |
Agenda | -0.012 |
| -0.012 |
ERA | -0.011 |
palp | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
romy | +1.457 |
apeake | +1.304 |
odan | +1.300 |
inx | +1.263 |
antis | +1.229 |
Neg logit contributions | |
isers | -1.307 |
Agenda | -1.188 |
| -1.166 |
ERA | -1.036 |
palp | -0.974 |
Token | America |
Token ID | 2253 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
romy | +0.417 |
apeake | +0.370 |
odan | +0.370 |
inx | +0.358 |
antis | +0.349 |
Neg logit contributions | |
isers | -0.432 |
Agenda | -0.392 |
| -0.385 |
ERA | -0.347 |
palp | -0.329 |
Token | needs |
Token ID | 2476 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
romy | +1.905 |
odan | +1.678 |
apeake | +1.674 |
inx | +1.603 |
antis | +1.571 |
Neg logit contributions | |
isers | -1.675 |
Agenda | -1.478 |
| -1.473 |
ERA | -1.301 |
SA | -1.234 |
Token | With |
Token ID | 3152 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
romy | +0.082 |
apeake | +0.073 |
odan | +0.073 |
inx | +0.071 |
antis | +0.069 |
Neg logit contributions | |
isers | -0.079 |
Agenda | -0.071 |
| -0.070 |
ERA | -0.063 |
palp | -0.059 |
Token | low |
Token ID | 1877 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
isers | +0.697 |
Agenda | +0.625 |
| +0.616 |
ERA | +0.562 |
palp | +0.538 |
Neg logit contributions | |
romy | -0.610 |
apeake | -0.539 |
odan | -0.539 |
inx | -0.517 |
antis | -0.511 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
romy | +1.682 |
apeake | +1.512 |
odan | +1.467 |
inx | +1.467 |
antis | +1.388 |
Neg logit contributions | |
isers | -1.884 |
Agenda | -1.761 |
| -1.726 |
ERA | -1.538 |
Gospel | -1.446 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
romy | +0.012 |
apeake | +0.011 |
odan | +0.011 |
inx | +0.010 |
antis | +0.010 |
Neg logit contributions | |
isers | -0.014 |
Agenda | -0.012 |
| -0.012 |
ERA | -0.011 |
palp | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
romy | +1.457 |
apeake | +1.304 |
odan | +1.300 |
inx | +1.263 |
antis | +1.229 |
Neg logit contributions | |
isers | -1.307 |
Agenda | -1.188 |
| -1.166 |
ERA | -1.036 |
palp | -0.974 |
Token | America |
Token ID | 2253 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
romy | +0.417 |
apeake | +0.370 |
odan | +0.370 |
inx | +0.358 |
antis | +0.349 |
Neg logit contributions | |
isers | -0.432 |
Agenda | -0.392 |
| -0.385 |
ERA | -0.347 |
palp | -0.329 |
Token | needs |
Token ID | 2476 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
romy | +1.905 |
odan | +1.678 |
apeake | +1.674 |
inx | +1.603 |
antis | +1.571 |
Neg logit contributions | |
isers | -1.675 |
Agenda | -1.478 |
| -1.473 |
ERA | -1.301 |
SA | -1.234 |
Token | future |
Token ID | 2003 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
romy | +1.173 |
apeake | +1.048 |
odan | +1.046 |
inx | +1.012 |
antis | +0.982 |
Neg logit contributions | |
isers | -1.117 |
Agenda | -1.023 |
| -1.007 |
ERA | -0.901 |
SA | -0.850 |
Token | migrants |
Token ID | 12783 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
romy | +0.607 |
apeake | +0.534 |
odan | +0.531 |
inx | +0.512 |
antis | +0.500 |
Neg logit contributions | |
isers | -0.754 |
Agenda | -0.688 |
| -0.677 |
ERA | -0.616 |
palp | -0.584 |
Token | 4 |
Token ID | 604 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
isers | +0.455 |
Agenda | +0.411 |
| +0.401 |
ERA | +0.366 |
palp | +0.351 |
Neg logit contributions | |
romy | -0.388 |
apeake | -0.343 |
odan | -0.343 |
inx | -0.333 |
antis | -0.327 |
Token | ways |
Token ID | 2842 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
romy | +0.617 |
apeake | +0.553 |
odan | +0.551 |
inx | +0.533 |
antis | +0.523 |
Neg logit contributions | |
isers | -0.556 |
Agenda | -0.500 |
| -0.492 |
ERA | -0.437 |
palp | -0.413 |
Token | it |
Token ID | 340 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
romy | +0.345 |
apeake | +0.309 |
odan | +0.308 |
inx | +0.298 |
antis | +0.292 |
Neg logit contributions | |
isers | -0.339 |
Agenda | -0.305 |
| -0.300 |
ERA | -0.268 |
palp | -0.255 |
Token | has |
Token ID | 468 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
romy | +0.391 |
apeake | +0.349 |
odan | +0.349 |
inx | +0.338 |
antis | +0.330 |
Neg logit contributions | |
isers | -0.381 |
Agenda | -0.344 |
| -0.338 |
ERA | -0.302 |
palp | -0.286 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
romy | +0.742 |
apeake | +0.638 |
odan | +0.629 |
inx | +0.606 |
antis | +0.581 |
Neg logit contributions | |
isers | -1.208 |
Agenda | -1.120 |
| -1.105 |
ERA | -1.014 |
palp | -0.967 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
romy | +1.305 |
odan | +1.176 |
apeake | +1.166 |
inx | +1.121 |
antis | +1.107 |
Neg logit contributions | |
isers | -1.128 |
Agenda | -1.020 |
| -1.010 |
ERA | -0.884 |
palp | -0.836 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
romy | +0.138 |
apeake | +0.123 |
odan | +0.123 |
inx | +0.119 |
antis | +0.117 |
Neg logit contributions | |
isers | -0.129 |
Agenda | -0.115 |
| -0.113 |
ERA | -0.101 |
palp | -0.096 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
romy | +1.061 |
apeake | +0.941 |
odan | +0.932 |
inx | +0.887 |
antis | +0.862 |
Neg logit contributions | |
isers | -1.558 |
Agenda | -1.435 |
| -1.429 |
ERA | -1.290 |
palp | -1.247 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
romy | +1.542 |
apeake | +1.380 |
odan | +1.358 |
inx | +1.300 |
antis | +1.270 |
Neg logit contributions | |
isers | -1.964 |
Agenda | -1.806 |
| -1.802 |
ERA | -1.636 |
SA | -1.540 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
romy | +1.288 |
apeake | +1.154 |
odan | +1.144 |
antis | +1.096 |
inx | +1.094 |
Neg logit contributions | |
isers | -1.178 |
Agenda | -1.068 |
| -1.058 |
ERA | -0.936 |
palp | -0.882 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
romy | +1.487 |
apeake | +1.313 |
odan | +1.295 |
inx | +1.264 |
antis | +1.230 |
Neg logit contributions | |
isers | -1.396 |
| -1.268 |
Agenda | -1.254 |
ERA | -1.124 |
palp | -1.057 |
Token | of |
Token ID | 286 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
romy | +1.060 |
apeake | +0.951 |
odan | +0.945 |
inx | +0.914 |
antis | +0.898 |
Neg logit contributions | |
isers | -0.937 |
Agenda | -0.845 |
| -0.832 |
ERA | -0.736 |
palp | -0.692 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
romy | +1.599 |
apeake | +1.421 |
odan | +1.414 |
inx | +1.351 |
antis | +1.327 |
Neg logit contributions | |
isers | -1.778 |
Agenda | -1.615 |
| -1.613 |
ERA | -1.443 |
palp | -1.369 |
Token | from |
Token ID | 422 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
romy | +0.750 |
odan | +0.664 |
apeake | +0.664 |
inx | +0.641 |
antis | +0.626 |
Neg logit contributions | |
isers | -0.807 |
Agenda | -0.727 |
| -0.719 |
ERA | -0.647 |
palp | -0.617 |
Token | Cleveland |
Token ID | 10306 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
romy | +0.696 |
odan | +0.615 |
apeake | +0.615 |
inx | +0.596 |
antis | +0.583 |
Neg logit contributions | |
isers | -0.760 |
Agenda | -0.688 |
| -0.678 |
ERA | -0.610 |
palp | -0.582 |
Token | Cavaliers |
Token ID | 29411 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
romy | +0.533 |
odan | +0.466 |
apeake | +0.464 |
inx | +0.449 |
antis | +0.440 |
Neg logit contributions | |
isers | -0.660 |
Agenda | -0.600 |
| -0.591 |
ERA | -0.537 |
palp | -0.513 |
Token | guard |
Token ID | 4860 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
romy | +0.344 |
odan | +0.307 |
apeake | +0.307 |
inx | +0.297 |
antis | +0.292 |
Neg logit contributions | |
isers | -0.338 |
Agenda | -0.304 |
| -0.298 |
ERA | -0.267 |
palp | -0.254 |
Token | J |
Token ID | 449 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
romy | +0.413 |
apeake | +0.369 |
odan | +0.369 |
inx | +0.357 |
antis | +0.351 |
Neg logit contributions | |
isers | -0.387 |
Agenda | -0.347 |
| -0.341 |
ERA | -0.304 |
palp | -0.289 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
romy | +1.005 |
apeake | +0.902 |
odan | +0.893 |
inx | +0.868 |
antis | +0.853 |
Neg logit contributions | |
isers | -0.962 |
Agenda | -0.863 |
| -0.852 |
ERA | -0.758 |
palp | -0.719 |
Token | R |
Token ID | 49 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
romy | +1.755 |
odan | +1.571 |
apeake | +1.557 |
antis | +1.499 |
inx | +1.496 |
Neg logit contributions | |
isers | -1.708 |
| -1.567 |
Agenda | -1.559 |
ERA | -1.391 |
SA | -1.325 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
isers | +0.011 |
Agenda | +0.010 |
| +0.010 |
ERA | +0.009 |
palp | +0.009 |
Neg logit contributions | |
romy | -0.012 |
apeake | -0.010 |
odan | -0.010 |
inx | -0.010 |
antis | -0.010 |
Token | Smith |
Token ID | 4176 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
romy | +0.127 |
apeake | +0.112 |
odan | +0.112 |
inx | +0.107 |
antis | +0.105 |
Neg logit contributions | |
isers | -0.160 |
Agenda | -0.145 |
| -0.143 |
ERA | -0.130 |
palp | -0.124 |
Token | in |
Token ID | 287 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
romy | +0.464 |
apeake | +0.414 |
odan | +0.413 |
inx | +0.400 |
antis | +0.393 |
Neg logit contributions | |
isers | -0.455 |
Agenda | -0.410 |
| -0.402 |
ERA | -0.361 |
palp | -0.343 |
Token | Game |
Token ID | 3776 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
romy | +0.435 |
odan | +0.387 |
apeake | +0.386 |
inx | +0.375 |
antis | +0.368 |
Neg logit contributions | |
isers | -0.428 |
Agenda | -0.386 |
| -0.379 |
ERA | -0.339 |
palp | -0.322 |
Token | : |
Token ID | 25 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
romy | +0.630 |
apeake | +0.545 |
odan | +0.538 |
inx | +0.513 |
antis | +0.500 |
Neg logit contributions | |
isers | -0.946 |
Agenda | -0.874 |
| -0.862 |
ERA | -0.786 |
palp | -0.754 |
Token | report |
Token ID | 989 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
isers | +1.367 |
Agenda | +1.244 |
| +1.208 |
ERA | +1.110 |
palp | +1.073 |
Neg logit contributions | |
romy | -0.998 |
odan | -0.869 |
apeake | -0.865 |
inx | -0.854 |
antis | -0.832 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
isers | +0.193 |
Agenda | +0.175 |
| +0.171 |
ERA | +0.156 |
palp | +0.149 |
Neg logit contributions | |
romy | -0.162 |
apeake | -0.143 |
odan | -0.143 |
inx | -0.138 |
antis | -0.135 |
Token | airline |
Token ID | 18091 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
isers | +0.443 |
Agenda | +0.400 |
| +0.390 |
ERA | +0.355 |
palp | +0.340 |
Neg logit contributions | |
romy | -0.392 |
apeake | -0.347 |
odan | -0.346 |
inx | -0.336 |
antis | -0.330 |
Token | takes |
Token ID | 2753 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
isers | +0.703 |
Agenda | +0.641 |
| +0.617 |
ERA | +0.558 |
palp | +0.534 |
Neg logit contributions | |
romy | -0.686 |
apeake | -0.614 |
odan | -0.612 |
inx | -0.594 |
antis | -0.583 |
Token | steps |
Token ID | 4831 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
isers | +0.036 |
Agenda | +0.033 |
| +0.033 |
ERA | +0.030 |
palp | +0.029 |
Neg logit contributions | |
romy | -0.025 |
apeake | -0.022 |
odan | -0.022 |
inx | -0.021 |
antis | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
romy | +1.808 |
apeake | +1.657 |
odan | +1.646 |
inx | +1.567 |
antis | +1.557 |
Neg logit contributions | |
isers | -1.568 |
| -1.422 |
Agenda | -1.406 |
ERA | -1.241 |
SA | -1.160 |
Token | open |
Token ID | 1280 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
romy | +1.113 |
apeake | +1.005 |
odan | +0.998 |
inx | +0.975 |
antis | +0.956 |
Neg logit contributions | |
isers | -0.912 |
| -0.811 |
Agenda | -0.807 |
ERA | -0.714 |
palp | -0.676 |
Token | flights |
Token ID | 13956 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
isers | +0.083 |
Agenda | +0.075 |
| +0.073 |
ERA | +0.066 |
palp | +0.063 |
Neg logit contributions | |
romy | -0.076 |
apeake | -0.068 |
odan | -0.068 |
inx | -0.065 |
antis | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
isers | +0.404 |
Agenda | +0.361 |
| +0.350 |
ERA | +0.316 |
palp | +0.299 |
Neg logit contributions | |
romy | -0.420 |
odan | -0.375 |
apeake | -0.375 |
inx | -0.365 |
antis | -0.360 |
Token | US |
Token ID | 1294 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
isers | +0.003 |
Agenda | +0.002 |
| +0.002 |
ERA | +0.002 |
palp | +0.002 |
Neg logit contributions | |
romy | -0.003 |
odan | -0.003 |
apeake | -0.003 |
inx | -0.003 |
antis | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
isers | +0.168 |
Agenda | +0.152 |
| +0.148 |
ERA | +0.133 |
palp | +0.127 |
Neg logit contributions | |
romy | -0.171 |
odan | -0.152 |
apeake | -0.152 |
inx | -0.147 |
antis | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
romy | +0.083 |
apeake | +0.074 |
odan | +0.074 |
inx | +0.071 |
antis | +0.070 |
Neg logit contributions | |
isers | -0.087 |
Agenda | -0.079 |
| -0.077 |
ERA | -0.070 |
palp | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
isers | +0.044 |
Agenda | +0.039 |
| +0.039 |
ERA | +0.035 |
palp | +0.033 |
Neg logit contributions | |
romy | -0.042 |
apeake | -0.038 |
odan | -0.038 |
inx | -0.036 |
antis | -0.036 |
Token | J |
Token ID | 41 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
romy | +0.090 |
apeake | +0.080 |
odan | +0.080 |
inx | +0.078 |
antis | +0.076 |
Neg logit contributions | |
isers | -0.087 |
Agenda | -0.078 |
| -0.077 |
ERA | -0.069 |
palp | -0.066 |
Token | ER |
Token ID | 1137 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
romy | +0.114 |
apeake | +0.101 |
odan | +0.101 |
inx | +0.097 |
antis | +0.096 |
Neg logit contributions | |
isers | -0.128 |
Agenda | -0.116 |
| -0.114 |
ERA | -0.103 |
palp | -0.098 |
Token | US |
Token ID | 2937 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
romy | +0.302 |
apeake | +0.273 |
odan | +0.273 |
inx | +0.266 |
antis | +0.262 |
Neg logit contributions | |
isers | -0.225 |
Agenda | -0.199 |
| -0.195 |
ERA | -0.171 |
palp | -0.160 |
Token | AL |
Token ID | 1847 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
romy | +1.540 |
odan | +1.351 |
apeake | +1.349 |
inx | +1.309 |
antis | +1.246 |
Neg logit contributions | |
isers | -1.865 |
Agenda | -1.710 |
| -1.707 |
ERA | -1.573 |
SA | -1.492 |
Token | EM |
Token ID | 3620 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
isers | +0.727 |
Agenda | +0.624 |
| +0.586 |
ERA | +0.492 |
palp | +0.465 |
Neg logit contributions | |
romy | -1.364 |
apeake | -1.251 |
odan | -1.239 |
inx | -1.228 |
antis | -1.210 |
Token | — |
Token ID | 851 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
isers | +0.260 |
Agenda | +0.232 |
| +0.227 |
ERA | +0.203 |
palp | +0.194 |
Neg logit contributions | |
romy | -0.279 |
apeake | -0.250 |
odan | -0.249 |
inx | -0.242 |
antis | -0.237 |
Token | Israeli |
Token ID | 6085 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
romy | +0.061 |
apeake | +0.054 |
odan | +0.054 |
inx | +0.052 |
antis | +0.051 |
Neg logit contributions | |
isers | -0.066 |
Agenda | -0.060 |
| -0.058 |
ERA | -0.053 |
palp | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
romy | +0.254 |
apeake | +0.219 |
odan | +0.219 |
inx | +0.210 |
antis | +0.205 |
Neg logit contributions | |
isers | -0.379 |
Agenda | -0.348 |
| -0.343 |
ERA | -0.313 |
palp | -0.301 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
isers | +0.076 |
Agenda | +0.069 |
| +0.067 |
ERA | +0.060 |
palp | +0.058 |
Neg logit contributions | |
romy | -0.076 |
apeake | -0.068 |
odan | -0.068 |
inx | -0.066 |
antis | -0.065 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
romy | +1.037 |
apeake | +0.915 |
odan | +0.905 |
inx | +0.864 |
antis | +0.837 |
Neg logit contributions | |
isers | -1.499 |
Agenda | -1.377 |
| -1.365 |
ERA | -1.232 |
palp | -1.191 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
romy | +1.684 |
apeake | +1.523 |
odan | +1.504 |
inx | +1.458 |
antis | +1.427 |
Neg logit contributions | |
isers | -1.531 |
Agenda | -1.379 |
| -1.366 |
ERA | -1.216 |
SA | -1.133 |
Token | in |
Token ID | 287 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
romy | +1.491 |
apeake | +1.338 |
odan | +1.319 |
antis | +1.268 |
inx | +1.260 |
Neg logit contributions | |
isers | -1.315 |
Agenda | -1.188 |
| -1.175 |
ERA | -1.035 |
palp | -0.974 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
romy | +1.489 |
apeake | +1.317 |
odan | +1.297 |
inx | +1.267 |
antis | +1.236 |
Neg logit contributions | |
isers | -1.379 |
| -1.245 |
Agenda | -1.237 |
ERA | -1.104 |
palp | -1.041 |
Token | of |
Token ID | 286 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
romy | +0.974 |
apeake | +0.870 |
odan | +0.865 |
inx | +0.838 |
antis | +0.821 |
Neg logit contributions | |
isers | -0.917 |
Agenda | -0.827 |
| -0.815 |
ERA | -0.725 |
palp | -0.685 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
romy | +1.686 |
apeake | +1.500 |
odan | +1.489 |
inx | +1.433 |
antis | +1.410 |
Neg logit contributions | |
isers | -1.725 |
Agenda | -1.554 |
| -1.551 |
ERA | -1.375 |
palp | -1.312 |
Token | probe |
Token ID | 12774 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
romy | +0.538 |
apeake | +0.479 |
odan | +0.479 |
inx | +0.462 |
antis | +0.454 |
Neg logit contributions | |
isers | -0.541 |
Agenda | -0.487 |
| -0.480 |
ERA | -0.429 |
palp | -0.409 |
Token | : |
Token ID | 25 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
romy | +0.755 |
apeake | +0.669 |
odan | +0.661 |
inx | +0.638 |
antis | +0.625 |
Neg logit contributions | |
isers | -0.822 |
Agenda | -0.749 |
| -0.736 |
ERA | -0.660 |
palp | -0.627 |
Token | report |
Token ID | 989 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
isers | +1.000 |
Agenda | +0.916 |
| +0.893 |
ERA | +0.817 |
palp | +0.786 |
Neg logit contributions | |
romy | -0.766 |
odan | -0.674 |
apeake | -0.668 |
inx | -0.658 |
antis | -0.642 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
romy | +0.177 |
apeake | +0.157 |
odan | +0.157 |
inx | +0.152 |
antis | +0.149 |
Neg logit contributions | |
isers | -0.193 |
Agenda | -0.175 |
| -0.171 |
ERA | -0.155 |
palp | -0.148 |
Token | a |
Token ID | 257 |
Feature activation | +2.50e-04 |
Pos logit contributions | |
isers | +0.086 |
Agenda | +0.077 |
| +0.076 |
ERA | +0.068 |
palp | +0.065 |
Neg logit contributions | |
romy | -0.084 |
odan | -0.075 |
apeake | -0.075 |
inx | -0.072 |
antis | -0.071 |
Token | Human |
Token ID | 5524 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
isers | +0.000 |
Agenda | +0.000 |
| +0.000 |
ERA | +0.000 |
palp | +0.000 |
Neg logit contributions | |
romy | -0.000 |
odan | -0.000 |
apeake | -0.000 |
inx | -0.000 |
antis | -0.000 |
Token | Rights |
Token ID | 6923 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
isers | +0.090 |
Agenda | +0.078 |
| +0.076 |
ERA | +0.066 |
palp | +0.061 |
Neg logit contributions | |
romy | -0.143 |
odan | -0.130 |
apeake | -0.130 |
inx | -0.127 |
antis | -0.125 |
Token | Watch |
Token ID | 6305 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
isers | +0.083 |
Agenda | +0.076 |
| +0.075 |
ERA | +0.069 |
palp | +0.066 |
Neg logit contributions | |
romy | -0.056 |
odan | -0.048 |
apeake | -0.048 |
inx | -0.046 |
antis | -0.045 |
Token | ( |
Token ID | 357 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
isers | +0.255 |
Agenda | +0.231 |
| +0.227 |
ERA | +0.206 |
palp | +0.197 |
Neg logit contributions | |
romy | -0.217 |
odan | -0.191 |
apeake | -0.190 |
inx | -0.184 |
antis | -0.180 |
Token | HR |
Token ID | 17184 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
romy | +0.697 |
odan | +0.636 |
apeake | +0.636 |
inx | +0.619 |
antis | +0.611 |
Neg logit contributions | |
isers | -0.403 |
Agenda | -0.348 |
| -0.338 |
ERA | -0.290 |
palp | -0.267 |
Token | W |
Token ID | 54 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
romy | +1.640 |
odan | +1.456 |
apeake | +1.449 |
inx | +1.390 |
antis | +1.372 |
Neg logit contributions | |
isers | -1.757 |
Agenda | -1.597 |
| -1.570 |
ERA | -1.423 |
SA | -1.359 |
Token | ) |
Token ID | 8 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
romy | +0.229 |
apeake | +0.203 |
odan | +0.203 |
inx | +0.197 |
antis | +0.193 |
Neg logit contributions | |
isers | -0.233 |
Agenda | -0.210 |
| -0.206 |
ERA | -0.185 |
palp | -0.176 |
Token | report |
Token ID | 989 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
isers | +0.041 |
Agenda | +0.037 |
| +0.036 |
ERA | +0.033 |
palp | +0.032 |
Neg logit contributions | |
romy | -0.034 |
apeake | -0.030 |
odan | -0.030 |
inx | -0.029 |
antis | -0.028 |
Token | says |
Token ID | 1139 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
isers | +0.220 |
Agenda | +0.198 |
| +0.193 |
ERA | +0.173 |
palp | +0.165 |
Neg logit contributions | |
romy | -0.227 |
apeake | -0.202 |
odan | -0.202 |
inx | -0.196 |
antis | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
isers | +0.092 |
Agenda | +0.083 |
| +0.081 |
ERA | +0.073 |
palp | +0.069 |
Neg logit contributions | |
romy | -0.094 |
apeake | -0.083 |
odan | -0.083 |
inx | -0.081 |
antis | -0.079 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
romy | +0.138 |
apeake | +0.123 |
odan | +0.123 |
inx | +0.119 |
antis | +0.117 |
Neg logit contributions | |
isers | -0.129 |
Agenda | -0.115 |
| -0.113 |
ERA | -0.101 |
palp | -0.096 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
romy | +1.061 |
apeake | +0.941 |
odan | +0.932 |
inx | +0.887 |
antis | +0.862 |
Neg logit contributions | |
isers | -1.558 |
Agenda | -1.435 |
| -1.429 |
ERA | -1.290 |
palp | -1.247 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
romy | +1.542 |
apeake | +1.380 |
odan | +1.358 |
inx | +1.300 |
antis | +1.270 |
Neg logit contributions | |
isers | -1.964 |
Agenda | -1.806 |
| -1.802 |
ERA | -1.636 |
SA | -1.540 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
romy | +1.288 |
apeake | +1.154 |
odan | +1.144 |
antis | +1.096 |
inx | +1.094 |
Neg logit contributions | |
isers | -1.178 |
Agenda | -1.068 |
| -1.058 |
ERA | -0.936 |
palp | -0.882 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
romy | +1.487 |
apeake | +1.313 |
odan | +1.295 |
inx | +1.264 |
antis | +1.230 |
Neg logit contributions | |
isers | -1.396 |
| -1.268 |
Agenda | -1.254 |
ERA | -1.124 |
palp | -1.057 |
Token | of |
Token ID | 286 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
romy | +1.060 |
apeake | +0.951 |
odan | +0.945 |
inx | +0.914 |
antis | +0.898 |
Neg logit contributions | |
isers | -0.937 |
Agenda | -0.845 |
| -0.832 |
ERA | -0.736 |
palp | -0.692 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
romy | +1.599 |
apeake | +1.421 |
odan | +1.414 |
inx | +1.351 |
antis | +1.327 |
Neg logit contributions | |
isers | -1.778 |
Agenda | -1.615 |
| -1.613 |
ERA | -1.443 |
palp | -1.369 |
Token | probe |
Token ID | 12774 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
romy | +0.260 |
apeake | +0.231 |
odan | +0.231 |
inx | +0.223 |
antis | +0.219 |
Neg logit contributions | |
isers | -0.269 |
Agenda | -0.243 |
| -0.239 |
ERA | -0.215 |
palp | -0.204 |
Token | : |
Token ID | 25 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
romy | +0.630 |
apeake | +0.545 |
odan | +0.538 |
inx | +0.513 |
antis | +0.500 |
Neg logit contributions | |
isers | -0.946 |
Agenda | -0.874 |
| -0.862 |
ERA | -0.786 |
palp | -0.754 |
Token | report |
Token ID | 989 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
isers | +1.367 |
Agenda | +1.244 |
| +1.208 |
ERA | +1.110 |
palp | +1.073 |
Neg logit contributions | |
romy | -0.998 |
odan | -0.869 |
apeake | -0.865 |
inx | -0.854 |
antis | -0.832 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
isers | +0.193 |
Agenda | +0.175 |
| +0.171 |
ERA | +0.156 |
palp | +0.149 |
Neg logit contributions | |
romy | -0.162 |
apeake | -0.143 |
odan | -0.143 |
inx | -0.138 |
antis | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
isers | +0.483 |
Agenda | +0.434 |
| +0.424 |
ERA | +0.382 |
palp | +0.364 |
Neg logit contributions | |
romy | -0.475 |
apeake | -0.423 |
odan | -0.421 |
inx | -0.409 |
antis | -0.402 |
Token | say |
Token ID | 910 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
isers | +0.032 |
Agenda | +0.028 |
| +0.028 |
ERA | +0.024 |
palp | +0.022 |
Neg logit contributions | |
romy | -0.050 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.044 |
antis | -0.043 |
Token | today |
Token ID | 1909 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
romy | +0.187 |
apeake | +0.168 |
odan | +0.168 |
inx | +0.163 |
antis | +0.160 |
Neg logit contributions | |
isers | -0.172 |
Agenda | -0.154 |
| -0.151 |
ERA | -0.135 |
palp | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
romy | +0.268 |
apeake | +0.239 |
odan | +0.239 |
inx | +0.232 |
antis | +0.228 |
Neg logit contributions | |
isers | -0.261 |
Agenda | -0.235 |
| -0.230 |
ERA | -0.206 |
palp | -0.196 |
Token | about |
Token ID | 546 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
romy | +0.095 |
apeake | +0.085 |
odan | +0.085 |
inx | +0.082 |
antis | +0.081 |
Neg logit contributions | |
isers | -0.086 |
Agenda | -0.077 |
| -0.075 |
ERA | -0.067 |
palp | -0.064 |
Token | Dw |
Token ID | 19113 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
romy | +0.062 |
apeake | +0.055 |
odan | +0.055 |
inx | +0.054 |
antis | +0.053 |
Neg logit contributions | |
isers | -0.066 |
Agenda | -0.059 |
| -0.058 |
ERA | -0.053 |
palp | -0.050 |
Token | y |
Token ID | 88 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
romy | +1.344 |
apeake | +1.155 |
odan | +1.134 |
inx | +1.090 |
antis | +1.072 |
Neg logit contributions | |
isers | -2.003 |
Agenda | -1.828 |
| -1.818 |
ERA | -1.648 |
Gospel | -1.581 |
Token | ane |
Token ID | 1531 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
romy | +0.865 |
apeake | +0.791 |
odan | +0.790 |
inx | +0.770 |
antis | +0.757 |
Neg logit contributions | |
isers | -0.456 |
Agenda | -0.388 |
| -0.380 |
ERA | -0.317 |
palp | -0.291 |
Token | Wade |
Token ID | 19136 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
romy | +0.391 |
apeake | +0.336 |
odan | +0.335 |
inx | +0.320 |
antis | +0.313 |
Neg logit contributions | |
isers | -0.630 |
Agenda | -0.582 |
| -0.575 |
ERA | -0.527 |
palp | -0.506 |
Token | , |
Token ID | 11 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
romy | +0.035 |
apeake | +0.031 |
odan | +0.031 |
inx | +0.030 |
antis | +0.029 |
Neg logit contributions | |
isers | -0.037 |
Agenda | -0.034 |
| -0.033 |
ERA | -0.030 |
palp | -0.029 |
Token | Chris |
Token ID | 5180 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
romy | +0.193 |
apeake | +0.171 |
odan | +0.171 |
inx | +0.165 |
antis | +0.162 |
Neg logit contributions | |
isers | -0.213 |
Agenda | -0.193 |
| -0.189 |
ERA | -0.171 |
palp | -0.163 |
Token | : |
Token ID | 25 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
romy | +0.621 |
apeake | +0.548 |
odan | +0.543 |
inx | +0.523 |
antis | +0.512 |
Neg logit contributions | |
isers | -0.718 |
Agenda | -0.656 |
| -0.645 |
ERA | -0.581 |
palp | -0.554 |
Token | report |
Token ID | 989 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
isers | +1.136 |
Agenda | +1.039 |
| +1.009 |
ERA | +0.925 |
palp | +0.893 |
Neg logit contributions | |
romy | -0.839 |
odan | -0.737 |
apeake | -0.731 |
inx | -0.720 |
antis | -0.703 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
isers | +0.053 |
Agenda | +0.048 |
| +0.047 |
ERA | +0.043 |
palp | +0.041 |
Neg logit contributions | |
romy | -0.043 |
apeake | -0.038 |
odan | -0.038 |
inx | -0.036 |
antis | -0.036 |
Token | airline |
Token ID | 18091 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
isers | +0.412 |
Agenda | +0.371 |
| +0.362 |
ERA | +0.328 |
palp | +0.313 |
Neg logit contributions | |
romy | -0.386 |
apeake | -0.342 |
odan | -0.341 |
inx | -0.332 |
antis | -0.326 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
isers | +0.598 |
Agenda | +0.542 |
| +0.524 |
ERA | +0.473 |
palp | +0.452 |
Neg logit contributions | |
romy | -0.598 |
apeake | -0.535 |
odan | -0.534 |
inx | -0.518 |
antis | -0.509 |
Token | steps |
Token ID | 4831 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
isers | +0.143 |
Agenda | +0.131 |
| +0.128 |
ERA | +0.118 |
palp | +0.113 |
Neg logit contributions | |
romy | -0.095 |
odan | -0.082 |
apeake | -0.081 |
inx | -0.078 |
antis | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
romy | +1.722 |
apeake | +1.575 |
odan | +1.566 |
inx | +1.491 |
antis | +1.481 |
Neg logit contributions | |
isers | -1.498 |
| -1.355 |
Agenda | -1.343 |
ERA | -1.185 |
SA | -1.107 |
Token | open |
Token ID | 1280 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
romy | +1.222 |
apeake | +1.100 |
odan | +1.090 |
inx | +1.064 |
antis | +1.041 |
Neg logit contributions | |
isers | -1.091 |
| -0.979 |
Agenda | -0.972 |
ERA | -0.869 |
palp | -0.824 |
Token | flights |
Token ID | 13956 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
isers | +0.168 |
Agenda | +0.153 |
| +0.149 |
ERA | +0.135 |
palp | +0.128 |
Neg logit contributions | |
romy | -0.152 |
apeake | -0.135 |
odan | -0.135 |
inx | -0.131 |
antis | -0.128 |
Token | to |
Token ID | 284 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
isers | +0.343 |
Agenda | +0.305 |
| +0.297 |
ERA | +0.266 |
palp | +0.252 |
Neg logit contributions | |
romy | -0.374 |
odan | -0.335 |
apeake | -0.335 |
inx | -0.326 |
antis | -0.322 |
Token | US |
Token ID | 1294 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
romy | +0.040 |
odan | +0.036 |
apeake | +0.036 |
inx | +0.035 |
antis | +0.034 |
Neg logit contributions | |
isers | -0.039 |
Agenda | -0.035 |
| -0.034 |
ERA | -0.031 |
palp | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
romy | +0.450 |
apeake | +0.403 |
odan | +0.401 |
inx | +0.388 |
antis | +0.379 |
Neg logit contributions | |
isers | -0.464 |
Agenda | -0.419 |
| -0.412 |
ERA | -0.370 |
palp | -0.352 |
Token | has |
Token ID | 468 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
romy | +0.664 |
apeake | +0.596 |
odan | +0.595 |
inx | +0.577 |
antis | +0.561 |
Neg logit contributions | |
isers | -0.626 |
Agenda | -0.565 |
| -0.557 |
ERA | -0.495 |
palp | -0.469 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
romy | +1.082 |
apeake | +0.940 |
odan | +0.917 |
inx | +0.889 |
antis | +0.847 |
Neg logit contributions | |
isers | -1.723 |
Agenda | -1.597 |
| -1.582 |
ERA | -1.449 |
palp | -1.380 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
romy | +1.147 |
odan | +1.029 |
apeake | +1.026 |
inx | +0.984 |
antis | +0.971 |
Neg logit contributions | |
isers | -1.021 |
Agenda | -0.922 |
| -0.911 |
ERA | -0.802 |
palp | -0.761 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
isers | +0.076 |
Agenda | +0.069 |
| +0.067 |
ERA | +0.060 |
palp | +0.058 |
Neg logit contributions | |
romy | -0.076 |
apeake | -0.068 |
odan | -0.068 |
inx | -0.066 |
antis | -0.065 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
romy | +1.037 |
apeake | +0.915 |
odan | +0.905 |
inx | +0.864 |
antis | +0.837 |
Neg logit contributions | |
isers | -1.499 |
Agenda | -1.377 |
| -1.365 |
ERA | -1.232 |
palp | -1.191 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
romy | +1.684 |
apeake | +1.523 |
odan | +1.504 |
inx | +1.458 |
antis | +1.427 |
Neg logit contributions | |
isers | -1.531 |
Agenda | -1.379 |
| -1.366 |
ERA | -1.216 |
SA | -1.133 |
Token | in |
Token ID | 287 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
romy | +1.491 |
apeake | +1.338 |
odan | +1.319 |
antis | +1.268 |
inx | +1.260 |
Neg logit contributions | |
isers | -1.315 |
Agenda | -1.188 |
| -1.175 |
ERA | -1.035 |
palp | -0.974 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
romy | +1.489 |
apeake | +1.317 |
odan | +1.297 |
inx | +1.267 |
antis | +1.236 |
Neg logit contributions | |
isers | -1.379 |
| -1.245 |
Agenda | -1.237 |
ERA | -1.104 |
palp | -1.041 |
Token | of |
Token ID | 286 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
romy | +0.974 |
apeake | +0.870 |
odan | +0.865 |
inx | +0.838 |
antis | +0.821 |
Neg logit contributions | |
isers | -0.917 |
Agenda | -0.827 |
| -0.815 |
ERA | -0.725 |
palp | -0.685 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
romy | +1.686 |
apeake | +1.500 |
odan | +1.489 |
inx | +1.433 |
antis | +1.410 |
Neg logit contributions | |
isers | -1.725 |
Agenda | -1.554 |
| -1.551 |
ERA | -1.375 |
palp | -1.312 |
Token | planetary |
Token ID | 27047 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
romy | +0.323 |
apeake | +0.290 |
odan | +0.290 |
inx | +0.281 |
antis | +0.276 |
Neg logit contributions | |
isers | -0.287 |
Agenda | -0.257 |
| -0.251 |
ERA | -0.224 |
palp | -0.212 |
Token | system |
Token ID | 1080 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
romy | +0.375 |
apeake | +0.335 |
odan | +0.334 |
inx | +0.324 |
antis | +0.318 |
Neg logit contributions | |
isers | -0.362 |
Agenda | -0.326 |
| -0.320 |
ERA | -0.287 |
palp | -0.272 |
Token | revis |
Token ID | 22124 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
romy | +0.317 |
apeake | +0.283 |
odan | +0.282 |
inx | +0.273 |
antis | +0.268 |
Neg logit contributions | |
isers | -0.317 |
Agenda | -0.286 |
| -0.280 |
ERA | -0.252 |
palp | -0.239 |
Token | ited |
Token ID | 863 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
romy | +0.188 |
apeake | +0.166 |
odan | +0.166 |
inx | +0.160 |
antis | +0.157 |
Neg logit contributions | |
isers | -0.221 |
Agenda | -0.201 |
| -0.197 |
ERA | -0.179 |
palp | -0.171 |
Token | by |
Token ID | 416 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
romy | +0.111 |
apeake | +0.099 |
odan | +0.099 |
inx | +0.096 |
antis | +0.094 |
Neg logit contributions | |
isers | -0.112 |
Agenda | -0.101 |
| -0.099 |
ERA | -0.089 |
palp | -0.085 |
Token | HAR |
Token ID | 43638 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
romy | +0.140 |
apeake | +0.124 |
odan | +0.124 |
inx | +0.120 |
antis | +0.118 |
Neg logit contributions | |
isers | -0.148 |
Agenda | -0.134 |
| -0.131 |
ERA | -0.118 |
palp | -0.113 |
Token | PS |
Token ID | 3705 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
romy | +1.254 |
apeake | +1.092 |
odan | +1.088 |
inx | +1.040 |
antis | +1.008 |
Neg logit contributions | |
isers | -1.946 |
Agenda | -1.790 |
| -1.787 |
ERA | -1.643 |
palp | -1.577 |
Token | - |
Token ID | 12 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
romy | +0.683 |
odan | +0.606 |
apeake | +0.606 |
inx | +0.587 |
antis | +0.575 |
Neg logit contributions | |
isers | -0.703 |
Agenda | -0.635 |
| -0.625 |
ERA | -0.562 |
palp | -0.534 |
Token | N |
Token ID | 45 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
romy | +0.334 |
apeake | +0.297 |
odan | +0.297 |
inx | +0.287 |
antis | +0.281 |
Neg logit contributions | |
isers | -0.343 |
Agenda | -0.310 |
| -0.304 |
ERA | -0.273 |
palp | -0.260 |
Token | : |
Token ID | 25 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
romy | +0.582 |
apeake | +0.520 |
odan | +0.519 |
inx | +0.501 |
antis | +0.491 |
Neg logit contributions | |
isers | -0.578 |
Agenda | -0.521 |
| -0.512 |
ERA | -0.460 |
palp | -0.436 |
Token | A |
Token ID | 317 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
romy | +0.405 |
apeake | +0.359 |
odan | +0.359 |
inx | +0.347 |
antis | +0.340 |
Neg logit contributions | |
isers | -0.434 |
Agenda | -0.393 |
| -0.386 |
ERA | -0.348 |
palp | -0.332 |
Token | it |
Token ID | 340 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
romy | +0.147 |
apeake | +0.130 |
odan | +0.130 |
inx | +0.126 |
antis | +0.124 |
Neg logit contributions | |
isers | -0.154 |
Agenda | -0.139 |
| -0.137 |
ERA | -0.123 |
palp | -0.117 |
Token | has |
Token ID | 468 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
romy | +0.330 |
apeake | +0.294 |
odan | +0.294 |
inx | +0.285 |
antis | +0.278 |
Neg logit contributions | |
isers | -0.330 |
Agenda | -0.297 |
| -0.292 |
ERA | -0.262 |
palp | -0.249 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
romy | +1.071 |
apeake | +0.920 |
odan | +0.903 |
inx | +0.873 |
antis | +0.833 |
Neg logit contributions | |
isers | -1.684 |
Agenda | -1.563 |
| -1.546 |
ERA | -1.417 |
palp | -1.349 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
romy | +1.006 |
odan | +0.899 |
apeake | +0.897 |
inx | +0.862 |
antis | +0.849 |
Neg logit contributions | |
isers | -0.922 |
Agenda | -0.836 |
| -0.826 |
ERA | -0.728 |
palp | -0.691 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
romy | +0.131 |
apeake | +0.117 |
odan | +0.117 |
inx | +0.114 |
antis | +0.112 |
Neg logit contributions | |
isers | -0.127 |
Agenda | -0.114 |
| -0.111 |
ERA | -0.100 |
palp | -0.095 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
romy | +1.181 |
apeake | +1.050 |
odan | +1.038 |
inx | +0.989 |
antis | +0.956 |
Neg logit contributions | |
isers | -1.669 |
Agenda | -1.532 |
| -1.526 |
ERA | -1.374 |
palp | -1.328 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
romy | +1.708 |
apeake | +1.552 |
odan | +1.537 |
inx | +1.484 |
antis | +1.459 |
Neg logit contributions | |
isers | -1.489 |
Agenda | -1.339 |
| -1.326 |
ERA | -1.179 |
SA | -1.088 |
Token | in |
Token ID | 287 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
romy | +1.312 |
apeake | +1.174 |
odan | +1.163 |
antis | +1.115 |
inx | +1.113 |
Neg logit contributions | |
isers | -1.199 |
Agenda | -1.087 |
| -1.075 |
ERA | -0.954 |
palp | -0.899 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
romy | +1.450 |
apeake | +1.284 |
odan | +1.267 |
inx | +1.236 |
antis | +1.203 |
Neg logit contributions | |
isers | -1.314 |
| -1.186 |
Agenda | -1.178 |
ERA | -1.051 |
palp | -0.991 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
romy | +0.819 |
apeake | +0.734 |
odan | +0.731 |
inx | +0.707 |
antis | +0.695 |
Neg logit contributions | |
isers | -0.734 |
Agenda | -0.660 |
| -0.649 |
ERA | -0.576 |
palp | -0.543 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
romy | +1.262 |
apeake | +1.123 |
odan | +1.117 |
inx | +1.075 |
antis | +1.056 |
Neg logit contributions | |
isers | -1.303 |
Agenda | -1.175 |
| -1.167 |
ERA | -1.040 |
palp | -0.992 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
romy | +0.174 |
apeake | +0.153 |
odan | +0.153 |
inx | +0.147 |
antis | +0.144 |
Neg logit contributions | |
isers | -0.212 |
Agenda | -0.193 |
| -0.189 |
ERA | -0.172 |
palp | -0.164 |
Token | : |
Token ID | 25 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
isers | +0.089 |
Agenda | +0.080 |
| +0.078 |
ERA | +0.071 |
palp | +0.067 |
Neg logit contributions | |
romy | -0.084 |
apeake | -0.075 |
odan | -0.075 |
inx | -0.072 |
antis | -0.071 |
Token | ' |
Token ID | 705 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
isers | +1.055 |
Agenda | +0.960 |
| +0.937 |
ERA | +0.856 |
palp | +0.837 |
Neg logit contributions | |
romy | -0.832 |
odan | -0.731 |
apeake | -0.726 |
inx | -0.705 |
antis | -0.693 |
Token | Damn |
Token ID | 43343 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
romy | +0.433 |
odan | +0.386 |
apeake | +0.386 |
inx | +0.372 |
antis | +0.364 |
Neg logit contributions | |
isers | -0.437 |
Agenda | -0.393 |
| -0.386 |
ERA | -0.347 |
palp | -0.329 |
Token | right |
Token ID | 826 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
romy | +0.446 |
odan | +0.399 |
apeake | +0.399 |
inx | +0.385 |
antis | +0.378 |
Neg logit contributions | |
isers | -0.432 |
Agenda | -0.390 |
| -0.381 |
ERA | -0.342 |
palp | -0.324 |
Token | ' |
Token ID | 6 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
romy | +0.467 |
apeake | +0.415 |
odan | +0.415 |
inx | +0.399 |
antis | +0.391 |
Neg logit contributions | |
isers | -0.522 |
Agenda | -0.476 |
| -0.467 |
ERA | -0.421 |
palp | -0.401 |
Token | I |
Token ID | 314 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
romy | +1.689 |
odan | +1.549 |
apeake | +1.547 |
inx | +1.482 |
antis | +1.438 |
Neg logit contributions | |
isers | -1.475 |
Agenda | -1.327 |
| -1.322 |
ERA | -1.164 |
palp | -1.070 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
romy | +0.915 |
odan | +0.834 |
apeake | +0.829 |
inx | +0.812 |
antis | +0.795 |
Neg logit contributions | |
isers | -0.636 |
Agenda | -0.568 |
| -0.560 |
ERA | -0.488 |
palp | -0.454 |
Token | make |
Token ID | 787 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
isers | +1.017 |
Agenda | +0.921 |
| +0.885 |
ERA | +0.808 |
palp | +0.783 |
Neg logit contributions | |
romy | -0.925 |
odan | -0.824 |
apeake | -0.815 |
inx | -0.797 |
antis | -0.764 |
Token | the |
Token ID | 262 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
isers | +0.045 |
Agenda | +0.040 |
| +0.039 |
ERA | +0.035 |
palp | +0.033 |
Neg logit contributions | |
romy | -0.051 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.044 |
antis | -0.043 |
Token | large |
Token ID | 1588 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
romy | +0.075 |
apeake | +0.067 |
odan | +0.067 |
inx | +0.065 |
antis | +0.064 |
Neg logit contributions | |
isers | -0.071 |
Agenda | -0.064 |
| -0.063 |
ERA | -0.056 |
palp | -0.053 |
Token | : |
Token ID | 25 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
romy | +0.755 |
apeake | +0.669 |
odan | +0.661 |
inx | +0.638 |
antis | +0.625 |
Neg logit contributions | |
isers | -0.822 |
Agenda | -0.749 |
| -0.736 |
ERA | -0.660 |
palp | -0.627 |
Token | report |
Token ID | 989 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
isers | +1.000 |
Agenda | +0.916 |
| +0.893 |
ERA | +0.817 |
palp | +0.786 |
Neg logit contributions | |
romy | -0.766 |
odan | -0.674 |
apeake | -0.668 |
inx | -0.658 |
antis | -0.642 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
romy | +0.177 |
apeake | +0.157 |
odan | +0.157 |
inx | +0.152 |
antis | +0.149 |
Neg logit contributions | |
isers | -0.193 |
Agenda | -0.175 |
| -0.171 |
ERA | -0.155 |
palp | -0.148 |
Token | airline |
Token ID | 18091 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
isers | +0.481 |
Agenda | +0.432 |
| +0.420 |
ERA | +0.379 |
palp | +0.362 |
Neg logit contributions | |
romy | -0.485 |
apeake | -0.432 |
odan | -0.431 |
inx | -0.419 |
antis | -0.412 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
isers | +0.611 |
Agenda | +0.554 |
| +0.535 |
ERA | +0.482 |
palp | +0.460 |
Neg logit contributions | |
romy | -0.627 |
apeake | -0.562 |
odan | -0.560 |
inx | -0.544 |
antis | -0.535 |
Token | steps |
Token ID | 4831 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
isers | +0.168 |
Agenda | +0.155 |
| +0.152 |
ERA | +0.139 |
palp | +0.134 |
Neg logit contributions | |
romy | -0.109 |
odan | -0.093 |
apeake | -0.093 |
inx | -0.090 |
antis | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
romy | +1.672 |
apeake | +1.527 |
odan | +1.519 |
inx | +1.447 |
antis | +1.434 |
Neg logit contributions | |
isers | -1.466 |
| -1.325 |
Agenda | -1.315 |
ERA | -1.162 |
SA | -1.084 |
Token | open |
Token ID | 1280 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
romy | +1.155 |
apeake | +1.034 |
odan | +1.023 |
inx | +0.994 |
antis | +0.975 |
Neg logit contributions | |
isers | -1.112 |
| -1.000 |
Agenda | -0.994 |
ERA | -0.893 |
palp | -0.849 |
Token | flights |
Token ID | 13956 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
isers | +0.239 |
Agenda | +0.218 |
| +0.212 |
ERA | +0.192 |
palp | +0.183 |
Neg logit contributions | |
romy | -0.212 |
apeake | -0.188 |
odan | -0.188 |
inx | -0.182 |
antis | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
isers | +0.103 |
Agenda | +0.092 |
| +0.090 |
ERA | +0.081 |
palp | +0.077 |
Neg logit contributions | |
romy | -0.108 |
apeake | -0.097 |
odan | -0.097 |
inx | -0.094 |
antis | -0.092 |
Token | US |
Token ID | 1294 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
romy | +0.218 |
apeake | +0.194 |
odan | +0.193 |
inx | +0.187 |
antis | +0.183 |
Neg logit contributions | |
isers | -0.229 |
Agenda | -0.207 |
| -0.203 |
ERA | -0.183 |
palp | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
isers | +0.177 |
Agenda | +0.160 |
| +0.156 |
ERA | +0.141 |
palp | +0.134 |
Neg logit contributions | |
romy | -0.176 |
apeake | -0.157 |
odan | -0.157 |
inx | -0.152 |
antis | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
isers | +0.082 |
Agenda | +0.074 |
| +0.072 |
ERA | +0.065 |
palp | +0.062 |
Neg logit contributions | |
romy | -0.077 |
apeake | -0.069 |
odan | -0.069 |
inx | -0.067 |
antis | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
isers | +0.077 |
Agenda | +0.069 |
| +0.067 |
ERA | +0.061 |
palp | +0.058 |
Neg logit contributions | |
romy | -0.074 |
apeake | -0.066 |
odan | -0.066 |
inx | -0.064 |
antis | -0.062 |
Token | Remember |
Token ID | 16676 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
isers | +0.215 |
Agenda | +0.193 |
| +0.189 |
ERA | +0.169 |
palp | +0.161 |
Neg logit contributions | |
romy | -0.230 |
apeake | -0.206 |
odan | -0.206 |
inx | -0.200 |
antis | -0.196 |
Token | Na |
Token ID | 11013 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
isers | +0.053 |
Agenda | +0.048 |
| +0.047 |
ERA | +0.043 |
palp | +0.041 |
Neg logit contributions | |
romy | -0.051 |
apeake | -0.045 |
odan | -0.045 |
inx | -0.044 |
antis | -0.043 |
Token | V |
Token ID | 53 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
isers | +0.779 |
Agenda | +0.706 |
| +0.689 |
ERA | +0.624 |
palp | +0.599 |
Neg logit contributions | |
romy | -0.727 |
odan | -0.646 |
apeake | -0.644 |
inx | -0.625 |
antis | -0.612 |
Token | or |
Token ID | 273 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
isers | +1.051 |
Agenda | +0.910 |
| +0.873 |
ERA | +0.760 |
palp | +0.712 |
Neg logit contributions | |
romy | -1.783 |
odan | -1.640 |
apeake | -1.633 |
inx | -1.602 |
antis | -1.580 |
Token | ro |
Token ID | 305 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
isers | +0.232 |
Agenda | +0.212 |
| +0.208 |
ERA | +0.190 |
palp | +0.183 |
Neg logit contributions | |
romy | -0.166 |
odan | -0.145 |
apeake | -0.144 |
inx | -0.139 |
antis | -0.136 |
Token | Bowman |
Token ID | 38774 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
isers | +0.393 |
Agenda | +0.356 |
| +0.348 |
ERA | +0.317 |
palp | +0.304 |
Neg logit contributions | |
romy | -0.327 |
odan | -0.289 |
apeake | -0.288 |
inx | -0.278 |
antis | -0.271 |
Token | at |
Token ID | 379 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
romy | +0.137 |
apeake | +0.123 |
odan | +0.123 |
inx | +0.119 |
antis | +0.117 |
Neg logit contributions | |
isers | -0.123 |
Agenda | -0.110 |
| -0.108 |
ERA | -0.096 |
palp | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
romy | +0.257 |
odan | +0.228 |
apeake | +0.228 |
inx | +0.221 |
antis | +0.216 |
Neg logit contributions | |
isers | -0.276 |
Agenda | -0.249 |
| -0.245 |
ERA | -0.221 |
palp | -0.210 |
Token | received |
Token ID | 2722 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
isers | +0.216 |
Agenda | +0.195 |
| +0.191 |
ERA | +0.172 |
palp | +0.164 |
Neg logit contributions | |
romy | -0.212 |
odan | -0.189 |
apeake | -0.189 |
inx | -0.183 |
antis | -0.180 |
Token | agreement |
Token ID | 4381 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
isers | +0.161 |
Agenda | +0.145 |
| +0.141 |
ERA | +0.127 |
palp | +0.121 |
Neg logit contributions | |
romy | -0.165 |
apeake | -0.147 |
odan | -0.147 |
inx | -0.142 |
antis | -0.140 |
Token | from |
Token ID | 422 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
romy | +0.080 |
apeake | +0.071 |
odan | +0.071 |
inx | +0.068 |
antis | +0.067 |
Neg logit contributions | |
isers | -0.089 |
Agenda | -0.081 |
| -0.079 |
ERA | -0.072 |
palp | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
isers | +0.334 |
Agenda | +0.300 |
| +0.294 |
ERA | +0.265 |
palp | +0.253 |
Neg logit contributions | |
romy | -0.323 |
apeake | -0.287 |
odan | -0.287 |
inx | -0.277 |
antis | -0.273 |
Token | Eth |
Token ID | 9956 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
isers | +0.397 |
Agenda | +0.356 |
| +0.349 |
ERA | +0.315 |
palp | +0.300 |
Neg logit contributions | |
romy | -0.383 |
apeake | -0.341 |
odan | -0.340 |
inx | -0.329 |
antis | -0.323 |
Token | ical |
Token ID | 605 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
isers | +0.484 |
Agenda | +0.432 |
| +0.419 |
ERA | +0.373 |
palp | +0.352 |
Neg logit contributions | |
romy | -0.603 |
apeake | -0.543 |
odan | -0.543 |
inx | -0.528 |
antis | -0.519 |
Token | Committee |
Token ID | 4606 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
isers | +1.225 |
Agenda | +1.090 |
| +1.072 |
ERA | +0.972 |
palp | +0.929 |
Neg logit contributions | |
romy | -1.225 |
odan | -1.094 |
apeake | -1.093 |
inx | -1.063 |
antis | -1.041 |
Token | for |
Token ID | 329 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
isers | +0.406 |
Agenda | +0.364 |
| +0.357 |
ERA | +0.321 |
palp | +0.306 |
Neg logit contributions | |
romy | -0.402 |
odan | -0.359 |
apeake | -0.358 |
inx | -0.346 |
antis | -0.341 |
Token | Animal |
Token ID | 13792 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
romy | +0.087 |
apeake | +0.076 |
odan | +0.076 |
inx | +0.074 |
antis | +0.072 |
Neg logit contributions | |
isers | -0.101 |
Agenda | -0.092 |
| -0.090 |
ERA | -0.082 |
palp | -0.078 |
Token | Research |
Token ID | 4992 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
isers | +0.151 |
Agenda | +0.136 |
| +0.133 |
ERA | +0.120 |
palp | +0.114 |
Neg logit contributions | |
romy | -0.153 |
apeake | -0.136 |
odan | -0.136 |
inx | -0.131 |
antis | -0.129 |
Token | CE |
Token ID | 18671 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
isers | +0.142 |
Agenda | +0.128 |
| +0.125 |
ERA | +0.113 |
palp | +0.107 |
Neg logit contributions | |
romy | -0.142 |
odan | -0.127 |
apeake | -0.127 |
inx | -0.123 |
antis | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
isers | +0.685 |
Agenda | +0.617 |
| +0.597 |
ERA | +0.544 |
palp | +0.522 |
Neg logit contributions | |
romy | -0.657 |
apeake | -0.583 |
odan | -0.582 |
inx | -0.567 |
antis | -0.556 |
Token | In |
Token ID | 554 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
isers | +0.482 |
Agenda | +0.432 |
| +0.420 |
ERA | +0.380 |
palp | +0.367 |
Neg logit contributions | |
romy | -0.468 |
apeake | -0.419 |
odan | -0.416 |
inx | -0.406 |
antis | -0.398 |
Token | Daily |
Token ID | 28545 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
isers | +1.146 |
Agenda | +0.966 |
| +0.941 |
ERA | +0.819 |
palp | +0.789 |
Neg logit contributions | |
romy | -1.745 |
apeake | -1.600 |
odan | -1.594 |
antis | -1.536 |
inx | -1.535 |
Token | provides |
Token ID | 3769 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
isers | +0.116 |
Agenda | +0.106 |
| +0.104 |
ERA | +0.096 |
palp | +0.092 |
Neg logit contributions | |
romy | -0.079 |
apeake | -0.068 |
odan | -0.068 |
inx | -0.065 |
antis | -0.064 |
Token | valuable |
Token ID | 8119 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
romy | +0.197 |
apeake | +0.178 |
odan | +0.178 |
inx | +0.173 |
antis | +0.170 |
Neg logit contributions | |
isers | -0.160 |
Agenda | -0.142 |
| -0.139 |
ERA | -0.123 |
palp | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
isers | +0.188 |
Agenda | +0.169 |
| +0.165 |
ERA | +0.149 |
palp | +0.142 |
Neg logit contributions | |
romy | -0.185 |
apeake | -0.164 |
odan | -0.164 |
inx | -0.159 |
antis | -0.156 |
Token | local |
Token ID | 1957 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
isers | +1.626 |
Agenda | +1.474 |
| +1.440 |
ERA | +1.335 |
palp | +1.298 |
Neg logit contributions | |
romy | -1.020 |
odan | -0.901 |
apeake | -0.891 |
inx | -0.856 |
antis | -0.848 |
Token | independent |
Token ID | 4795 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
isers | +1.413 |
Agenda | +1.277 |
| +1.245 |
ERA | +1.140 |
palp | +1.124 |
Neg logit contributions | |
romy | -1.013 |
odan | -0.893 |
apeake | -0.890 |
inx | -0.860 |
antis | -0.853 |
Token | journalism |
Token ID | 14033 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
isers | +0.933 |
Agenda | +0.841 |
| +0.815 |
ERA | +0.739 |
palp | +0.720 |
Neg logit contributions | |
romy | -0.824 |
odan | -0.730 |
apeake | -0.719 |
inx | -0.705 |
antis | -0.692 |
Token | in |
Token ID | 287 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
isers | +1.364 |
Agenda | +1.223 |
| +1.180 |
ERA | +1.075 |
palp | +1.043 |
Neg logit contributions | |
romy | -1.176 |
odan | -1.036 |
apeake | -1.030 |
inx | -1.025 |
antis | -1.007 |
Token | South |
Token ID | 2520 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
isers | +1.656 |
Agenda | +1.419 |
| +1.353 |
ERA | +1.193 |
palp | +1.171 |
Neg logit contributions | |
romy | -2.235 |
apeake | -1.991 |
Polk | -1.983 |
odan | -1.966 |
inx | -1.965 |
Token | gives |
Token ID | 3607 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
isers | +0.620 |
Agenda | +0.555 |
| +0.541 |
ERA | +0.492 |
palp | +0.473 |
Neg logit contributions | |
romy | -0.572 |
odan | -0.513 |
apeake | -0.512 |
inx | -0.493 |
antis | -0.486 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
isers | +1.023 |
Agenda | +0.922 |
| +0.900 |
ERA | +0.818 |
palp | +0.786 |
Neg logit contributions | |
romy | -0.938 |
apeake | -0.832 |
odan | -0.830 |
inx | -0.801 |
antis | -0.790 |
Token | views |
Token ID | 5009 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
isers | +0.628 |
Agenda | +0.521 |
| +0.499 |
ERA | +0.410 |
palp | +0.383 |
Neg logit contributions | |
romy | -1.435 |
odan | -1.324 |
apeake | -1.323 |
inx | -1.299 |
antis | -1.280 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
isers | +0.443 |
Agenda | +0.400 |
| +0.390 |
ERA | +0.352 |
palp | +0.338 |
Neg logit contributions | |
romy | -0.424 |
odan | -0.377 |
apeake | -0.377 |
inx | -0.364 |
antis | -0.358 |
Token | the |
Token ID | 262 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
isers | +0.846 |
Agenda | +0.758 |
| +0.743 |
ERA | +0.668 |
palp | +0.651 |
Neg logit contributions | |
romy | -0.763 |
odan | -0.677 |
apeake | -0.675 |
inx | -0.654 |
antis | -0.647 |
Token | author |
Token ID | 1772 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
isers | +0.550 |
Agenda | +0.493 |
| +0.481 |
ERA | +0.433 |
palp | +0.420 |
Neg logit contributions | |
romy | -0.541 |
apeake | -0.485 |
odan | -0.482 |
inx | -0.468 |
antis | -0.461 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
isers | +1.461 |
Agenda | +1.349 |
| +1.302 |
ERA | +1.182 |
palp | +1.157 |
Neg logit contributions | |
romy | -1.334 |
apeake | -1.179 |
odan | -1.166 |
inx | -1.140 |
antis | -1.124 |
Token | not |
Token ID | 407 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
isers | +0.949 |
Agenda | +0.858 |
| +0.832 |
ERA | +0.759 |
palp | +0.734 |
Neg logit contributions | |
romy | -0.856 |
apeake | -0.760 |
odan | -0.758 |
inx | -0.727 |
antis | -0.724 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
isers | +0.731 |
Agenda | +0.659 |
| +0.641 |
ERA | +0.581 |
palp | +0.562 |
Neg logit contributions | |
romy | -0.664 |
apeake | -0.586 |
odan | -0.584 |
inx | -0.565 |
antis | -0.552 |
Token | position |
Token ID | 2292 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
isers | +1.105 |
Agenda | +0.992 |
| +0.960 |
ERA | +0.861 |
palp | +0.842 |
Neg logit contributions | |
romy | -1.108 |
apeake | -0.999 |
odan | -0.982 |
inx | -0.965 |
antis | -0.938 |
Token | of |
Token ID | 286 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
romy | +0.118 |
apeake | +0.105 |
odan | +0.105 |
inx | +0.101 |
antis | +0.100 |
Neg logit contributions | |
isers | -0.119 |
Agenda | -0.107 |
| -0.105 |
ERA | -0.095 |
palp | -0.090 |
Token | this |
Token ID | 428 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
romy | +0.286 |
apeake | +0.254 |
odan | +0.254 |
inx | +0.245 |
antis | +0.241 |
Neg logit contributions | |
isers | -0.303 |
Agenda | -0.275 |
| -0.269 |
ERA | -0.243 |
palp | -0.231 |
Token | recipe |
Token ID | 8364 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
romy | +0.293 |
apeake | +0.253 |
odan | +0.253 |
inx | +0.242 |
antis | +0.237 |
Neg logit contributions | |
isers | -0.437 |
Agenda | -0.402 |
| -0.396 |
ERA | -0.362 |
palp | -0.348 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
romy | +0.267 |
apeake | +0.237 |
odan | +0.237 |
inx | +0.229 |
antis | +0.225 |
Neg logit contributions | |
isers | -0.277 |
Agenda | -0.251 |
| -0.246 |
ERA | -0.221 |
palp | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
romy | +0.101 |
apeake | +0.090 |
odan | +0.090 |
inx | +0.087 |
antis | +0.085 |
Neg logit contributions | |
isers | -0.103 |
Agenda | -0.093 |
| -0.091 |
ERA | -0.082 |
palp | -0.078 |
Token | Cu |
Token ID | 46141 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
romy | +0.443 |
apeake | +0.396 |
odan | +0.396 |
inx | +0.383 |
antis | +0.376 |
Neg logit contributions | |
isers | -0.431 |
Agenda | -0.388 |
| -0.381 |
ERA | -0.340 |
palp | -0.324 |
Token | isin |
Token ID | 45763 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
romy | +0.349 |
apeake | +0.311 |
odan | +0.311 |
inx | +0.301 |
antis | +0.295 |
Neg logit contributions | |
isers | -0.351 |
Agenda | -0.315 |
| -0.309 |
ERA | -0.278 |
palp | -0.264 |
Token | art |
Token ID | 433 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
isers | +1.312 |
Agenda | +1.191 |
| +1.152 |
ERA | +1.050 |
palp | +1.013 |
Neg logit contributions | |
romy | -1.148 |
apeake | -1.026 |
odan | -1.022 |
inx | -0.979 |
antis | -0.951 |
Token | 7 |
Token ID | 767 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
romy | +0.498 |
odan | +0.442 |
apeake | +0.442 |
inx | +0.427 |
antis | +0.419 |
Neg logit contributions | |
isers | -0.540 |
Agenda | -0.489 |
| -0.481 |
ERA | -0.433 |
palp | -0.413 |
Token | - |
Token ID | 12 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
romy | +0.529 |
odan | +0.471 |
apeake | +0.471 |
inx | +0.455 |
antis | +0.448 |
Neg logit contributions | |
isers | -0.552 |
Agenda | -0.498 |
| -0.490 |
ERA | -0.441 |
palp | -0.419 |
Token | C |
Token ID | 34 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
romy | +0.533 |
odan | +0.471 |
apeake | +0.470 |
inx | +0.453 |
antis | +0.445 |
Neg logit contributions | |
isers | -0.619 |
Agenda | -0.561 |
| -0.552 |
ERA | -0.499 |
palp | -0.477 |
Token | up |
Token ID | 929 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
romy | +0.575 |
apeake | +0.507 |
odan | +0.506 |
inx | +0.489 |
antis | +0.480 |
Neg logit contributions | |
isers | -0.648 |
Agenda | -0.587 |
| -0.578 |
ERA | -0.521 |
palp | -0.496 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
isers | +0.314 |
Agenda | +0.283 |
| +0.276 |
ERA | +0.248 |
palp | +0.236 |
Neg logit contributions | |
romy | -0.317 |
apeake | -0.283 |
odan | -0.283 |
inx | -0.274 |
antis | -0.268 |
Token | with |
Token ID | 351 |
Feature activation | -9.16e-03 |
Pos logit contributions | |
romy | +0.014 |
apeake | +0.012 |
odan | +0.012 |
inx | +0.012 |
antis | +0.012 |
Neg logit contributions | |
isers | -0.014 |
Agenda | -0.013 |
| -0.013 |
ERA | -0.012 |
palp | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
romy | +0.007 |
apeake | +0.006 |
odan | +0.006 |
inx | +0.006 |
antis | +0.006 |
Neg logit contributions | |
isers | -0.007 |
Agenda | -0.006 |
| -0.006 |
ERA | -0.006 |
palp | -0.005 |
Token | cup |
Token ID | 6508 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
isers | +0.088 |
Agenda | +0.079 |
| +0.078 |
ERA | +0.070 |
palp | +0.067 |
Neg logit contributions | |
romy | -0.083 |
apeake | -0.074 |
odan | -0.074 |
inx | -0.072 |
antis | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
romy | +0.128 |
apeake | +0.114 |
odan | +0.114 |
inx | +0.111 |
antis | +0.109 |
Neg logit contributions | |
isers | -0.130 |
Agenda | -0.118 |
| -0.115 |
ERA | -0.104 |
palp | -0.099 |
Token | hot |
Token ID | 3024 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
isers | +0.224 |
Agenda | +0.201 |
| +0.196 |
ERA | +0.176 |
palp | +0.168 |
Neg logit contributions | |
romy | -0.236 |
apeake | -0.211 |
odan | -0.211 |
inx | -0.204 |
antis | -0.200 |
Token | w |
Token ID | 266 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
isers | +0.116 |
Agenda | +0.105 |
| +0.103 |
ERA | +0.093 |
palp | +0.088 |
Neg logit contributions | |
romy | -0.112 |
apeake | -0.099 |
odan | -0.099 |
inx | -0.096 |
antis | -0.094 |
Token | ort |
Token ID | 419 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
isers | +0.285 |
Agenda | +0.259 |
| +0.254 |
ERA | +0.230 |
palp | +0.221 |
Neg logit contributions | |
romy | -0.246 |
odan | -0.218 |
apeake | -0.217 |
inx | -0.209 |
antis | -0.205 |
Token | mixed |
Token ID | 7668 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
isers | +0.307 |
Agenda | +0.278 |
| +0.272 |
ERA | +0.245 |
palp | +0.234 |
Neg logit contributions | |
romy | -0.289 |
apeake | -0.257 |
odan | -0.257 |
inx | -0.248 |
antis | -0.244 |
Token | with |
Token ID | 351 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
isers | +0.443 |
Agenda | +0.401 |
| +0.390 |
ERA | +0.352 |
palp | +0.335 |
Neg logit contributions | |
romy | -0.433 |
apeake | -0.386 |
odan | -0.384 |
inx | -0.372 |
antis | -0.366 |
Token | some |
Token ID | 617 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
isers | +0.141 |
Agenda | +0.127 |
| +0.125 |
ERA | +0.112 |
palp | +0.107 |
Neg logit contributions | |
romy | -0.135 |
apeake | -0.120 |
odan | -0.120 |
inx | -0.116 |
antis | -0.114 |
Token | were |
Token ID | 547 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
isers | +0.508 |
Agenda | +0.461 |
| +0.448 |
ERA | +0.409 |
palp | +0.391 |
Neg logit contributions | |
romy | -0.438 |
apeake | -0.387 |
odan | -0.386 |
inx | -0.372 |
antis | -0.364 |
Token | in |
Token ID | 287 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
isers | +0.304 |
Agenda | +0.275 |
| +0.267 |
ERA | +0.243 |
palp | +0.231 |
Neg logit contributions | |
romy | -0.295 |
apeake | -0.262 |
odan | -0.262 |
inx | -0.253 |
antis | -0.249 |
Token | college |
Token ID | 4152 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
romy | +0.002 |
apeake | +0.002 |
odan | +0.002 |
inx | +0.002 |
antis | +0.001 |
Neg logit contributions | |
isers | -0.002 |
Agenda | -0.002 |
| -0.002 |
ERA | -0.001 |
palp | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
isers | +0.191 |
Agenda | +0.172 |
| +0.168 |
ERA | +0.151 |
palp | +0.144 |
Neg logit contributions | |
romy | -0.190 |
apeake | -0.169 |
odan | -0.169 |
inx | -0.163 |
antis | -0.160 |
Token | I |
Token ID | 314 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
isers | +0.160 |
Agenda | +0.145 |
| +0.141 |
ERA | +0.128 |
palp | +0.122 |
Neg logit contributions | |
romy | -0.153 |
apeake | -0.136 |
odan | -0.136 |
inx | -0.131 |
antis | -0.129 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
isers | +0.319 |
Agenda | +0.289 |
| +0.281 |
ERA | +0.255 |
palp | +0.242 |
Neg logit contributions | |
romy | -0.304 |
odan | -0.270 |
apeake | -0.270 |
inx | -0.261 |
antis | -0.256 |
Token | it |
Token ID | 340 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
isers | +0.413 |
Agenda | +0.370 |
| +0.359 |
ERA | +0.324 |
palp | +0.307 |
Neg logit contributions | |
romy | -0.439 |
odan | -0.391 |
apeake | -0.391 |
inx | -0.380 |
antis | -0.373 |
Token | was |
Token ID | 373 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
isers | +0.097 |
Agenda | +0.087 |
| +0.085 |
ERA | +0.077 |
palp | +0.073 |
Neg logit contributions | |
romy | -0.092 |
apeake | -0.082 |
odan | -0.082 |
inx | -0.079 |
antis | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
isers | +0.424 |
Agenda | +0.383 |
| +0.373 |
ERA | +0.339 |
palp | +0.323 |
Neg logit contributions | |
romy | -0.390 |
odan | -0.346 |
apeake | -0.346 |
inx | -0.334 |
antis | -0.328 |
Token | st |
Token ID | 336 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
isers | +0.499 |
Agenda | +0.451 |
| +0.438 |
ERA | +0.399 |
palp | +0.378 |
Neg logit contributions | |
romy | -0.477 |
odan | -0.424 |
apeake | -0.424 |
inx | -0.410 |
antis | -0.401 |
Token | oner |
Token ID | 14491 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
isers | +0.288 |
Agenda | +0.256 |
| +0.249 |
ERA | +0.222 |
palp | +0.210 |
Neg logit contributions | |
romy | -0.352 |
odan | -0.318 |
apeake | -0.317 |
inx | -0.309 |
antis | -0.303 |
Token | differently |
Token ID | 10338 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
isers | +0.113 |
Agenda | +0.102 |
| +0.099 |
ERA | +0.089 |
palp | +0.085 |
Neg logit contributions | |
romy | -0.115 |
apeake | -0.103 |
odan | -0.103 |
inx | -0.100 |
antis | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
isers | +0.176 |
Agenda | +0.159 |
| +0.155 |
ERA | +0.140 |
palp | +0.133 |
Neg logit contributions | |
romy | -0.177 |
apeake | -0.157 |
odan | -0.157 |
inx | -0.153 |
antis | -0.150 |
Token | even |
Token ID | 772 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
isers | +0.167 |
Agenda | +0.151 |
| +0.147 |
ERA | +0.133 |
palp | +0.127 |
Neg logit contributions | |
romy | -0.160 |
odan | -0.142 |
apeake | -0.142 |
inx | -0.137 |
antis | -0.135 |
Token | if |
Token ID | 611 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
isers | +0.137 |
Agenda | +0.121 |
| +0.118 |
ERA | +0.105 |
palp | +0.099 |
Neg logit contributions | |
romy | -0.169 |
odan | -0.152 |
apeake | -0.152 |
inx | -0.148 |
antis | -0.145 |
Token | that |
Token ID | 326 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
isers | +0.116 |
Agenda | +0.105 |
| +0.103 |
ERA | +0.093 |
palp | +0.088 |
Neg logit contributions | |
romy | -0.110 |
apeake | -0.098 |
odan | -0.098 |
inx | -0.095 |
antis | -0.093 |
Token | � |
Token ID | 447 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
romy | +0.186 |
apeake | +0.165 |
odan | +0.165 |
inx | +0.159 |
antis | +0.156 |
Neg logit contributions | |
isers | -0.197 |
Agenda | -0.178 |
| -0.175 |
ERA | -0.157 |
palp | -0.150 |
Token | � |
Token ID | 247 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
isers | +0.077 |
Agenda | +0.069 |
| +0.068 |
ERA | +0.061 |
palp | +0.058 |
Neg logit contributions | |
romy | -0.072 |
apeake | -0.064 |
odan | -0.064 |
inx | -0.062 |
antis | -0.060 |
Token | s |
Token ID | 82 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
isers | +0.071 |
Agenda | +0.063 |
| +0.062 |
ERA | +0.055 |
palp | +0.052 |
Neg logit contributions | |
romy | -0.081 |
apeake | -0.073 |
odan | -0.073 |
inx | -0.071 |
antis | -0.070 |
Token | not |
Token ID | 407 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
isers | +0.065 |
Agenda | +0.059 |
| +0.058 |
ERA | +0.052 |
palp | +0.049 |
Neg logit contributions | |
romy | -0.065 |
apeake | -0.058 |
odan | -0.057 |
inx | -0.056 |
antis | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
romy | +0.047 |
apeake | +0.041 |
odan | +0.041 |
inx | +0.040 |
antis | +0.039 |
Neg logit contributions | |
isers | -0.048 |
Agenda | -0.044 |
| -0.043 |
ERA | -0.038 |
palp | -0.037 |
Token | case |
Token ID | 1339 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
isers | +0.403 |
Agenda | +0.347 |
| +0.335 |
ERA | +0.288 |
palp | +0.266 |
Neg logit contributions | |
romy | -0.694 |
odan | -0.633 |
apeake | -0.633 |
inx | -0.618 |
antis | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
isers | +0.152 |
Agenda | +0.137 |
| +0.134 |
ERA | +0.121 |
palp | +0.115 |
Neg logit contributions | |
romy | -0.151 |
apeake | -0.134 |
odan | -0.134 |
inx | -0.130 |
antis | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
isers | +0.185 |
Agenda | +0.166 |
| +0.163 |
ERA | +0.147 |
palp | +0.140 |
Neg logit contributions | |
romy | -0.175 |
apeake | -0.155 |
odan | -0.155 |
inx | -0.150 |
antis | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
romy | +0.034 |
apeake | +0.030 |
odan | +0.030 |
inx | +0.029 |
antis | +0.029 |
Neg logit contributions | |
isers | -0.035 |
Agenda | -0.032 |
| -0.031 |
ERA | -0.028 |
palp | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
isers | +0.230 |
Agenda | +0.208 |
| +0.203 |
ERA | +0.182 |
palp | +0.174 |
Neg logit contributions | |
romy | -0.234 |
apeake | -0.209 |
odan | -0.209 |
inx | -0.202 |
antis | -0.199 |
Token | high |
Token ID | 1029 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
isers | +0.355 |
Agenda | +0.321 |
| +0.314 |
ERA | +0.284 |
palp | +0.271 |
Neg logit contributions | |
romy | -0.328 |
odan | -0.290 |
apeake | -0.290 |
inx | -0.280 |
antis | -0.275 |
Token | court |
Token ID | 2184 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
romy | +0.268 |
apeake | +0.232 |
odan | +0.232 |
inx | +0.223 |
antis | +0.218 |
Neg logit contributions | |
isers | -0.380 |
Agenda | -0.347 |
| -0.342 |
ERA | -0.313 |
palp | -0.300 |
Token | had |
Token ID | 550 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
isers | +0.191 |
Agenda | +0.173 |
| +0.169 |
ERA | +0.152 |
palp | +0.145 |
Neg logit contributions | |
romy | -0.185 |
apeake | -0.165 |
odan | -0.164 |
inx | -0.159 |
antis | -0.156 |
Token | also |
Token ID | 635 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
isers | +0.112 |
Agenda | +0.101 |
| +0.098 |
ERA | +0.088 |
palp | +0.084 |
Neg logit contributions | |
romy | -0.111 |
apeake | -0.099 |
odan | -0.099 |
inx | -0.096 |
antis | -0.094 |
Token | directed |
Token ID | 7924 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
isers | +0.062 |
Agenda | +0.055 |
| +0.054 |
ERA | +0.049 |
palp | +0.046 |
Neg logit contributions | |
romy | -0.063 |
apeake | -0.056 |
odan | -0.056 |
inx | -0.054 |
antis | -0.053 |
Token | Gh |
Token ID | 11972 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
isers | +0.215 |
Agenda | +0.194 |
| +0.190 |
ERA | +0.171 |
palp | +0.163 |
Neg logit contributions | |
romy | -0.209 |
apeake | -0.185 |
odan | -0.185 |
inx | -0.179 |
antis | -0.176 |
Token | ai |
Token ID | 1872 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
isers | +0.214 |
Agenda | +0.195 |
| +0.191 |
ERA | +0.175 |
palp | +0.168 |
Neg logit contributions | |
romy | -0.162 |
apeake | -0.142 |
odan | -0.141 |
inx | -0.136 |
antis | -0.133 |
Token | use |
Token ID | 779 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
isers | +0.203 |
Agenda | +0.183 |
| +0.179 |
ERA | +0.162 |
palp | +0.155 |
Neg logit contributions | |
romy | -0.188 |
odan | -0.166 |
apeake | -0.166 |
inx | -0.161 |
antis | -0.158 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
isers | +0.393 |
Agenda | +0.354 |
| +0.346 |
ERA | +0.312 |
palp | +0.298 |
Neg logit contributions | |
romy | -0.379 |
apeake | -0.336 |
odan | -0.336 |
inx | -0.326 |
antis | -0.320 |
Token | remove |
Token ID | 4781 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
isers | +0.090 |
Agenda | +0.081 |
| +0.079 |
ERA | +0.072 |
palp | +0.068 |
Neg logit contributions | |
romy | -0.084 |
odan | -0.074 |
apeake | -0.074 |
inx | -0.072 |
antis | -0.070 |
Token | opponent |
Token ID | 6125 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
isers | +0.337 |
Agenda | +0.303 |
| +0.297 |
ERA | +0.268 |
palp | +0.256 |
Neg logit contributions | |
romy | -0.326 |
odan | -0.290 |
apeake | -0.289 |
inx | -0.280 |
antis | -0.275 |
Token | � |
Token ID | 447 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
isers | +0.181 |
Agenda | +0.164 |
| +0.161 |
ERA | +0.147 |
palp | +0.141 |
Neg logit contributions | |
romy | -0.146 |
odan | -0.128 |
apeake | -0.128 |
inx | -0.124 |
antis | -0.121 |
Token | � |
Token ID | 247 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
isers | +0.053 |
Agenda | +0.048 |
| +0.047 |
ERA | +0.043 |
palp | +0.041 |
Neg logit contributions | |
romy | -0.050 |
apeake | -0.044 |
odan | -0.044 |
inx | -0.043 |
antis | -0.042 |
Token | s |
Token ID | 82 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
isers | +0.306 |
Agenda | +0.274 |
| +0.268 |
ERA | +0.240 |
palp | +0.228 |
Neg logit contributions | |
romy | -0.339 |
odan | -0.305 |
apeake | -0.304 |
inx | -0.295 |
antis | -0.290 |
Token | monsters |
Token ID | 10963 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
isers | +0.154 |
Agenda | +0.139 |
| +0.137 |
ERA | +0.123 |
palp | +0.118 |
Neg logit contributions | |
romy | -0.145 |
odan | -0.129 |
apeake | -0.129 |
inx | -0.124 |
antis | -0.122 |
Token | with |
Token ID | 351 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
isers | +0.116 |
Agenda | +0.105 |
| +0.103 |
ERA | +0.093 |
palp | +0.088 |
Neg logit contributions | |
romy | -0.112 |
apeake | -0.100 |
odan | -0.100 |
inx | -0.096 |
antis | -0.095 |
Token | no |
Token ID | 645 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
isers | +0.332 |
Agenda | +0.299 |
| +0.293 |
ERA | +0.264 |
palp | +0.252 |
Neg logit contributions | |
romy | -0.317 |
odan | -0.282 |
apeake | -0.281 |
inx | -0.272 |
antis | -0.267 |
Token | strings |
Token ID | 13042 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
isers | +0.284 |
Agenda | +0.255 |
| +0.250 |
ERA | +0.226 |
palp | +0.216 |
Neg logit contributions | |
romy | -0.273 |
odan | -0.243 |
apeake | -0.243 |
inx | -0.235 |
antis | -0.230 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
isers | +0.131 |
Agenda | +0.117 |
| +0.115 |
ERA | +0.103 |
palp | +0.097 |
Neg logit contributions | |
romy | -0.142 |
apeake | -0.128 |
odan | -0.128 |
inx | -0.124 |
antis | -0.122 |
Token | 22 |
Token ID | 1828 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
isers | +0.233 |
Agenda | +0.205 |
| +0.200 |
ERA | +0.176 |
palp | +0.165 |
Neg logit contributions | |
romy | -0.316 |
apeake | -0.286 |
odan | -0.286 |
inx | -0.278 |
antis | -0.274 |
Token | ] |
Token ID | 60 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
isers | +0.171 |
Agenda | +0.153 |
| +0.150 |
ERA | +0.134 |
palp | +0.128 |
Neg logit contributions | |
romy | -0.177 |
apeake | -0.158 |
odan | -0.158 |
inx | -0.153 |
antis | -0.150 |
Token | The |
Token ID | 383 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
isers | +0.205 |
Agenda | +0.184 |
| +0.180 |
ERA | +0.162 |
palp | +0.155 |
Neg logit contributions | |
romy | -0.199 |
apeake | -0.177 |
odan | -0.177 |
inx | -0.171 |
antis | -0.168 |
Token | plan |
Token ID | 1410 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
isers | +0.031 |
Agenda | +0.028 |
| +0.027 |
ERA | +0.025 |
palp | +0.024 |
Neg logit contributions | |
romy | -0.026 |
apeake | -0.023 |
odan | -0.023 |
inx | -0.022 |
antis | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
isers | +0.291 |
Agenda | +0.262 |
| +0.256 |
ERA | +0.230 |
palp | +0.218 |
Neg logit contributions | |
romy | -0.297 |
apeake | -0.266 |
odan | -0.265 |
inx | -0.257 |
antis | -0.252 |
Token | completed |
Token ID | 5668 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
romy | +0.011 |
apeake | +0.010 |
odan | +0.010 |
inx | +0.010 |
antis | +0.009 |
Neg logit contributions | |
isers | -0.011 |
Agenda | -0.010 |
| -0.010 |
ERA | -0.009 |
palp | -0.008 |
Token | no |
Token ID | 645 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
isers | +0.164 |
Agenda | +0.147 |
| +0.144 |
ERA | +0.129 |
palp | +0.123 |
Neg logit contributions | |
romy | -0.164 |
apeake | -0.146 |
odan | -0.146 |
inx | -0.141 |
antis | -0.139 |
Token | later |
Token ID | 1568 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
isers | +0.399 |
Agenda | +0.360 |
| +0.352 |
ERA | +0.317 |
palp | +0.304 |
Neg logit contributions | |
romy | -0.379 |
odan | -0.336 |
apeake | -0.336 |
inx | -0.326 |
antis | -0.320 |
Token | than |
Token ID | 621 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
romy | +0.107 |
apeake | +0.092 |
odan | +0.092 |
inx | +0.088 |
antis | +0.086 |
Neg logit contributions | |
isers | -0.170 |
Agenda | -0.157 |
| -0.154 |
ERA | -0.142 |
palp | -0.136 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
isers | +0.376 |
Agenda | +0.338 |
| +0.330 |
ERA | +0.298 |
palp | +0.284 |
Neg logit contributions | |
romy | -0.367 |
apeake | -0.327 |
odan | -0.327 |
inx | -0.316 |
antis | -0.311 |
Token | full |
Token ID | 1336 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
isers | +0.582 |
Agenda | +0.526 |
| +0.512 |
ERA | +0.462 |
palp | +0.440 |
Neg logit contributions | |
romy | -0.565 |
odan | -0.502 |
apeake | -0.502 |
inx | -0.485 |
antis | -0.476 |
Token | liter |
Token ID | 4187 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
isers | +0.716 |
Agenda | +0.650 |
| +0.633 |
ERA | +0.574 |
palp | +0.549 |
Neg logit contributions | |
romy | -0.638 |
apeake | -0.564 |
odan | -0.563 |
inx | -0.545 |
antis | -0.533 |
Token | of |
Token ID | 286 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
isers | +0.293 |
Agenda | +0.265 |
| +0.259 |
ERA | +0.233 |
palp | +0.222 |
Neg logit contributions | |
romy | -0.284 |
odan | -0.253 |
apeake | -0.253 |
inx | -0.245 |
antis | -0.240 |
Token | the |
Token ID | 262 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
isers | +0.366 |
Agenda | +0.326 |
| +0.317 |
ERA | +0.283 |
palp | +0.269 |
Neg logit contributions | |
romy | -0.419 |
odan | -0.377 |
apeake | -0.377 |
inx | -0.365 |
antis | -0.359 |
Token | famed |
Token ID | 28331 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
isers | +0.468 |
Agenda | +0.421 |
| +0.412 |
ERA | +0.371 |
palp | +0.353 |
Neg logit contributions | |
romy | -0.466 |
odan | -0.416 |
apeake | -0.415 |
inx | -0.402 |
antis | -0.394 |
Token | amber |
Token ID | 36505 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
isers | +0.271 |
Agenda | +0.244 |
| +0.238 |
ERA | +0.214 |
palp | +0.204 |
Neg logit contributions | |
romy | -0.274 |
odan | -0.244 |
apeake | -0.244 |
inx | -0.236 |
antis | -0.232 |
Token | n |
Token ID | 299 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
romy | +0.143 |
apeake | +0.127 |
odan | +0.127 |
inx | +0.122 |
antis | +0.120 |
Neg logit contributions | |
isers | -0.164 |
Agenda | -0.149 |
| -0.146 |
ERA | -0.132 |
palp | -0.126 |
Token | ectar |
Token ID | 44504 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
romy | +0.305 |
apeake | +0.270 |
odan | +0.270 |
inx | +0.261 |
antis | +0.255 |
Neg logit contributions | |
isers | -0.338 |
Agenda | -0.306 |
| -0.300 |
ERA | -0.271 |
palp | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
romy | +0.349 |
apeake | +0.310 |
odan | +0.310 |
inx | +0.300 |
antis | +0.294 |
Neg logit contributions | |
isers | -0.355 |
Agenda | -0.320 |
| -0.314 |
ERA | -0.282 |
palp | -0.268 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
isers | +0.042 |
Agenda | +0.038 |
| +0.037 |
ERA | +0.033 |
palp | +0.032 |
Neg logit contributions | |
romy | -0.040 |
apeake | -0.036 |
odan | -0.036 |
inx | -0.035 |
antis | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
isers | +0.034 |
Agenda | +0.031 |
| +0.030 |
ERA | +0.027 |
palp | +0.026 |
Neg logit contributions | |
romy | -0.033 |
apeake | -0.030 |
odan | -0.029 |
inx | -0.029 |
antis | -0.028 |
Token | Apple |
Token ID | 16108 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
romy | +0.200 |
apeake | +0.179 |
odan | +0.179 |
inx | +0.174 |
antis | +0.171 |
Neg logit contributions | |
isers | -0.182 |
Agenda | -0.163 |
| -0.160 |
ERA | -0.142 |
palp | -0.135 |
Token | � |
Token ID | 447 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
isers | +0.005 |
Agenda | +0.005 |
| +0.005 |
ERA | +0.004 |
palp | +0.004 |
Neg logit contributions | |
romy | -0.005 |
apeake | -0.005 |
odan | -0.005 |
inx | -0.005 |
antis | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
isers | +0.302 |
Agenda | +0.272 |
| +0.266 |
ERA | +0.241 |
palp | +0.230 |
Neg logit contributions | |
romy | -0.283 |
apeake | -0.252 |
odan | -0.251 |
inx | -0.244 |
antis | -0.239 |
Token | s |
Token ID | 82 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
romy | +0.090 |
apeake | +0.080 |
odan | +0.080 |
inx | +0.078 |
antis | +0.076 |
Neg logit contributions | |
isers | -0.081 |
Agenda | -0.072 |
| -0.071 |
ERA | -0.063 |
palp | -0.060 |
Token | default |
Token ID | 4277 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
romy | +0.443 |
apeake | +0.393 |
odan | +0.393 |
inx | +0.380 |
antis | +0.373 |
Neg logit contributions | |
isers | -0.474 |
Agenda | -0.430 |
| -0.422 |
ERA | -0.380 |
palp | -0.362 |
Token | UI |
Token ID | 12454 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
romy | +0.162 |
apeake | +0.144 |
odan | +0.144 |
inx | +0.139 |
antis | +0.136 |
Neg logit contributions | |
isers | -0.178 |
Agenda | -0.161 |
| -0.158 |
ERA | -0.143 |
palp | -0.136 |
Token | elements |
Token ID | 4847 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
isers | +0.033 |
Agenda | +0.030 |
| +0.030 |
ERA | +0.027 |
palp | +0.026 |
Neg logit contributions | |
romy | -0.028 |
odan | -0.024 |
apeake | -0.024 |
inx | -0.023 |
antis | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
isers | +0.089 |
Agenda | +0.080 |
| +0.079 |
ERA | +0.071 |
palp | +0.068 |
Neg logit contributions | |
romy | -0.085 |
apeake | -0.076 |
odan | -0.076 |
inx | -0.073 |
antis | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
isers | +0.200 |
Agenda | +0.180 |
| +0.176 |
ERA | +0.158 |
palp | +0.151 |
Neg logit contributions | |
romy | -0.198 |
odan | -0.176 |
apeake | -0.176 |
inx | -0.170 |
antis | -0.167 |
Token | importance |
Token ID | 6817 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
isers | +0.023 |
Agenda | +0.021 |
| +0.021 |
ERA | +0.019 |
palp | +0.018 |
Neg logit contributions | |
romy | -0.022 |
apeake | -0.020 |
odan | -0.020 |
inx | -0.019 |
antis | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
isers | +0.177 |
Agenda | +0.160 |
| +0.156 |
ERA | +0.141 |
palp | +0.134 |
Neg logit contributions | |
romy | -0.173 |
odan | -0.153 |
apeake | -0.153 |
inx | -0.148 |
antis | -0.146 |
Token | gained |
Token ID | 8618 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
romy | +0.070 |
apeake | +0.063 |
odan | +0.063 |
inx | +0.061 |
antis | +0.060 |
Neg logit contributions | |
isers | -0.069 |
Agenda | -0.062 |
| -0.061 |
ERA | -0.054 |
palp | -0.052 |
Token | from |
Token ID | 422 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
isers | +0.098 |
Agenda | +0.088 |
| +0.087 |
ERA | +0.078 |
palp | +0.075 |
Neg logit contributions | |
romy | -0.091 |
odan | -0.081 |
apeake | -0.081 |
inx | -0.078 |
antis | -0.076 |
Token | its |
Token ID | 663 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
romy | +0.315 |
apeake | +0.278 |
odan | +0.278 |
inx | +0.269 |
antis | +0.263 |
Neg logit contributions | |
isers | -0.350 |
Agenda | -0.318 |
| -0.312 |
ERA | -0.282 |
palp | -0.269 |
Token | membership |
Token ID | 9931 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
romy | +0.364 |
apeake | +0.323 |
odan | +0.323 |
inx | +0.312 |
antis | +0.306 |
Neg logit contributions | |
isers | -0.386 |
Agenda | -0.349 |
| -0.342 |
ERA | -0.308 |
palp | -0.294 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
romy | +0.170 |
apeake | +0.152 |
odan | +0.151 |
inx | +0.147 |
antis | +0.144 |
Neg logit contributions | |
isers | -0.170 |
Agenda | -0.154 |
| -0.150 |
ERA | -0.135 |
palp | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
romy | +0.180 |
apeake | +0.160 |
odan | +0.160 |
inx | +0.155 |
antis | +0.152 |
Neg logit contributions | |
isers | -0.186 |
Agenda | -0.168 |
| -0.165 |
ERA | -0.148 |
palp | -0.141 |
Token | EU |
Token ID | 4576 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
romy | +0.331 |
apeake | +0.294 |
odan | +0.293 |
inx | +0.283 |
antis | +0.278 |
Neg logit contributions | |
isers | -0.352 |
Agenda | -0.318 |
| -0.312 |
ERA | -0.281 |
palp | -0.268 |
Token | has |
Token ID | 468 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
romy | +0.007 |
odan | +0.006 |
apeake | +0.006 |
inx | +0.006 |
antis | +0.006 |
Neg logit contributions | |
isers | -0.007 |
Agenda | -0.006 |
| -0.006 |
ERA | -0.006 |
palp | -0.005 |
Token | benefited |
Token ID | 25050 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
isers | +0.062 |
Agenda | +0.056 |
| +0.054 |
ERA | +0.049 |
palp | +0.047 |
Neg logit contributions | |
romy | -0.061 |
odan | -0.054 |
apeake | -0.054 |
inx | -0.052 |
antis | -0.051 |
Token | as |
Token ID | 355 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
romy | +0.224 |
apeake | +0.198 |
odan | +0.198 |
inx | +0.191 |
antis | +0.187 |
Neg logit contributions | |
isers | -0.246 |
Agenda | -0.222 |
| -0.218 |
ERA | -0.197 |
palp | -0.188 |
Token | well |
Token ID | 880 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
isers | +0.155 |
Agenda | +0.140 |
| +0.137 |
ERA | +0.123 |
palp | +0.117 |
Neg logit contributions | |
romy | -0.158 |
odan | -0.141 |
apeake | -0.140 |
inx | -0.136 |
antis | -0.134 |
Token | Shotgun |
Token ID | 34198 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
isers | +0.300 |
Agenda | +0.271 |
| +0.265 |
ERA | +0.240 |
palp | +0.229 |
Neg logit contributions | |
romy | -0.278 |
odan | -0.246 |
apeake | -0.246 |
inx | -0.237 |
antis | -0.233 |
Token | Willie |
Token ID | 28623 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
isers | +0.160 |
Agenda | +0.144 |
| +0.140 |
ERA | +0.126 |
palp | +0.120 |
Neg logit contributions | |
romy | -0.164 |
apeake | -0.147 |
odan | -0.146 |
inx | -0.142 |
antis | -0.139 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
isers | +0.314 |
Agenda | +0.284 |
| +0.277 |
ERA | +0.251 |
palp | +0.240 |
Neg logit contributions | |
romy | -0.289 |
apeake | -0.256 |
odan | -0.256 |
inx | -0.248 |
antis | -0.243 |
Token | � |
Token ID | 247 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
isers | +0.159 |
Agenda | +0.143 |
| +0.140 |
ERA | +0.127 |
palp | +0.121 |
Neg logit contributions | |
romy | -0.150 |
apeake | -0.133 |
odan | -0.133 |
inx | -0.129 |
antis | -0.126 |
Token | s |
Token ID | 82 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
isers | +0.333 |
Agenda | +0.299 |
| +0.291 |
ERA | +0.261 |
palp | +0.247 |
Neg logit contributions | |
romy | -0.368 |
apeake | -0.330 |
odan | -0.329 |
inx | -0.320 |
antis | -0.315 |
Token | violated |
Token ID | 13998 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
isers | +0.497 |
Agenda | +0.448 |
| +0.438 |
ERA | +0.396 |
palp | +0.378 |
Neg logit contributions | |
romy | -0.459 |
apeake | -0.407 |
odan | -0.406 |
inx | -0.393 |
antis | -0.386 |
Token | Price |
Token ID | 7886 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
isers | +0.021 |
Agenda | +0.019 |
| +0.018 |
ERA | +0.017 |
palp | +0.016 |
Neg logit contributions | |
romy | -0.020 |
apeake | -0.017 |
odan | -0.017 |
inx | -0.017 |
antis | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
romy | +0.082 |
apeake | +0.073 |
odan | +0.073 |
inx | +0.070 |
antis | +0.069 |
Neg logit contributions | |
isers | -0.086 |
Agenda | -0.077 |
| -0.076 |
ERA | -0.068 |
palp | -0.065 |
Token | � |
Token ID | 247 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
isers | +0.086 |
Agenda | +0.077 |
| +0.076 |
ERA | +0.068 |
palp | +0.065 |
Neg logit contributions | |
romy | -0.081 |
apeake | -0.072 |
odan | -0.072 |
inx | -0.069 |
antis | -0.068 |
Token | s |
Token ID | 82 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
romy | +0.065 |
apeake | +0.058 |
odan | +0.058 |
inx | +0.056 |
antis | +0.055 |
Neg logit contributions | |
isers | -0.058 |
Agenda | -0.052 |
| -0.050 |
ERA | -0.045 |
palp | -0.043 |
Token | rights |
Token ID | 2489 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
romy | +0.090 |
apeake | +0.080 |
odan | +0.080 |
inx | +0.077 |
antis | +0.076 |
Neg logit contributions | |
isers | -0.095 |
Agenda | -0.086 |
| -0.084 |
ERA | -0.076 |
palp | -0.073 |
Token | Van |
Token ID | 6656 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
romy | +0.010 |
apeake | +0.009 |
odan | +0.009 |
inx | +0.009 |
antis | +0.009 |
Neg logit contributions | |
isers | -0.011 |
Agenda | -0.010 |
| -0.010 |
ERA | -0.009 |
palp | -0.008 |
Token | Go |
Token ID | 1514 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
isers | +0.206 |
Agenda | +0.185 |
| +0.181 |
ERA | +0.163 |
palp | +0.155 |
Neg logit contributions | |
romy | -0.212 |
odan | -0.189 |
apeake | -0.189 |
inx | -0.183 |
antis | -0.179 |
Token | gh |
Token ID | 456 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
romy | +0.188 |
apeake | +0.165 |
odan | +0.165 |
inx | +0.158 |
antis | +0.155 |
Neg logit contributions | |
isers | -0.244 |
Agenda | -0.222 |
| -0.218 |
ERA | -0.199 |
palp | -0.191 |
Token | , |
Token ID | 11 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
isers | +0.025 |
Agenda | +0.022 |
| +0.022 |
ERA | +0.019 |
palp | +0.019 |
Neg logit contributions | |
romy | -0.024 |
apeake | -0.022 |
odan | -0.022 |
inx | -0.021 |
antis | -0.021 |
Token | Ing |
Token ID | 17589 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
romy | +0.055 |
apeake | +0.049 |
odan | +0.049 |
inx | +0.047 |
antis | +0.046 |
Neg logit contributions | |
isers | -0.055 |
Agenda | -0.050 |
| -0.049 |
ERA | -0.044 |
palp | -0.042 |
Token | mar |
Token ID | 3876 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
isers | +0.052 |
Agenda | +0.046 |
| +0.045 |
ERA | +0.040 |
palp | +0.038 |
Neg logit contributions | |
romy | -0.066 |
apeake | -0.060 |
odan | -0.060 |
inx | -0.058 |
antis | -0.057 |
Token | Berg |
Token ID | 24626 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
romy | +1.102 |
apeake | +0.972 |
odan | +0.964 |
inx | +0.923 |
antis | +0.915 |
Neg logit contributions | |
isers | -1.280 |
Agenda | -1.182 |
| -1.176 |
ERA | -1.040 |
palp | -0.998 |
Token | man |
Token ID | 805 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
isers | +0.722 |
Agenda | +0.649 |
| +0.628 |
ERA | +0.573 |
palp | +0.549 |
Neg logit contributions | |
romy | -0.672 |
odan | -0.598 |
apeake | -0.594 |
inx | -0.579 |
antis | -0.567 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
isers | +0.126 |
Agenda | +0.114 |
| +0.111 |
ERA | +0.100 |
palp | +0.096 |
Neg logit contributions | |
romy | -0.125 |
apeake | -0.112 |
odan | -0.112 |
inx | -0.108 |
antis | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
romy | +0.131 |
apeake | +0.116 |
odan | +0.116 |
inx | +0.113 |
antis | +0.111 |
Neg logit contributions | |
isers | -0.133 |
Agenda | -0.120 |
| -0.118 |
ERA | -0.106 |
palp | -0.101 |
Token | F |
Token ID | 376 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
romy | +0.143 |
apeake | +0.127 |
odan | +0.127 |
inx | +0.123 |
antis | +0.121 |
Neg logit contributions | |
isers | -0.140 |
Agenda | -0.126 |
| -0.124 |
ERA | -0.111 |
palp | -0.106 |
Token | terms |
Token ID | 2846 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
isers | +0.057 |
Agenda | +0.051 |
| +0.050 |
ERA | +0.045 |
palp | +0.043 |
Neg logit contributions | |
romy | -0.056 |
apeake | -0.050 |
odan | -0.050 |
inx | -0.048 |
antis | -0.047 |
Token | of |
Token ID | 286 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
romy | +0.021 |
apeake | +0.019 |
odan | +0.019 |
inx | +0.018 |
antis | +0.018 |
Neg logit contributions | |
isers | -0.021 |
Agenda | -0.019 |
| -0.019 |
ERA | -0.017 |
palp | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
romy | +0.100 |
apeake | +0.089 |
odan | +0.089 |
inx | +0.086 |
antis | +0.084 |
Neg logit contributions | |
isers | -0.100 |
Agenda | -0.090 |
| -0.088 |
ERA | -0.079 |
palp | -0.075 |
Token | qu |
Token ID | 627 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
isers | +0.211 |
Agenda | +0.190 |
| +0.186 |
ERA | +0.167 |
palp | +0.159 |
Neg logit contributions | |
romy | -0.208 |
apeake | -0.185 |
odan | -0.185 |
inx | -0.179 |
antis | -0.176 |
Token | id |
Token ID | 312 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
romy | +0.007 |
odan | +0.007 |
apeake | +0.007 |
inx | +0.006 |
antis | +0.006 |
Neg logit contributions | |
isers | -0.009 |
Agenda | -0.008 |
| -0.008 |
ERA | -0.007 |
palp | -0.007 |
Token | pro |
Token ID | 386 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
romy | +0.137 |
apeake | +0.121 |
odan | +0.121 |
inx | +0.116 |
antis | +0.114 |
Neg logit contributions | |
isers | -0.164 |
Agenda | -0.149 |
| -0.146 |
ERA | -0.133 |
palp | -0.127 |
Token | quo |
Token ID | 18658 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
romy | +1.063 |
apeake | +0.943 |
odan | +0.935 |
inx | +0.897 |
antis | +0.877 |
Neg logit contributions | |
isers | -1.198 |
Agenda | -1.087 |
| -1.072 |
ERA | -0.971 |
palp | -0.921 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
isers | +0.176 |
Agenda | +0.159 |
| +0.155 |
ERA | +0.140 |
palp | +0.133 |
Neg logit contributions | |
romy | -0.172 |
apeake | -0.153 |
odan | -0.153 |
inx | -0.148 |
antis | -0.145 |
Token | it |
Token ID | 340 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
isers | +0.160 |
Agenda | +0.143 |
| +0.139 |
ERA | +0.124 |
palp | +0.118 |
Neg logit contributions | |
romy | -0.183 |
apeake | -0.164 |
odan | -0.164 |
inx | -0.160 |
antis | -0.157 |
Token | � |
Token ID | 447 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
romy | +0.341 |
apeake | +0.303 |
odan | +0.303 |
inx | +0.293 |
antis | +0.288 |
Neg logit contributions | |
isers | -0.344 |
Agenda | -0.310 |
| -0.304 |
ERA | -0.273 |
palp | -0.260 |
Token | � |
Token ID | 247 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
romy | +0.055 |
apeake | +0.049 |
odan | +0.049 |
inx | +0.047 |
antis | +0.047 |
Neg logit contributions | |
isers | -0.057 |
Agenda | -0.051 |
| -0.050 |
ERA | -0.045 |
palp | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
romy | +0.186 |
apeake | +0.165 |
odan | +0.165 |
inx | +0.160 |
antis | +0.157 |
Neg logit contributions | |
isers | -0.193 |
Agenda | -0.174 |
| -0.171 |
ERA | -0.154 |
palp | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
isers | +0.026 |
Agenda | +0.024 |
| +0.023 |
ERA | +0.021 |
palp | +0.020 |
Neg logit contributions | |
romy | -0.026 |
apeake | -0.023 |
odan | -0.023 |
inx | -0.022 |
antis | -0.022 |
Token | C |
Token ID | 34 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
romy | +0.289 |
odan | +0.258 |
apeake | +0.258 |
inx | +0.249 |
antis | +0.245 |
Neg logit contributions | |
isers | -0.287 |
Agenda | -0.258 |
| -0.253 |
ERA | -0.227 |
palp | -0.216 |
Token | elt |
Token ID | 2120 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
romy | +0.678 |
odan | +0.616 |
apeake | +0.615 |
inx | +0.597 |
antis | +0.590 |
Neg logit contributions | |
isers | -0.495 |
Agenda | -0.435 |
| -0.427 |
ERA | -0.372 |
palp | -0.348 |
Token | ics |
Token ID | 873 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
isers | +0.232 |
Agenda | +0.203 |
| +0.196 |
ERA | +0.169 |
palp | +0.158 |
Neg logit contributions | |
romy | -0.386 |
apeake | -0.352 |
odan | -0.352 |
inx | -0.344 |
antis | -0.338 |
Token | coach |
Token ID | 3985 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
isers | +0.026 |
Agenda | +0.023 |
| +0.022 |
ERA | +0.020 |
palp | +0.019 |
Neg logit contributions | |
romy | -0.032 |
apeake | -0.029 |
odan | -0.029 |
inx | -0.028 |
antis | -0.027 |
Token | Brad |
Token ID | 8114 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
romy | +1.281 |
apeake | +1.141 |
odan | +1.137 |
inx | +1.097 |
antis | +1.086 |
Neg logit contributions | |
isers | -1.213 |
Agenda | -1.094 |
| -1.086 |
ERA | -0.964 |
palp | -0.918 |
Token | Stevens |
Token ID | 20019 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
isers | +0.203 |
Agenda | +0.188 |
| +0.185 |
ERA | +0.172 |
palp | +0.167 |
Neg logit contributions | |
romy | -0.086 |
apeake | -0.070 |
odan | -0.070 |
inx | -0.066 |
antis | -0.063 |
Token | isn |
Token ID | 2125 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
isers | +0.016 |
Agenda | +0.014 |
| +0.014 |
ERA | +0.013 |
palp | +0.012 |
Neg logit contributions | |
romy | -0.017 |
apeake | -0.015 |
odan | -0.015 |
inx | -0.014 |
antis | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
romy | +0.010 |
apeake | +0.009 |
odan | +0.009 |
inx | +0.009 |
antis | +0.008 |
Neg logit contributions | |
isers | -0.010 |
Agenda | -0.009 |
| -0.009 |
ERA | -0.008 |
palp | -0.008 |
Token | sure |
Token ID | 1654 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
romy | +0.312 |
odan | +0.277 |
apeake | +0.277 |
inx | +0.267 |
antis | +0.262 |
Neg logit contributions | |
isers | -0.326 |
Agenda | -0.294 |
| -0.289 |
ERA | -0.260 |
palp | -0.248 |
Token | requested |
Token ID | 9167 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
romy | +0.131 |
apeake | +0.117 |
odan | +0.117 |
inx | +0.114 |
antis | +0.112 |
Neg logit contributions | |
isers | -0.127 |
Agenda | -0.114 |
| -0.111 |
ERA | -0.100 |
palp | -0.095 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
romy | +1.181 |
apeake | +1.050 |
odan | +1.038 |
inx | +0.989 |
antis | +0.956 |
Neg logit contributions | |
isers | -1.669 |
Agenda | -1.532 |
| -1.526 |
ERA | -1.374 |
palp | -1.328 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
romy | +1.708 |
apeake | +1.552 |
odan | +1.537 |
inx | +1.484 |
antis | +1.459 |
Neg logit contributions | |
isers | -1.489 |
Agenda | -1.339 |
| -1.326 |
ERA | -1.179 |
SA | -1.088 |
Token | in |
Token ID | 287 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
romy | +1.312 |
apeake | +1.174 |
odan | +1.163 |
antis | +1.115 |
inx | +1.113 |
Neg logit contributions | |
isers | -1.199 |
Agenda | -1.087 |
| -1.075 |
ERA | -0.954 |
palp | -0.899 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
romy | +1.450 |
apeake | +1.284 |
odan | +1.267 |
inx | +1.236 |
antis | +1.203 |
Neg logit contributions | |
isers | -1.314 |
| -1.186 |
Agenda | -1.178 |
ERA | -1.051 |
palp | -0.991 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
romy | +0.819 |
apeake | +0.734 |
odan | +0.731 |
inx | +0.707 |
antis | +0.695 |
Neg logit contributions | |
isers | -0.734 |
Agenda | -0.660 |
| -0.649 |
ERA | -0.576 |
palp | -0.543 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
romy | +1.262 |
apeake | +1.123 |
odan | +1.117 |
inx | +1.075 |
antis | +1.056 |
Neg logit contributions | |
isers | -1.303 |
Agenda | -1.175 |
| -1.167 |
ERA | -1.040 |
palp | -0.992 |
Token | probe |
Token ID | 12774 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
romy | +0.413 |
odan | +0.367 |
apeake | +0.367 |
inx | +0.354 |
antis | +0.348 |
Neg logit contributions | |
isers | -0.419 |
Agenda | -0.377 |
| -0.371 |
ERA | -0.333 |
palp | -0.317 |
Token | : |
Token ID | 25 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
romy | +0.621 |
apeake | +0.548 |
odan | +0.543 |
inx | +0.523 |
antis | +0.512 |
Neg logit contributions | |
isers | -0.718 |
Agenda | -0.656 |
| -0.645 |
ERA | -0.581 |
palp | -0.554 |
Token | report |
Token ID | 989 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
isers | +1.136 |
Agenda | +1.039 |
| +1.009 |
ERA | +0.925 |
palp | +0.893 |
Neg logit contributions | |
romy | -0.839 |
odan | -0.737 |
apeake | -0.731 |
inx | -0.720 |
antis | -0.703 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
isers | +0.053 |
Agenda | +0.048 |
| +0.047 |
ERA | +0.043 |
palp | +0.041 |
Neg logit contributions | |
romy | -0.043 |
apeake | -0.038 |
odan | -0.038 |
inx | -0.036 |
antis | -0.036 |
Token | : |
Token ID | 25 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
isers | +0.257 |
Agenda | +0.229 |
| +0.223 |
ERA | +0.198 |
palp | +0.187 |
Neg logit contributions | |
romy | -0.313 |
apeake | -0.283 |
odan | -0.282 |
inx | -0.274 |
antis | -0.271 |
Token | ' |
Token ID | 705 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
romy | +0.222 |
apeake | +0.194 |
odan | +0.194 |
inx | +0.187 |
antis | +0.183 |
Neg logit contributions | |
isers | -0.277 |
Agenda | -0.252 |
| -0.248 |
ERA | -0.225 |
palp | -0.215 |
Token | I |
Token ID | 40 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
romy | +0.972 |
odan | +0.870 |
apeake | +0.867 |
inx | +0.833 |
antis | +0.806 |
Neg logit contributions | |
isers | -0.976 |
Agenda | -0.875 |
| -0.867 |
ERA | -0.777 |
palp | -0.735 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
romy | +0.943 |
odan | +0.841 |
apeake | +0.839 |
inx | +0.811 |
antis | +0.786 |
Neg logit contributions | |
isers | -1.062 |
Agenda | -0.966 |
| -0.964 |
ERA | -0.861 |
palp | -0.821 |
Token | expect |
Token ID | 1607 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
romy | +0.900 |
apeake | +0.806 |
odan | +0.803 |
inx | +0.769 |
antis | +0.764 |
Neg logit contributions | |
isers | -0.953 |
Agenda | -0.861 |
| -0.857 |
ERA | -0.759 |
palp | -0.725 |
Token | ' |
Token ID | 6 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
romy | +0.356 |
apeake | +0.315 |
odan | +0.315 |
inx | +0.302 |
antis | +0.296 |
Neg logit contributions | |
isers | -0.411 |
Agenda | -0.373 |
| -0.367 |
ERA | -0.332 |
palp | -0.317 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
romy | +1.680 |
apeake | +1.515 |
odan | +1.505 |
inx | +1.454 |
antis | +1.406 |
Neg logit contributions | |
isers | -1.388 |
Agenda | -1.265 |
| -1.261 |
ERA | -1.100 |
SA | -1.022 |
Token | treatment |
Token ID | 3513 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
romy | +0.986 |
apeake | +0.890 |
odan | +0.887 |
inx | +0.851 |
antis | +0.838 |
Neg logit contributions | |
isers | -1.050 |
Agenda | -0.946 |
| -0.931 |
ERA | -0.836 |
palp | -0.788 |
Token | by |
Token ID | 416 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
isers | +0.047 |
Agenda | +0.043 |
| +0.042 |
ERA | +0.038 |
palp | +0.036 |
Neg logit contributions | |
romy | -0.046 |
apeake | -0.041 |
odan | -0.041 |
inx | -0.039 |
antis | -0.039 |
Token | DNC |
Token ID | 17824 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
isers | +0.477 |
Agenda | +0.430 |
| +0.419 |
ERA | +0.375 |
palp | +0.362 |
Neg logit contributions | |
romy | -0.478 |
apeake | -0.426 |
odan | -0.425 |
inx | -0.414 |
antis | -0.409 |
Token | in |
Token ID | 287 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
romy | +0.334 |
apeake | +0.302 |
odan | +0.302 |
inx | +0.293 |
antis | +0.288 |
Neg logit contributions | |
isers | -0.255 |
Agenda | -0.226 |
| -0.221 |
ERA | -0.194 |
palp | -0.182 |