Token | - |
Token ID | 532 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
ponds | +0.258 |
edin | +0.253 |
anooga | +0.242 |
xus | +0.237 |
waters | +0.227 |
Neg logit contributions | |
OW | -0.250 |
ORN | -0.238 |
therefore | -0.225 |
olute | -0.222 |
arget | -0.220 |
Token | January |
Token ID | 3269 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
OW | +0.230 |
ORN | +0.218 |
therefore | +0.212 |
olute | +0.204 |
arget | +0.203 |
Neg logit contributions | |
ponds | -0.192 |
edin | -0.187 |
anooga | -0.183 |
xus | -0.177 |
waters | -0.167 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
OW | +2.313 |
therefore | +2.168 |
ORN | +2.121 |
edit | +2.048 |
olute | +2.003 |
Neg logit contributions | |
ponds | -2.679 |
anooga | -2.650 |
edin | -2.623 |
xus | -2.541 |
perty | -2.403 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
OW | +1.160 |
ORN | +1.070 |
therefore | +1.043 |
edit | +0.987 |
arget | +0.983 |
Neg logit contributions | |
ponds | -1.412 |
anooga | -1.375 |
edin | -1.374 |
xus | -1.326 |
perty | -1.262 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ponds | +1.446 |
edin | +1.414 |
anooga | +1.376 |
xus | +1.343 |
waters | +1.287 |
Neg logit contributions | |
OW | -1.199 |
ORN | -1.131 |
therefore | -1.078 |
olute | -1.037 |
ONES | -1.030 |
Token | Que |
Token ID | 15681 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
OW | +0.076 |
ORN | +0.073 |
therefore | +0.071 |
olute | +0.069 |
arget | +0.068 |
Neg logit contributions | |
ponds | -0.042 |
edin | -0.040 |
anooga | -0.039 |
xus | -0.037 |
waters | -0.035 |
Token | er |
Token ID | 263 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
edin | +7.046 |
xus | +6.259 |
ponds | +6.199 |
anooga | +6.047 |
amn | +5.878 |
Neg logit contributions | |
ORN | -11.629 |
OW | -11.462 |
ONES | -11.175 |
IND | -10.806 |
therefore | -10.774 |
Token | magnet |
Token ID | 19972 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ponds | +3.969 |
edin | +3.755 |
anooga | +3.582 |
xus | +3.509 |
bund | +3.365 |
Neg logit contributions | |
OW | -7.135 |
ORN | -6.838 |
olute | -6.453 |
therefore | -6.448 |
ONES | -6.422 |
Token | ? |
Token ID | 30 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
OW | +1.407 |
ORN | +1.314 |
therefore | +1.267 |
olute | +1.205 |
ONES | +1.200 |
Neg logit contributions | |
ponds | -1.754 |
edin | -1.711 |
anooga | -1.678 |
xus | -1.635 |
waters | -1.561 |
Token |
|
Token ID | 198 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
ponds | +1.632 |
edin | +1.613 |
anooga | +1.562 |
xus | +1.520 |
waters | +1.449 |
Neg logit contributions | |
OW | -1.424 |
ORN | -1.356 |
therefore | -1.280 |
olute | -1.238 |
arget | -1.231 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
OW | +0.130 |
ORN | +0.120 |
therefore | +0.116 |
olute | +0.110 |
edit | +0.110 |
Neg logit contributions | |
ponds | -0.179 |
edin | -0.175 |
anooga | -0.173 |
xus | -0.168 |
waters | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ponds | +0.001 |
edin | +0.001 |
anooga | +0.001 |
xus | +0.001 |
waters | +0.001 |
Neg logit contributions | |
OW | -0.001 |
ORN | -0.001 |
therefore | -0.001 |
olute | -0.001 |
edit | -0.001 |
Token | Miami |
Token ID | 41191 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
OW | +0.085 |
ORN | +0.080 |
therefore | +0.079 |
olute | +0.074 |
ONES | +0.073 |
Neg logit contributions | |
ponds | -0.122 |
edin | -0.122 |
anooga | -0.118 |
xus | -0.115 |
waters | -0.112 |
Token | Dolphins |
Token ID | 21668 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
OW | +1.876 |
ORN | +1.775 |
therefore | +1.703 |
olute | +1.641 |
arget | +1.631 |
Neg logit contributions | |
ponds | -1.917 |
edin | -1.867 |
anooga | -1.822 |
xus | -1.770 |
waters | -1.688 |
Token | : |
Token ID | 25 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ponds | +2.547 |
edin | +2.496 |
anooga | +2.423 |
xus | +2.324 |
bund | +2.243 |
Neg logit contributions | |
OW | -2.406 |
ORN | -2.302 |
therefore | -2.193 |
arget | -2.130 |
olute | -2.126 |
Token | DE |
Token ID | 5550 |
Feature activation | -4.90e-04 |
Pos logit contributions | |
ponds | +0.967 |
edin | +0.950 |
anooga | +0.888 |
xus | +0.864 |
waters | +0.817 |
Neg logit contributions | |
OW | -1.431 |
ORN | -1.376 |
therefore | -1.312 |
arget | -1.289 |
olute | -1.287 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
OW | +0.002 |
ORN | +0.002 |
therefore | +0.002 |
olute | +0.002 |
arget | +0.002 |
Neg logit contributions | |
ponds | -0.002 |
edin | -0.002 |
anooga | -0.002 |
xus | -0.002 |
waters | -0.001 |
Token | Wake |
Token ID | 20441 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
ponds | +5.929 |
Sou | +5.695 |
edin | +5.352 |
Nig | +4.925 |
waters | +4.852 |
Neg logit contributions | |
ORN | -11.703 |
OW | -11.343 |
olute | -11.152 |
ILE | -11.122 |
ONES | -11.068 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ponds | +3.230 |
edin | +3.147 |
anooga | +3.040 |
xus | +2.964 |
waters | +2.909 |
Neg logit contributions | |
OW | -2.873 |
ORN | -2.736 |
therefore | -2.587 |
ONES | -2.540 |
arget | -2.519 |
Token |
|
Token ID | 198 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ponds | +2.124 |
edin | +2.084 |
anooga | +2.002 |
xus | +1.962 |
waters | +1.900 |
Neg logit contributions | |
OW | -1.749 |
ORN | -1.663 |
therefore | -1.568 |
olute | -1.522 |
ONES | -1.510 |
Token | Contract |
Token ID | 45845 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
edin | +1.474 |
ponds | +1.455 |
anooga | +1.412 |
xus | +1.360 |
waters | +1.323 |
Neg logit contributions | |
OW | -1.451 |
ORN | -1.391 |
therefore | -1.375 |
olute | -1.308 |
ONES | -1.298 |
Token | : |
Token ID | 25 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ponds | +1.975 |
edin | +1.935 |
anooga | +1.855 |
xus | +1.823 |
waters | +1.754 |
Neg logit contributions | |
OW | -1.784 |
ORN | -1.700 |
therefore | -1.606 |
olute | -1.564 |
ONES | -1.558 |
Token | $ |
Token ID | 720 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
OW | +1.457 |
ORN | +1.385 |
therefore | +1.331 |
olute | +1.287 |
arget | +1.282 |
Neg logit contributions | |
ponds | -1.258 |
edin | -1.223 |
anooga | -1.187 |
xus | -1.153 |
waters | -1.091 |
Token | 16 |
Token ID | 1433 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
OW | +1.142 |
ORN | +1.065 |
therefore | +1.011 |
olute | +0.964 |
ONES | +0.953 |
Neg logit contributions | |
ponds | -1.771 |
edin | -1.742 |
anooga | -1.694 |
xus | -1.665 |
waters | -1.603 |
Token | million |
Token ID | 1510 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ponds | +2.319 |
edin | +2.278 |
anooga | +2.173 |
xus | +2.109 |
outsourcing | +2.015 |
Neg logit contributions | |
OW | -2.452 |
ORN | -2.372 |
therefore | -2.200 |
ONES | -2.171 |
olute | -2.153 |
Token | owed |
Token ID | 21057 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ponds | +1.140 |
edin | +1.109 |
anooga | +1.062 |
xus | +1.045 |
bund | +1.004 |
Neg logit contributions | |
OW | -1.134 |
ORN | -1.074 |
therefore | -1.002 |
olute | -0.994 |
ONES | -0.989 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ponds | +4.828 |
edin | +4.785 |
anooga | +4.342 |
xus | +4.319 |
bund | +4.315 |
Neg logit contributions | |
OW | -5.972 |
ORN | -5.765 |
olute | -5.441 |
RIC | -5.384 |
ILE | -5.383 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ponds | +0.397 |
edin | +0.388 |
anooga | +0.372 |
xus | +0.360 |
bund | +0.345 |
Neg logit contributions | |
OW | -0.469 |
ORN | -0.446 |
therefore | -0.425 |
olute | -0.416 |
arget | -0.414 |
Token | May |
Token ID | 1737 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ponds | +7.142 |
edin | +6.618 |
Sou | +6.412 |
bund | +6.217 |
Nig | +6.011 |
Neg logit contributions | |
ORN | -10.765 |
OW | -10.652 |
RIC | -10.163 |
ILE | -10.135 |
ARS | -9.978 |
Token | bin |
Token ID | 8800 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ponds | +4.193 |
edin | +4.152 |
anooga | +3.858 |
waters | +3.790 |
xus | +3.738 |
Neg logit contributions | |
OW | -3.448 |
ORN | -3.358 |
ILE | -3.175 |
ONES | -3.139 |
ARS | -3.135 |
Token | and |
Token ID | 290 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ponds | +1.956 |
edin | +1.922 |
anooga | +1.843 |
xus | +1.819 |
bund | +1.739 |
Neg logit contributions | |
OW | -1.831 |
ORN | -1.773 |
therefore | -1.648 |
ONES | -1.636 |
RIC | -1.625 |
Token | $ |
Token ID | 720 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
OW | +1.467 |
ORN | +1.391 |
therefore | +1.334 |
olute | +1.291 |
ONES | +1.284 |
Neg logit contributions | |
ponds | -1.356 |
edin | -1.321 |
anooga | -1.284 |
xus | -1.248 |
waters | -1.182 |
Token | 8 |
Token ID | 23 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
OW | +2.207 |
ORN | +2.021 |
therefore | +1.918 |
arget | +1.798 |
edit | +1.798 |
Neg logit contributions | |
ponds | -3.942 |
edin | -3.842 |
anooga | -3.816 |
xus | -3.713 |
waters | -3.545 |
Token | agreed |
Token ID | 4987 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
OW | +0.342 |
ORN | +0.323 |
therefore | +0.303 |
olute | +0.298 |
ONES | +0.297 |
Neg logit contributions | |
ponds | -0.355 |
edin | -0.344 |
anooga | -0.333 |
xus | -0.326 |
bund | -0.311 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
OW | +0.775 |
ORN | +0.733 |
therefore | +0.708 |
olute | +0.681 |
ONES | +0.676 |
Neg logit contributions | |
ponds | -0.722 |
edin | -0.703 |
anooga | -0.686 |
xus | -0.667 |
waters | -0.632 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
OW | +4.008 |
ORN | +3.785 |
therefore | +3.691 |
olute | +3.521 |
ONES | +3.504 |
Neg logit contributions | |
ponds | -3.487 |
edin | -3.409 |
anooga | -3.362 |
xus | -3.244 |
waters | -3.071 |
Token | on |
Token ID | 319 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
OW | +0.040 |
ORN | +0.038 |
therefore | +0.036 |
ONES | +0.035 |
RIC | +0.035 |
Neg logit contributions | |
ponds | -0.037 |
edin | -0.036 |
anooga | -0.035 |
xus | -0.034 |
waters | -0.033 |
Token | until |
Token ID | 1566 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
OW | +1.785 |
ORN | +1.677 |
therefore | +1.618 |
olute | +1.546 |
ONES | +1.535 |
Neg logit contributions | |
ponds | -2.001 |
edin | -1.955 |
anooga | -1.916 |
xus | -1.864 |
waters | -1.774 |
Token | Brexit |
Token ID | 11435 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
OW | +0.503 |
ORN | +0.476 |
therefore | +0.456 |
olute | +0.444 |
ONES | +0.442 |
Neg logit contributions | |
ponds | -0.462 |
edin | -0.448 |
anooga | -0.434 |
xus | -0.425 |
waters | -0.403 |
Token | negotiations |
Token ID | 9825 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ponds | +8.343 |
anooga | +7.655 |
edin | +7.650 |
waters | +7.422 |
mand | +7.333 |
Neg logit contributions | |
ORN | -9.136 |
OW | -8.838 |
ONES | -8.483 |
arget | -8.474 |
RIC | -8.451 |
Token | with |
Token ID | 351 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ponds | +7.394 |
wrap | +6.797 |
edin | +6.732 |
anooga | +6.429 |
mand | +6.338 |
Neg logit contributions | |
ORN | -8.690 |
OW | -8.515 |
arget | -8.054 |
RIC | -7.855 |
ILE | -7.758 |
Token | the |
Token ID | 262 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ponds | +2.347 |
anooga | +2.209 |
edin | +2.208 |
xus | +2.157 |
outsourcing | +2.065 |
Neg logit contributions | |
OW | -2.433 |
ORN | -2.338 |
arget | -2.185 |
therefore | -2.168 |
ONES | -2.149 |
Token | EU |
Token ID | 4576 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ponds | +1.143 |
edin | +1.083 |
anooga | +1.065 |
xus | +1.020 |
waters | +0.966 |
Neg logit contributions | |
OW | -1.678 |
ORN | -1.620 |
therefore | -1.541 |
arget | -1.512 |
olute | -1.510 |
Token | have |
Token ID | 423 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ponds | +5.432 |
anooga | +5.034 |
edin | +5.005 |
mand | +4.742 |
wrap | +4.721 |
Neg logit contributions | |
ORN | -5.836 |
OW | -5.820 |
arget | -5.472 |
ONES | -5.309 |
edit | -5.267 |
Token | he |
Token ID | 339 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
OW | +2.265 |
ORN | +2.140 |
therefore | +2.063 |
olute | +1.977 |
ONES | +1.966 |
Neg logit contributions | |
ponds | -2.311 |
edin | -2.254 |
anooga | -2.202 |
xus | -2.141 |
waters | -2.036 |
Token | says |
Token ID | 1139 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ponds | +1.007 |
edin | +0.985 |
anooga | +0.942 |
xus | +0.927 |
waters | +0.890 |
Neg logit contributions | |
OW | -1.081 |
ORN | -1.033 |
ONES | -0.954 |
olute | -0.953 |
therefore | -0.952 |
Token | . |
Token ID | 13 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
ponds | +1.473 |
edin | +1.441 |
anooga | +1.404 |
xus | +1.371 |
waters | +1.311 |
Neg logit contributions | |
OW | -1.312 |
ORN | -1.244 |
therefore | -1.179 |
ONES | -1.139 |
olute | -1.138 |
Token |
|
Token ID | 198 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ponds | +0.217 |
edin | +0.213 |
anooga | +0.207 |
xus | +0.201 |
waters | +0.194 |
Neg logit contributions | |
OW | -0.193 |
ORN | -0.182 |
therefore | -0.174 |
olute | -0.170 |
arget | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ponds | +0.240 |
edin | +0.234 |
anooga | +0.231 |
xus | +0.225 |
waters | +0.214 |
Neg logit contributions | |
OW | -0.179 |
ORN | -0.166 |
therefore | -0.160 |
olute | -0.152 |
arget | -0.151 |
Token | Fake |
Token ID | 49233 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
edin | +0.743 |
ponds | +0.740 |
anooga | +0.719 |
xus | +0.703 |
waters | +0.683 |
Neg logit contributions | |
OW | -0.584 |
ORN | -0.551 |
therefore | -0.545 |
olute | -0.522 |
ONES | -0.506 |
Token | - |
Token ID | 12 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ponds | +7.485 |
edin | +7.036 |
anooga | +6.937 |
xus | +6.599 |
mand | +6.543 |
Neg logit contributions | |
OW | -9.300 |
ORN | -8.939 |
ONES | -8.606 |
edit | -8.529 |
ILE | -8.512 |
Token | data |
Token ID | 7890 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ponds | +0.832 |
edin | +0.824 |
anooga | +0.806 |
xus | +0.777 |
waters | +0.761 |
Neg logit contributions | |
OW | -0.726 |
ORN | -0.685 |
therefore | -0.665 |
olute | -0.644 |
ONES | -0.639 |
Token | challenges |
Token ID | 6459 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ponds | +1.854 |
edin | +1.780 |
anooga | +1.716 |
xus | +1.665 |
bund | +1.609 |
Neg logit contributions | |
OW | -2.116 |
ORN | -2.026 |
olute | -1.900 |
therefore | -1.889 |
ONES | -1.881 |
Token | have |
Token ID | 423 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ponds | +2.026 |
edin | +1.942 |
anooga | +1.855 |
xus | +1.846 |
bund | +1.765 |
Neg logit contributions | |
OW | -2.027 |
ORN | -1.933 |
olute | -1.800 |
ONES | -1.786 |
arget | -1.785 |
Token | been |
Token ID | 587 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
OW | +1.457 |
ORN | +1.372 |
therefore | +1.312 |
olute | +1.264 |
ONES | +1.256 |
Neg logit contributions | |
ponds | -1.647 |
edin | -1.605 |
anooga | -1.568 |
xus | -1.528 |
waters | -1.458 |
Token | � |
Token ID | 447 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
OW | +1.986 |
ORN | +1.878 |
therefore | +1.789 |
olute | +1.730 |
ONES | +1.721 |
Neg logit contributions | |
ponds | -2.150 |
edin | -2.096 |
anooga | -2.041 |
xus | -1.988 |
waters | -1.901 |
Token | � |
Token ID | 247 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ponds | +0.644 |
edin | +0.631 |
anooga | +0.613 |
xus | +0.599 |
waters | +0.574 |
Neg logit contributions | |
OW | -0.502 |
ORN | -0.477 |
therefore | -0.450 |
ONES | -0.438 |
arget | -0.437 |
Token | s |
Token ID | 82 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ponds | +0.498 |
edin | +0.489 |
anooga | +0.473 |
xus | +0.468 |
waters | +0.456 |
Neg logit contributions | |
OW | -0.258 |
ORN | -0.243 |
therefore | -0.219 |
ONES | -0.214 |
arget | -0.211 |
Token | � |
Token ID | 564 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
OW | +0.771 |
ORN | +0.731 |
therefore | +0.688 |
olute | +0.674 |
ONES | +0.674 |
Neg logit contributions | |
ponds | -0.803 |
edin | -0.777 |
anooga | -0.759 |
xus | -0.735 |
waters | -0.704 |
Token | � |
Token ID | 250 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ponds | +3.330 |
edin | +3.252 |
anooga | +3.150 |
xus | +3.071 |
bund | +2.930 |
Neg logit contributions | |
OW | -2.787 |
ORN | -2.645 |
therefore | -2.527 |
ONES | -2.487 |
olute | -2.442 |
Token | eu |
Token ID | 12496 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
OW | +0.722 |
ORN | +0.688 |
therefore | +0.653 |
ONES | +0.629 |
olute | +0.625 |
Neg logit contributions | |
ponds | -0.831 |
edin | -0.817 |
anooga | -0.792 |
xus | -0.774 |
waters | -0.745 |
Token | ph |
Token ID | 746 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
ponds | +8.537 |
edin | +8.105 |
xus | +7.964 |
anooga | +7.943 |
perty | +7.839 |
Neg logit contributions | |
OW | -8.571 |
ORN | -8.152 |
ONES | -7.592 |
arget | -7.444 |
therefore | -7.329 |
Token | oric |
Token ID | 8146 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ponds | +2.458 |
edin | +2.422 |
anooga | +2.338 |
xus | +2.262 |
amia | +2.187 |
Neg logit contributions | |
OW | -2.154 |
ORN | -2.039 |
therefore | -1.986 |
ILE | -1.879 |
ONES | -1.878 |
Token | � |
Token ID | 447 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ponds | +1.640 |
edin | +1.565 |
anooga | +1.531 |
xus | +1.492 |
waters | +1.428 |
Neg logit contributions | |
OW | -1.635 |
ORN | -1.569 |
therefore | -1.465 |
ONES | -1.454 |
arget | -1.444 |
Token | � |
Token ID | 251 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
OW | +2.048 |
ORN | +1.911 |
therefore | +1.827 |
olute | +1.739 |
arget | +1.724 |
Neg logit contributions | |
ponds | -2.844 |
edin | -2.783 |
anooga | -2.726 |
xus | -2.661 |
waters | -2.551 |
Token | effects |
Token ID | 3048 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
OW | +0.579 |
ORN | +0.551 |
therefore | +0.519 |
ONES | +0.504 |
arget | +0.503 |
Neg logit contributions | |
ponds | -0.623 |
edin | -0.607 |
anooga | -0.591 |
xus | -0.578 |
waters | -0.553 |
Token | - |
Token ID | 532 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ponds | +1.855 |
edin | +1.811 |
anooga | +1.722 |
xus | +1.688 |
waters | +1.617 |
Neg logit contributions | |
OW | -1.877 |
ORN | -1.796 |
therefore | -1.697 |
olute | -1.680 |
arget | -1.657 |
Token | December |
Token ID | 3426 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
OW | +0.479 |
ORN | +0.455 |
therefore | +0.441 |
olute | +0.424 |
edit | +0.422 |
Neg logit contributions | |
ponds | -0.378 |
edin | -0.367 |
anooga | -0.360 |
xus | -0.346 |
waters | -0.326 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
OW | +3.014 |
therefore | +2.775 |
ORN | +2.728 |
edit | +2.614 |
ONES | +2.570 |
Neg logit contributions | |
ponds | -3.493 |
anooga | -3.459 |
edin | -3.439 |
xus | -3.363 |
ascript | -3.208 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
OW | +1.832 |
ORN | +1.677 |
therefore | +1.638 |
edit | +1.547 |
arget | +1.541 |
Neg logit contributions | |
ponds | -2.290 |
anooga | -2.244 |
edin | -2.226 |
xus | -2.163 |
perty | -2.073 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ponds | +1.288 |
edin | +1.258 |
anooga | +1.217 |
xus | +1.184 |
waters | +1.134 |
Neg logit contributions | |
OW | -1.214 |
ORN | -1.158 |
therefore | -1.096 |
olute | -1.066 |
ONES | -1.060 |
Token | Que |
Token ID | 15681 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ponds | +0.662 |
edin | +0.653 |
anooga | +0.610 |
xus | +0.592 |
waters | +0.567 |
Neg logit contributions | |
OW | -1.365 |
ORN | -1.325 |
therefore | -1.299 |
olute | -1.264 |
arget | -1.251 |
Token | ers |
Token ID | 364 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
edin | +4.535 |
ponds | +4.253 |
xus | +3.946 |
anooga | +3.721 |
waters | +3.687 |
Neg logit contributions | |
ORN | -12.283 |
OW | -12.283 |
therefore | -11.710 |
IND | -11.605 |
INC | -11.537 |
Token | are |
Token ID | 389 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ponds | +3.461 |
edin | +3.321 |
anooga | +3.064 |
xus | +3.050 |
bund | +2.959 |
Neg logit contributions | |
OW | -4.741 |
ORN | -4.609 |
arget | -4.358 |
RIC | -4.340 |
ONES | -4.325 |
Token | Here |
Token ID | 3423 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ponds | +0.759 |
edin | +0.748 |
anooga | +0.727 |
xus | +0.700 |
waters | +0.680 |
Neg logit contributions | |
OW | -0.585 |
ORN | -0.552 |
therefore | -0.520 |
olute | -0.504 |
RIC | -0.503 |
Token | .... |
Token ID | 1106 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
OW | +0.868 |
ORN | +0.819 |
therefore | +0.783 |
olute | +0.749 |
arget | +0.746 |
Neg logit contributions | |
ponds | -1.094 |
edin | -1.072 |
anooga | -1.051 |
xus | -1.019 |
waters | -0.983 |
Token |
|
Token ID | 198 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
ponds | +0.590 |
edin | +0.580 |
anooga | +0.564 |
xus | +0.549 |
waters | +0.524 |
Neg logit contributions | |
OW | -0.495 |
ORN | -0.467 |
therefore | -0.445 |
olute | -0.429 |
arget | -0.427 |
Token | ushi |
Token ID | 17731 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
OW | +0.635 |
ORN | +0.603 |
therefore | +0.574 |
olute | +0.552 |
ONES | +0.551 |
Neg logit contributions | |
ponds | -0.714 |
edin | -0.697 |
anooga | -0.675 |
xus | -0.659 |
waters | -0.631 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ponds | +3.378 |
edin | +3.142 |
anooga | +3.052 |
xus | +2.956 |
bund | +2.942 |
Neg logit contributions | |
OW | -3.258 |
ORN | -3.075 |
arget | -2.878 |
olute | -2.863 |
ONES | -2.862 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ponds | +0.539 |
edin | +0.517 |
anooga | +0.505 |
xus | +0.491 |
bund | +0.474 |
Neg logit contributions | |
OW | -0.497 |
ORN | -0.470 |
therefore | -0.437 |
olute | -0.435 |
arget | -0.434 |
Token | Japanese |
Token ID | 4960 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ponds | +1.042 |
edin | +0.987 |
anooga | +0.954 |
xus | +0.927 |
bund | +0.893 |
Neg logit contributions | |
OW | -1.282 |
ORN | -1.225 |
therefore | -1.160 |
arget | -1.145 |
olute | -1.140 |
Token | egg |
Token ID | 5935 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ponds | +4.315 |
edin | +3.929 |
bund | +3.776 |
anooga | +3.762 |
piping | +3.739 |
Neg logit contributions | |
OW | -5.152 |
ORN | -4.956 |
arget | -4.674 |
olute | -4.630 |
ONES | -4.610 |
Token | cust |
Token ID | 9378 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ponds | +2.227 |
edin | +2.165 |
anooga | +2.020 |
bund | +1.924 |
xus | +1.921 |
Neg logit contributions | |
OW | -3.177 |
ORN | -3.063 |
therefore | -2.901 |
ONES | -2.890 |
arget | -2.885 |
Token | ard |
Token ID | 446 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
edin | +7.492 |
ponds | +6.981 |
amia | +6.831 |
xus | +6.707 |
amn | +6.542 |
Neg logit contributions | |
OW | -9.470 |
ORN | -9.251 |
ILE | -8.980 |
therefore | -8.905 |
RIC | -8.816 |
Token | , |
Token ID | 11 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ponds | +2.826 |
edin | +2.644 |
anooga | +2.558 |
bund | +2.510 |
xus | +2.495 |
Neg logit contributions | |
OW | -2.921 |
ORN | -2.783 |
olute | -2.589 |
arget | -2.586 |
ONES | -2.584 |
Token | so |
Token ID | 523 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ponds | +1.526 |
edin | +1.455 |
anooga | +1.426 |
xus | +1.384 |
bund | +1.346 |
Neg logit contributions | |
OW | -1.390 |
ORN | -1.308 |
therefore | -1.219 |
arget | -1.210 |
olute | -1.210 |
Token | perfect |
Token ID | 2818 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ponds | +1.913 |
edin | +1.848 |
anooga | +1.791 |
xus | +1.751 |
bund | +1.678 |
Neg logit contributions | |
OW | -1.889 |
ORN | -1.793 |
therefore | -1.696 |
edit | -1.667 |
arget | -1.662 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ponds | +5.027 |
edin | +4.756 |
anooga | +4.607 |
xus | +4.593 |
piping | +4.460 |
Neg logit contributions | |
OW | -4.701 |
ORN | -4.371 |
ONES | -4.144 |
arget | -4.131 |
ILE | -4.128 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
ponds | +1.314 |
edin | +1.281 |
anooga | +1.262 |
xus | +1.227 |
waters | +1.169 |
Neg logit contributions | |
OW | -1.061 |
ORN | -0.992 |
therefore | -0.956 |
olute | -0.911 |
arget | -0.906 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ponds | +2.501 |
edin | +2.449 |
anooga | +2.357 |
xus | +2.310 |
waters | +2.240 |
Neg logit contributions | |
OW | -2.056 |
ORN | -1.946 |
therefore | -1.843 |
olute | -1.785 |
ONES | -1.765 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ponds | +1.046 |
edin | +1.024 |
anooga | +1.000 |
xus | +0.976 |
waters | +0.936 |
Neg logit contributions | |
OW | -0.813 |
ORN | -0.763 |
therefore | -0.728 |
olute | -0.697 |
ONES | -0.692 |
Token | � |
Token ID | 447 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ponds | +0.553 |
edin | +0.550 |
anooga | +0.534 |
xus | +0.522 |
waters | +0.504 |
Neg logit contributions | |
OW | -0.436 |
ORN | -0.410 |
therefore | -0.403 |
olute | -0.384 |
ONES | -0.375 |
Token | � |
Token ID | 250 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
ponds | +2.218 |
edin | +2.178 |
anooga | +2.132 |
xus | +2.088 |
waters | +2.001 |
Neg logit contributions | |
OW | -1.324 |
ORN | -1.234 |
therefore | -1.180 |
olute | -1.125 |
arget | -1.111 |
Token | Lord |
Token ID | 22438 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ponds | +0.178 |
edin | +0.176 |
anooga | +0.172 |
xus | +0.167 |
waters | +0.162 |
Neg logit contributions | |
OW | -0.130 |
ORN | -0.122 |
therefore | -0.118 |
olute | -0.113 |
ONES | -0.111 |
Token | Jesus |
Token ID | 5803 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ponds | +7.845 |
edin | +7.708 |
anooga | +7.296 |
amn | +7.124 |
bund | +7.040 |
Neg logit contributions | |
ORN | -8.405 |
OW | -8.240 |
ONES | -8.060 |
arget | -7.943 |
INC | -7.741 |
Token | , |
Token ID | 11 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
ponds | +5.879 |
edin | +5.428 |
anooga | +5.283 |
bund | +5.231 |
xus | +5.153 |
Neg logit contributions | |
ORN | -6.870 |
OW | -6.819 |
ONES | -6.366 |
RIC | -6.298 |
ILE | -6.291 |
Token | � |
Token ID | 447 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
ponds | +0.256 |
edin | +0.245 |
anooga | +0.241 |
xus | +0.235 |
waters | +0.222 |
Neg logit contributions | |
OW | -0.265 |
ORN | -0.253 |
therefore | -0.238 |
olute | -0.233 |
arget | -0.232 |
Token | � |
Token ID | 251 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
OW | +2.769 |
ORN | +2.548 |
therefore | +2.419 |
olute | +2.231 |
ONES | +2.226 |
Neg logit contributions | |
ponds | -4.664 |
edin | -4.580 |
anooga | -4.482 |
xus | -4.391 |
waters | -4.230 |
Token | Mr |
Token ID | 1770 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
OW | +1.027 |
ORN | +0.971 |
therefore | +0.932 |
olute | +0.899 |
arget | +0.895 |
Neg logit contributions | |
ponds | -1.025 |
edin | -0.996 |
anooga | -0.974 |
xus | -0.949 |
waters | -0.900 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
OW | +0.338 |
ORN | +0.316 |
therefore | +0.305 |
olute | +0.295 |
arget | +0.294 |
Neg logit contributions | |
ponds | -0.421 |
edin | -0.413 |
anooga | -0.400 |
xus | -0.387 |
waters | -0.377 |
Token | Boston |
Token ID | 6182 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
OW | +1.211 |
ORN | +1.149 |
therefore | +1.108 |
olute | +1.069 |
ONES | +1.063 |
Neg logit contributions | |
ponds | -1.134 |
edin | -1.107 |
anooga | -1.073 |
xus | -1.040 |
waters | -0.994 |
Token | Celtics |
Token ID | 24116 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
OW | +0.906 |
ORN | +0.867 |
therefore | +0.831 |
arget | +0.811 |
olute | +0.808 |
Neg logit contributions | |
ponds | -0.767 |
edin | -0.732 |
anooga | -0.722 |
xus | -0.691 |
waters | -0.661 |
Token | swing |
Token ID | 9628 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ponds | +1.452 |
edin | +1.398 |
anooga | +1.348 |
xus | +1.305 |
bund | +1.275 |
Neg logit contributions | |
OW | -1.345 |
ORN | -1.280 |
therefore | -1.203 |
ILE | -1.190 |
arget | -1.183 |
Token | man |
Token ID | 805 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ponds | +1.257 |
edin | +1.184 |
anooga | +1.093 |
waters | +1.019 |
xus | +1.001 |
Neg logit contributions | |
OW | -2.921 |
ORN | -2.846 |
therefore | -2.742 |
ILE | -2.717 |
ONES | -2.690 |
Token | Jae |
Token ID | 34521 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ponds | +1.081 |
edin | +1.047 |
anooga | +0.992 |
xus | +0.967 |
waters | +0.937 |
Neg logit contributions | |
OW | -1.259 |
ORN | -1.210 |
therefore | -1.126 |
ILE | -1.124 |
ONES | -1.116 |
Token | Crow |
Token ID | 15502 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ponds | +7.116 |
xus | +6.686 |
edin | +6.552 |
waters | +6.406 |
anooga | +6.306 |
Neg logit contributions | |
ORN | -9.860 |
OW | -9.765 |
ONES | -9.128 |
therefore | -8.898 |
ILE | -8.871 |
Token | der |
Token ID | 1082 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ponds | +5.986 |
edin | +5.803 |
waters | +5.420 |
xus | +5.408 |
anooga | +5.364 |
Neg logit contributions | |
OW | -5.464 |
ORN | -5.351 |
ONES | -5.055 |
edit | -5.039 |
RIC | -4.966 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ponds | +3.050 |
edin | +2.920 |
anooga | +2.798 |
xus | +2.749 |
waters | +2.668 |
Neg logit contributions | |
OW | -3.011 |
ORN | -2.929 |
ONES | -2.684 |
ILE | -2.684 |
olute | -2.675 |
Token | whose |
Token ID | 3025 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ponds | +0.936 |
edin | +0.898 |
anooga | +0.867 |
xus | +0.848 |
bund | +0.820 |
Neg logit contributions | |
OW | -0.904 |
ORN | -0.862 |
olute | -0.794 |
therefore | -0.791 |
arget | -0.789 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ponds | +0.757 |
edin | +0.733 |
anooga | +0.704 |
xus | +0.684 |
waters | +0.656 |
Neg logit contributions | |
OW | -0.864 |
ORN | -0.821 |
therefore | -0.785 |
arget | -0.763 |
olute | -0.762 |
Token | exit |
Token ID | 8420 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ponds | +1.654 |
edin | +1.618 |
anooga | +1.534 |
xus | +1.488 |
bund | +1.443 |
Neg logit contributions | |
OW | -2.064 |
ORN | -1.951 |
therefore | -1.888 |
olute | -1.850 |
arget | -1.836 |
Token | polls |
Token ID | 9231 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ponds | +3.054 |
edin | +2.913 |
anooga | +2.759 |
bund | +2.560 |
xus | +2.553 |
Neg logit contributions | |
OW | -4.366 |
ORN | -4.173 |
therefore | -4.064 |
edit | -3.981 |
olute | -3.973 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ponds | +1.683 |
edin | +1.658 |
anooga | +1.595 |
xus | +1.552 |
waters | +1.497 |
Neg logit contributions | |
OW | -1.541 |
ORN | -1.456 |
therefore | -1.371 |
olute | -1.350 |
arget | -1.337 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
OW | +0.638 |
ORN | +0.604 |
therefore | +0.575 |
olute | +0.561 |
ONES | +0.555 |
Neg logit contributions | |
ponds | -0.706 |
edin | -0.696 |
anooga | -0.671 |
xus | -0.652 |
waters | -0.630 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ponds | +0.107 |
edin | +0.104 |
anooga | +0.103 |
xus | +0.100 |
waters | +0.095 |
Neg logit contributions | |
OW | -0.080 |
ORN | -0.075 |
therefore | -0.072 |
olute | -0.068 |
arget | -0.068 |
Token | Christ |
Token ID | 10684 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
edin | +0.593 |
ponds | +0.585 |
anooga | +0.570 |
xus | +0.555 |
waters | +0.541 |
Neg logit contributions | |
OW | -0.450 |
ORN | -0.426 |
therefore | -0.419 |
olute | -0.403 |
ONES | -0.393 |
Token | ie |
Token ID | 494 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
ponds | +7.672 |
edin | +7.510 |
xus | +7.333 |
amn | +7.028 |
anooga | +7.023 |
Neg logit contributions | |
ORN | -8.411 |
OW | -8.399 |
RIC | -7.886 |
ONES | -7.671 |
olute | -7.553 |
Token | � |
Token ID | 447 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ponds | +2.940 |
edin | +2.830 |
anooga | +2.702 |
xus | +2.682 |
bund | +2.611 |
Neg logit contributions | |
OW | -2.869 |
ORN | -2.753 |
ONES | -2.553 |
RIC | -2.551 |
olute | -2.540 |
Token | � |
Token ID | 247 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
ponds | +1.019 |
edin | +0.998 |
anooga | +0.981 |
xus | +0.955 |
waters | +0.907 |
Neg logit contributions | |
OW | -0.856 |
ORN | -0.812 |
therefore | -0.778 |
olute | -0.755 |
ONES | -0.744 |
Token | s |
Token ID | 82 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
OW | +0.079 |
ORN | +0.075 |
therefore | +0.071 |
ONES | +0.068 |
olute | +0.068 |
Neg logit contributions | |
ponds | -0.094 |
edin | -0.092 |
anooga | -0.089 |
xus | -0.088 |
waters | -0.084 |
Token | showing |
Token ID | 4478 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ponds | +0.349 |
edin | +0.340 |
anooga | +0.328 |
xus | +0.319 |
waters | +0.303 |
Neg logit contributions | |
OW | -0.408 |
ORN | -0.388 |
therefore | -0.371 |
ONES | -0.361 |
arget | -0.361 |
Token | � |
Token ID | 247 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
OW | +0.881 |
ORN | +0.816 |
therefore | +0.778 |
olute | +0.737 |
arget | +0.732 |
Neg logit contributions | |
ponds | -1.351 |
edin | -1.324 |
anooga | -1.299 |
xus | -1.268 |
waters | -1.218 |
Token | s |
Token ID | 82 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
OW | +0.421 |
ORN | +0.381 |
therefore | +0.355 |
olute | +0.329 |
ONES | +0.326 |
Neg logit contributions | |
ponds | -1.031 |
edin | -1.013 |
anooga | -0.995 |
xus | -0.977 |
waters | -0.944 |
Token | cabinet |
Token ID | 13447 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ponds | +0.247 |
edin | +0.238 |
anooga | +0.230 |
xus | +0.225 |
waters | +0.212 |
Neg logit contributions | |
OW | -0.322 |
ORN | -0.306 |
therefore | -0.294 |
arget | -0.286 |
olute | -0.286 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ponds | +1.119 |
edin | +1.080 |
anooga | +1.057 |
xus | +1.045 |
waters | +0.993 |
Neg logit contributions | |
OW | -0.979 |
ORN | -0.926 |
therefore | -0.862 |
arget | -0.850 |
olute | -0.847 |
Token | said |
Token ID | 531 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
OW | +0.405 |
ORN | +0.382 |
therefore | +0.362 |
olute | +0.355 |
arget | +0.351 |
Neg logit contributions | |
ponds | -0.448 |
edin | -0.433 |
anooga | -0.421 |
xus | -0.414 |
waters | -0.394 |
Token | Nigel |
Token ID | 28772 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ponds | +0.688 |
edin | +0.659 |
anooga | +0.635 |
xus | +0.630 |
waters | +0.603 |
Neg logit contributions | |
OW | -0.746 |
ORN | -0.709 |
therefore | -0.680 |
arget | -0.664 |
olute | -0.662 |
Token | Bank |
Token ID | 5018 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ponds | +7.714 |
edin | +7.479 |
Sou | +7.147 |
xus | +6.821 |
waters | +6.796 |
Neg logit contributions | |
OW | -8.502 |
ORN | -8.261 |
ILE | -7.841 |
RIC | -7.776 |
therefore | -7.707 |
Token | es |
Token ID | 274 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ponds | +0.553 |
edin | +0.546 |
anooga | +0.523 |
xus | +0.514 |
waters | +0.492 |
Neg logit contributions | |
OW | -0.524 |
ORN | -0.501 |
therefore | -0.477 |
ONES | -0.462 |
olute | -0.459 |
Token | , |
Token ID | 11 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
ponds | +4.204 |
edin | +4.073 |
xus | +3.905 |
anooga | +3.893 |
waters | +3.754 |
Neg logit contributions | |
OW | -4.535 |
ORN | -4.382 |
therefore | -4.144 |
ONES | -4.116 |
RIC | -4.112 |
Token | professor |
Token ID | 6240 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ponds | +3.331 |
edin | +3.061 |
xus | +3.013 |
anooga | +2.982 |
bund | +2.946 |
Neg logit contributions | |
OW | -3.487 |
ORN | -3.339 |
RIC | -3.170 |
arget | -3.155 |
ONES | -3.127 |
Token | at |
Token ID | 379 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ponds | +0.659 |
edin | +0.634 |
anooga | +0.619 |
xus | +0.608 |
waters | +0.584 |
Neg logit contributions | |
OW | -0.646 |
ORN | -0.612 |
therefore | -0.579 |
ONES | -0.568 |
olute | -0.563 |
Token | US |
Token ID | 1294 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
OW | +2.562 |
ORN | +2.420 |
therefore | +2.344 |
olute | +2.232 |
ONES | +2.206 |
Neg logit contributions | |
ponds | -2.643 |
edin | -2.586 |
anooga | -2.518 |
xus | -2.453 |
waters | -2.333 |
Token | President |
Token ID | 1992 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ponds | +0.465 |
edin | +0.453 |
anooga | +0.445 |
xus | +0.429 |
bund | +0.409 |
Neg logit contributions | |
OW | -0.563 |
ORN | -0.533 |
therefore | -0.512 |
ONES | -0.501 |
arget | -0.499 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ponds | +1.097 |
edin | +1.063 |
anooga | +1.037 |
xus | +1.016 |
waters | +0.969 |
Neg logit contributions | |
OW | -1.104 |
ORN | -1.059 |
therefore | -0.984 |
RIC | -0.974 |
olute | -0.972 |
Token |
|
Token ID | 198 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
OW | +0.729 |
ORN | +0.685 |
therefore | +0.654 |
olute | +0.635 |
arget | +0.627 |
Neg logit contributions | |
ponds | -0.871 |
edin | -0.857 |
anooga | -0.831 |
xus | -0.811 |
waters | -0.778 |
Token |
|
Token ID | 198 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
OW | +0.207 |
ORN | +0.192 |
therefore | +0.185 |
olute | +0.175 |
arget | +0.174 |
Neg logit contributions | |
ponds | -0.285 |
edin | -0.279 |
anooga | -0.276 |
xus | -0.269 |
waters | -0.255 |
Token | Brexit |
Token ID | 40730 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
OW | +0.259 |
ORN | +0.243 |
therefore | +0.237 |
olute | +0.228 |
ONES | +0.221 |
Neg logit contributions | |
ponds | -0.350 |
edin | -0.350 |
anooga | -0.338 |
xus | -0.331 |
waters | -0.320 |
Token | is |
Token ID | 318 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
ponds | +8.081 |
edin | +7.592 |
anooga | +7.431 |
xus | +7.321 |
outsourcing | +7.275 |
Neg logit contributions | |
OW | -7.890 |
ORN | -7.767 |
arget | -7.272 |
olute | -7.261 |
ILE | -7.259 |
Token | another |
Token ID | 1194 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
OW | +0.273 |
ORN | +0.259 |
therefore | +0.241 |
olute | +0.238 |
ONES | +0.237 |
Neg logit contributions | |
ponds | -0.293 |
edin | -0.285 |
anooga | -0.277 |
xus | -0.271 |
outsourcing | -0.259 |
Token | major |
Token ID | 1688 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ponds | +1.655 |
edin | +1.571 |
anooga | +1.518 |
xus | +1.505 |
outsourcing | +1.464 |
Neg logit contributions | |
OW | -1.661 |
ORN | -1.571 |
olute | -1.464 |
therefore | -1.457 |
arget | -1.444 |
Token | disrupt |
Token ID | 10114 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
OW | +1.331 |
ORN | +1.259 |
therefore | +1.212 |
olute | +1.166 |
ONES | +1.160 |
Neg logit contributions | |
ponds | -1.296 |
edin | -1.263 |
anooga | -1.232 |
xus | -1.198 |
waters | -1.138 |
Token | or |
Token ID | 273 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
OW | +2.072 |
ORN | +1.941 |
therefore | +1.861 |
olute | +1.776 |
arget | +1.763 |
Neg logit contributions | |
ponds | -2.667 |
edin | -2.606 |
anooga | -2.553 |
xus | -2.490 |
waters | -2.381 |
Token | business |
Token ID | 1597 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
OW | +0.962 |
ORN | +0.913 |
therefore | +0.879 |
arget | +0.852 |
olute | +0.851 |
Neg logit contributions | |
ponds | -0.802 |
edin | -0.779 |
anooga | -0.749 |
xus | -0.730 |
waters | -0.692 |
Token | of |
Token ID | 286 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ponds | +3.067 |
edin | +2.943 |
anooga | +2.848 |
xus | +2.774 |
outsourcing | +2.710 |
Neg logit contributions | |
OW | -2.995 |
ORN | -2.910 |
olute | -2.666 |
ONES | -2.659 |
arget | -2.645 |
Token | ignoring |
Token ID | 15482 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ponds | +1.604 |
edin | +1.525 |
anooga | +1.471 |
xus | +1.436 |
outsourcing | +1.406 |
Neg logit contributions | |
OW | -1.934 |
ORN | -1.872 |
therefore | -1.740 |
olute | -1.724 |
arget | -1.720 |
Token | what |
Token ID | 644 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
OW | +3.323 |
ORN | +3.139 |
therefore | +3.053 |
olute | +2.919 |
ONES | +2.903 |
Neg logit contributions | |
ponds | -3.103 |
edin | -3.049 |
anooga | -2.990 |
xus | -2.894 |
waters | -2.733 |
Token | The |
Token ID | 383 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
OW | +3.128 |
ORN | +2.948 |
therefore | +2.867 |
olute | +2.730 |
ONES | +2.718 |
Neg logit contributions | |
ponds | -3.079 |
edin | -3.022 |
anooga | -2.959 |
xus | -2.873 |
waters | -2.719 |
Token | Lord |
Token ID | 4453 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ponds | +1.159 |
edin | +1.126 |
anooga | +1.096 |
xus | +1.067 |
waters | +1.019 |
Neg logit contributions | |
OW | -1.432 |
ORN | -1.373 |
therefore | -1.328 |
arget | -1.276 |
RIC | -1.274 |
Token | has |
Token ID | 468 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
ponds | +7.137 |
edin | +6.859 |
mand | +6.404 |
waters | +6.341 |
bund | +6.303 |
Neg logit contributions | |
ORN | -8.952 |
OW | -8.747 |
ONES | -8.345 |
arget | -8.304 |
edit | -8.254 |
Token | commanded |
Token ID | 22419 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ponds | +2.379 |
edin | +2.297 |
anooga | +2.190 |
xus | +2.123 |
bund | +2.081 |
Neg logit contributions | |
OW | -2.503 |
ORN | -2.431 |
arget | -2.252 |
RIC | -2.251 |
therefore | -2.238 |
Token | me |
Token ID | 502 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
ponds | +5.115 |
edin | +4.954 |
anooga | +4.647 |
xus | +4.612 |
mand | +4.477 |
Neg logit contributions | |
OW | -6.696 |
ORN | -6.580 |
arget | -6.222 |
ONES | -6.143 |
RIC | -6.082 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ponds | +1.687 |
edin | +1.639 |
anooga | +1.590 |
xus | +1.545 |
waters | +1.468 |
Neg logit contributions | |
OW | -1.945 |
ORN | -1.886 |
therefore | -1.767 |
arget | -1.750 |
ONES | -1.739 |
Token | do |
Token ID | 466 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ponds | +0.039 |
edin | +0.038 |
anooga | +0.036 |
xus | +0.035 |
waters | +0.034 |
Neg logit contributions | |
OW | -0.048 |
ORN | -0.046 |
therefore | -0.044 |
arget | -0.043 |
olute | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
OW | +0.754 |
ORN | +0.714 |
therefore | +0.686 |
olute | +0.661 |
ONES | +0.658 |
Neg logit contributions | |
ponds | -0.735 |
edin | -0.717 |
anooga | -0.699 |
xus | -0.680 |
waters | -0.646 |
Token | Mountain |
Token ID | 9638 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ponds | +0.088 |
edin | +0.086 |
anooga | +0.082 |
xus | +0.080 |
waters | +0.077 |
Neg logit contributions | |
OW | -0.113 |
ORN | -0.108 |
therefore | -0.103 |
ONES | -0.101 |
arget | -0.101 |
Token | View |
Token ID | 3582 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
OW | +1.092 |
ORN | +1.016 |
therefore | +0.963 |
olute | +0.917 |
ONES | +0.910 |
Neg logit contributions | |
ponds | -1.748 |
edin | -1.712 |
anooga | -1.677 |
xus | -1.640 |
waters | -1.577 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
OW | +2.176 |
ORN | +2.032 |
therefore | +1.968 |
olute | +1.862 |
arget | +1.844 |
Neg logit contributions | |
ponds | -2.553 |
edin | -2.489 |
anooga | -2.447 |
xus | -2.386 |
waters | -2.268 |
Token | ( |
Token ID | 357 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ponds | +0.072 |
edin | +0.071 |
anooga | +0.068 |
xus | +0.066 |
waters | +0.064 |
Neg logit contributions | |
OW | -0.064 |
ORN | -0.061 |
therefore | -0.058 |
olute | -0.057 |
ONES | -0.056 |
Token | Justin |
Token ID | 33229 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
OW | +2.285 |
ORN | +2.145 |
therefore | +2.057 |
olute | +1.968 |
ONES | +1.955 |
Neg logit contributions | |
ponds | -2.775 |
edin | -2.714 |
anooga | -2.653 |
xus | -2.587 |
waters | -2.472 |
Token | Sullivan |
Token ID | 18501 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ponds | +6.876 |
edin | +6.378 |
anooga | +6.137 |
Sou | +6.125 |
xus | +6.115 |
Neg logit contributions | |
OW | -9.447 |
ORN | -8.965 |
RIC | -8.461 |
arget | -8.418 |
ONES | -8.408 |
Token | / |
Token ID | 14 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ponds | +1.001 |
edin | +0.989 |
anooga | +0.958 |
xus | +0.945 |
bund | +0.907 |
Neg logit contributions | |
OW | -0.657 |
ORN | -0.632 |
therefore | -0.576 |
ONES | -0.568 |
RIC | -0.564 |
Token | Getty |
Token ID | 6633 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ponds | +5.276 |
edin | +5.266 |
anooga | +5.159 |
xus | +5.087 |
waters | +4.990 |
Neg logit contributions | |
OW | -3.089 |
ORN | -2.958 |
therefore | -2.797 |
arget | -2.704 |
ONES | -2.675 |
Token | Images |
Token ID | 5382 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
ponds | +1.850 |
edin | +1.816 |
anooga | +1.767 |
xus | +1.713 |
waters | +1.631 |
Neg logit contributions | |
OW | -1.978 |
ORN | -1.895 |
therefore | -1.812 |
ONES | -1.756 |
arget | -1.750 |
Token | ) |
Token ID | 8 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ponds | +0.343 |
edin | +0.336 |
anooga | +0.324 |
xus | +0.318 |
waters | +0.301 |
Neg logit contributions | |
OW | -0.358 |
ORN | -0.339 |
therefore | -0.326 |
olute | -0.315 |
ONES | -0.313 |
Token | Indiana |
Token ID | 10278 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ponds | +0.168 |
edin | +0.164 |
anooga | +0.157 |
xus | +0.152 |
waters | +0.146 |
Neg logit contributions | |
OW | -0.204 |
ORN | -0.194 |
therefore | -0.187 |
olute | -0.183 |
ONES | -0.181 |
Token | Gov |
Token ID | 10964 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
OW | +1.605 |
ORN | +1.534 |
therefore | +1.488 |
olute | +1.452 |
arget | +1.447 |
Neg logit contributions | |
ponds | -0.974 |
edin | -0.937 |
anooga | -0.902 |
xus | -0.868 |
waters | -0.813 |
Token | . |
Token ID | 13 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
ponds | +0.157 |
edin | +0.152 |
anooga | +0.146 |
xus | +0.143 |
waters | +0.139 |
Neg logit contributions | |
OW | -0.144 |
ORN | -0.138 |
therefore | -0.131 |
olute | -0.126 |
arget | -0.126 |
Token | Mike |
Token ID | 4995 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
OW | +0.289 |
ORN | +0.277 |
therefore | +0.264 |
arget | +0.258 |
olute | +0.258 |
Neg logit contributions | |
ponds | -0.227 |
edin | -0.216 |
anooga | -0.206 |
xus | -0.203 |
outsourcing | -0.196 |
Token | Pence |
Token ID | 17339 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ponds | +1.310 |
edin | +1.274 |
anooga | +1.218 |
xus | +1.199 |
waters | +1.141 |
Neg logit contributions | |
OW | -1.503 |
ORN | -1.442 |
therefore | -1.369 |
olute | -1.337 |
arget | -1.328 |
Token | Pence |
Token ID | 17339 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ponds | +5.571 |
edin | +5.342 |
anooga | +4.992 |
bund | +4.989 |
xus | +4.944 |
Neg logit contributions | |
OW | -5.536 |
ORN | -5.396 |
olute | -5.048 |
ONES | -5.015 |
edit | -4.981 |
Token | is |
Token ID | 318 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ponds | +8.018 |
edin | +7.602 |
xus | +7.262 |
anooga | +7.233 |
outsourcing | +7.183 |
Neg logit contributions | |
OW | -7.619 |
ORN | -7.422 |
olute | -6.873 |
ONES | -6.825 |
edit | -6.793 |
Token | rumored |
Token ID | 29586 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
OW | +0.604 |
ORN | +0.572 |
therefore | +0.546 |
olute | +0.529 |
ONES | +0.526 |
Neg logit contributions | |
ponds | -0.608 |
edin | -0.592 |
anooga | -0.576 |
xus | -0.560 |
waters | -0.533 |
Token | to |
Token ID | 284 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ponds | +3.341 |
edin | +3.293 |
anooga | +3.157 |
xus | +3.026 |
bund | +2.943 |
Neg logit contributions | |
OW | -4.223 |
ORN | -4.095 |
therefore | -3.830 |
ONES | -3.819 |
olute | -3.804 |
Token | be |
Token ID | 307 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ponds | +1.809 |
edin | +1.787 |
anooga | +1.641 |
xus | +1.611 |
bund | +1.573 |
Neg logit contributions | |
OW | -2.745 |
ORN | -2.672 |
ONES | -2.493 |
olute | -2.491 |
therefore | -2.474 |
Token | one |
Token ID | 530 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ponds | +1.236 |
edin | +1.206 |
anooga | +1.149 |
xus | +1.114 |
bund | +1.093 |
Neg logit contributions | |
OW | -1.468 |
ORN | -1.417 |
therefore | -1.320 |
olute | -1.310 |
RIC | -1.298 |
Token | on |
Token ID | 319 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ponds | +2.292 |
edin | +2.235 |
anooga | +2.147 |
xus | +2.103 |
waters | +2.002 |
Neg logit contributions | |
OW | -2.600 |
ORN | -2.477 |
therefore | -2.366 |
olute | -2.302 |
arget | -2.287 |
Token | your |
Token ID | 534 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ponds | +1.302 |
edin | +1.272 |
anooga | +1.230 |
xus | +1.203 |
waters | +1.149 |
Neg logit contributions | |
OW | -1.231 |
ORN | -1.161 |
therefore | -1.107 |
olute | -1.071 |
ONES | -1.067 |
Token | device |
Token ID | 3335 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
OW | +0.680 |
ORN | +0.628 |
therefore | +0.611 |
olute | +0.568 |
ONES | +0.562 |
Neg logit contributions | |
ponds | -1.094 |
edin | -1.073 |
anooga | -1.066 |
xus | -1.027 |
waters | -0.993 |
Token | Media |
Token ID | 6343 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
OW | +0.686 |
ORN | +0.647 |
therefore | +0.639 |
ONES | +0.608 |
olute | +0.607 |
Neg logit contributions | |
ponds | -0.506 |
edin | -0.491 |
anooga | -0.485 |
xus | -0.465 |
perty | -0.436 |
Token | caption |
Token ID | 8305 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ponds | +1.605 |
edin | +1.533 |
anooga | +1.454 |
xus | +1.405 |
waters | +1.283 |
Neg logit contributions | |
OW | -3.613 |
ORN | -3.478 |
therefore | -3.364 |
olute | -3.284 |
ONES | -3.277 |
Token | Nigel |
Token ID | 28772 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ponds | +0.437 |
edin | +0.426 |
anooga | +0.408 |
xus | +0.398 |
waters | +0.384 |
Neg logit contributions | |
OW | -0.486 |
ORN | -0.463 |
therefore | -0.445 |
olute | -0.434 |
arget | -0.428 |
Token | Farage |
Token ID | 33904 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ponds | +5.547 |
edin | +5.007 |
xus | +4.784 |
Sou | +4.720 |
waters | +4.677 |
Neg logit contributions | |
OW | -10.496 |
ORN | -10.250 |
ILE | -9.973 |
ONES | -9.858 |
ARS | -9.816 |
Token | : |
Token ID | 25 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ponds | +5.039 |
edin | +4.702 |
bund | +4.497 |
xus | +4.417 |
anooga | +4.384 |
Neg logit contributions | |
OW | -5.397 |
ORN | -5.267 |
olute | -4.917 |
ONES | -4.906 |
RIC | -4.900 |
Token | " |
Token ID | 366 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ponds | +1.493 |
edin | +1.440 |
anooga | +1.390 |
xus | +1.363 |
waters | +1.283 |
Neg logit contributions | |
OW | -1.982 |
ORN | -1.892 |
therefore | -1.814 |
olute | -1.775 |
ONES | -1.768 |
Token | Lord |
Token ID | 22438 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ponds | +2.028 |
edin | +2.017 |
anooga | +1.947 |
xus | +1.915 |
waters | +1.874 |
Neg logit contributions | |
OW | -1.516 |
ORN | -1.426 |
therefore | -1.400 |
olute | -1.345 |
ONES | -1.301 |
Token | Hes |
Token ID | 44773 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ponds | +7.100 |
edin | +6.943 |
xus | +6.473 |
anooga | +6.403 |
bund | +6.269 |
Neg logit contributions | |
ORN | -8.038 |
OW | -7.937 |
ONES | -7.504 |
arget | -7.387 |
INC | -7.265 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
OW | +1.320 |
ORN | +1.242 |
therefore | +1.194 |
olute | +1.143 |
ONES | +1.134 |
Neg logit contributions | |
ponds | -1.490 |
edin | -1.455 |
anooga | -1.423 |
xus | -1.387 |
waters | -1.321 |
Token | Calif |
Token ID | 3192 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
OW | +0.093 |
ORN | +0.088 |
therefore | +0.085 |
arget | +0.083 |
olute | +0.082 |
Neg logit contributions | |
ponds | -0.084 |
edin | -0.082 |
anooga | -0.080 |
xus | -0.077 |
waters | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
OW | +1.367 |
ORN | +1.282 |
therefore | +1.216 |
olute | +1.162 |
ONES | +1.158 |
Neg logit contributions | |
ponds | -1.820 |
edin | -1.773 |
anooga | -1.743 |
xus | -1.708 |
waters | -1.623 |
Token | Photo |
Token ID | 5555 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
OW | +0.345 |
ORN | +0.326 |
therefore | +0.315 |
olute | +0.304 |
arget | +0.304 |
Neg logit contributions | |
ponds | -0.367 |
edin | -0.357 |
anooga | -0.348 |
xus | -0.336 |
waters | -0.325 |
Token | : |
Token ID | 25 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
OW | +1.983 |
ORN | +1.873 |
therefore | +1.800 |
olute | +1.732 |
ONES | +1.722 |
Neg logit contributions | |
ponds | -2.044 |
edin | -1.995 |
anooga | -1.947 |
xus | -1.894 |
waters | -1.802 |
Token | Justin |
Token ID | 10799 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
ponds | +2.939 |
edin | +2.847 |
anooga | +2.683 |
xus | +2.620 |
waters | +2.605 |
Neg logit contributions | |
OW | -3.169 |
ORN | -3.011 |
olute | -2.872 |
therefore | -2.872 |
arget | -2.863 |
Token | Sullivan |
Token ID | 18501 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
ponds | +6.819 |
edin | +6.462 |
anooga | +6.243 |
Sou | +6.199 |
xus | +6.199 |
Neg logit contributions | |
OW | -9.362 |
ORN | -8.852 |
RIC | -8.485 |
arget | -8.434 |
ILE | -8.362 |
Token | / |
Token ID | 14 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ponds | +1.583 |
edin | +1.576 |
anooga | +1.511 |
xus | +1.477 |
waters | +1.430 |
Neg logit contributions | |
OW | -1.114 |
ORN | -1.062 |
therefore | -0.985 |
arget | -0.963 |
olute | -0.961 |
Token | Getty |
Token ID | 6633 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ponds | +6.951 |
edin | +6.927 |
anooga | +6.885 |
waters | +6.697 |
xus | +6.684 |
Neg logit contributions | |
OW | -4.632 |
ORN | -4.447 |
therefore | -4.244 |
arget | -4.152 |
olute | -4.038 |
Token | Images |
Token ID | 5382 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ponds | +2.396 |
edin | +2.349 |
anooga | +2.283 |
xus | +2.181 |
waters | +2.114 |
Neg logit contributions | |
OW | -2.695 |
ORN | -2.600 |
therefore | -2.470 |
ONES | -2.404 |
arget | -2.397 |
Token |
|
Token ID | 198 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ponds | +0.679 |
edin | +0.668 |
anooga | +0.646 |
xus | +0.631 |
waters | +0.607 |
Neg logit contributions | |
OW | -0.576 |
ORN | -0.544 |
therefore | -0.518 |
olute | -0.498 |
ONES | -0.497 |
Token | , |
Token ID | 11 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
ponds | +2.375 |
edin | +2.292 |
anooga | +2.209 |
xus | +2.181 |
waters | +2.096 |
Neg logit contributions | |
OW | -2.294 |
ORN | -2.189 |
therefore | -2.105 |
ONES | -2.043 |
olute | -2.037 |
Token | owner |
Token ID | 4870 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
ponds | +3.420 |
edin | +3.144 |
anooga | +3.099 |
xus | +3.021 |
bund | +3.015 |
Neg logit contributions | |
OW | -3.757 |
ORN | -3.620 |
therefore | -3.430 |
ONES | -3.426 |
olute | -3.399 |
Token | of |
Token ID | 286 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ponds | +3.085 |
edin | +2.953 |
anooga | +2.944 |
xus | +2.786 |
waters | +2.739 |
Neg logit contributions | |
OW | -2.736 |
ORN | -2.624 |
therefore | -2.480 |
ONES | -2.428 |
arget | -2.405 |
Token | Sp |
Token ID | 1338 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ponds | +0.993 |
edin | +0.944 |
anooga | +0.919 |
xus | +0.902 |
waters | +0.857 |
Neg logit contributions | |
OW | -1.137 |
ORN | -1.089 |
therefore | -1.054 |
olute | -1.015 |
edit | -1.013 |
Token | angler |
Token ID | 49910 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
OW | +0.855 |
ORN | +0.815 |
therefore | +0.788 |
ONES | +0.757 |
olute | +0.754 |
Neg logit contributions | |
ponds | -0.713 |
edin | -0.696 |
anooga | -0.678 |
xus | -0.657 |
waters | -0.620 |
Token | Vine |
Token ID | 28879 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ponds | +1.454 |
edin | +1.389 |
anooga | +1.348 |
xus | +1.331 |
waters | +1.282 |
Neg logit contributions | |
OW | -1.554 |
ORN | -1.501 |
therefore | -1.449 |
ONES | -1.396 |
olute | -1.393 |
Token | yards |
Token ID | 33750 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
ponds | +4.379 |
edin | +3.800 |
waters | +3.529 |
anooga | +3.464 |
weaving | +3.328 |
Neg logit contributions | |
ORN | -11.499 |
OW | -11.456 |
ONES | -10.976 |
therefore | -10.967 |
ILE | -10.938 |
Token | in |
Token ID | 287 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ponds | +3.578 |
edin | +3.386 |
anooga | +3.241 |
xus | +3.151 |
waters | +3.144 |
Neg logit contributions | |
OW | -3.710 |
ORN | -3.578 |
therefore | -3.416 |
ONES | -3.355 |
arget | -3.344 |
Token | the |
Token ID | 262 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ponds | +2.430 |
edin | +2.315 |
anooga | +2.235 |
xus | +2.177 |
waters | +2.119 |
Neg logit contributions | |
OW | -2.795 |
ORN | -2.689 |
therefore | -2.602 |
ONES | -2.504 |
RIC | -2.496 |
Token | U |
Token ID | 471 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ponds | +2.763 |
edin | +2.594 |
anooga | +2.492 |
xus | +2.458 |
waters | +2.380 |
Neg logit contributions | |
OW | -3.280 |
ORN | -3.135 |
therefore | -3.040 |
arget | -2.963 |
ILE | -2.947 |
Token | mp |
Token ID | 3149 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
ponds | +1.275 |
edin | +1.235 |
anooga | +1.198 |
xus | +1.195 |
waters | +1.150 |
Neg logit contributions | |
OW | -1.078 |
ORN | -1.032 |
therefore | -1.004 |
ONES | -0.960 |
arget | -0.949 |
Token | has |
Token ID | 468 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
ponds | +0.182 |
edin | +0.177 |
anooga | +0.171 |
xus | +0.168 |
waters | +0.160 |
Neg logit contributions | |
OW | -0.173 |
ORN | -0.165 |
therefore | -0.154 |
olute | -0.152 |
arget | -0.151 |
Token | repeatedly |
Token ID | 7830 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ponds | +0.094 |
edin | +0.091 |
anooga | +0.088 |
xus | +0.086 |
bund | +0.083 |
Neg logit contributions | |
OW | -0.092 |
ORN | -0.088 |
ONES | -0.081 |
therefore | -0.081 |
olute | -0.081 |
Token | criticized |
Token ID | 12318 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
OW | +0.484 |
ORN | +0.458 |
therefore | +0.428 |
ONES | +0.421 |
olute | +0.420 |
Neg logit contributions | |
ponds | -0.546 |
edin | -0.531 |
anooga | -0.513 |
xus | -0.502 |
bund | -0.483 |
Token | President |
Token ID | 1992 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
OW | +2.274 |
ORN | +2.146 |
therefore | +2.074 |
olute | +1.980 |
arget | +1.972 |
Neg logit contributions | |
ponds | -2.293 |
edin | -2.246 |
anooga | -2.194 |
xus | -2.133 |
waters | -2.024 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ponds | +0.246 |
edin | +0.240 |
anooga | +0.232 |
xus | +0.226 |
waters | +0.215 |
Neg logit contributions | |
OW | -0.273 |
ORN | -0.260 |
therefore | -0.248 |
ONES | -0.241 |
olute | -0.241 |
Token | Donald |
Token ID | 3759 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ponds | +4.583 |
edin | +4.379 |
anooga | +4.280 |
xus | +4.148 |
outsourcing | +4.127 |
Neg logit contributions | |
OW | -4.799 |
ORN | -4.739 |
ONES | -4.373 |
arget | -4.331 |
RIC | -4.330 |
Token | John |
Token ID | 1757 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
ponds | +7.559 |
edin | +7.452 |
anooga | +7.306 |
xus | +6.976 |
Sou | +6.943 |
Neg logit contributions | |
OW | -7.768 |
ORN | -7.730 |
therefore | -7.413 |
ONES | -7.371 |
olute | -7.328 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ponds | +0.222 |
edin | +0.215 |
anooga | +0.210 |
xus | +0.203 |
waters | +0.191 |
Neg logit contributions | |
OW | -0.294 |
ORN | -0.280 |
therefore | -0.271 |
olute | -0.261 |
arget | -0.260 |
Token | House |
Token ID | 18102 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
edin | +5.219 |
ponds | +5.170 |
anooga | +5.136 |
waters | +4.947 |
xus | +4.914 |
Neg logit contributions | |
therefore | -5.496 |
OW | -5.300 |
ORN | -5.162 |
| -5.019 |
olute | -4.996 |
Token | committee |
Token ID | 5583 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ponds | +2.327 |
anooga | +2.138 |
edin | +2.109 |
xus | +2.089 |
waters | +2.011 |
Neg logit contributions | |
OW | -2.773 |
ORN | -2.676 |
therefore | -2.543 |
edit | -2.510 |
arget | -2.504 |
Token | believes |
Token ID | 5804 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
OW | +1.267 |
ORN | +1.215 |
therefore | +1.184 |
olute | +1.149 |
ONES | +1.141 |
Neg logit contributions | |
ponds | -0.610 |
edin | -0.592 |
anooga | -0.570 |
xus | -0.542 |
waters | -0.495 |
Token | igue |
Token ID | 15212 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
OW | +2.556 |
ORN | +2.432 |
therefore | +2.327 |
olute | +2.243 |
ONES | +2.234 |
Neg logit contributions | |
ponds | -2.533 |
edin | -2.458 |
anooga | -2.392 |
xus | -2.328 |
waters | -2.217 |
Token | usually |
Token ID | 3221 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
OW | +1.005 |
ORN | +0.954 |
therefore | +0.900 |
olute | +0.881 |
arget | +0.878 |
Neg logit contributions | |
ponds | -1.086 |
edin | -1.048 |
anooga | -1.018 |
xus | -0.991 |
waters | -0.956 |
Token | follows |
Token ID | 5679 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
OW | +2.190 |
ORN | +2.068 |
therefore | +1.993 |
olute | +1.914 |
ONES | +1.903 |
Neg logit contributions | |
ponds | -2.208 |
edin | -2.155 |
anooga | -2.103 |
xus | -2.045 |
waters | -1.944 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ponds | +1.164 |
edin | +1.117 |
anooga | +1.089 |
xus | +1.061 |
waters | +1.025 |
Neg logit contributions | |
OW | -1.107 |
ORN | -1.052 |
therefore | -0.983 |
olute | -0.975 |
arget | -0.962 |
Token | both |
Token ID | 1111 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
OW | +1.230 |
ORN | +1.159 |
therefore | +1.084 |
olute | +1.065 |
arget | +1.054 |
Neg logit contributions | |
ponds | -1.519 |
edin | -1.475 |
anooga | -1.444 |
xus | -1.401 |
bund | -1.344 |
Token | physically |
Token ID | 10170 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
OW | +2.458 |
ORN | +2.308 |
therefore | +2.229 |
olute | +2.118 |
arget | +2.106 |
Neg logit contributions | |
ponds | -2.848 |
edin | -2.792 |
anooga | -2.733 |
xus | -2.663 |
waters | -2.539 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
OW | +7.981 |
therefore | +7.375 |
ORN | +7.101 |
olute | +6.414 |
edit | +6.398 |
Neg logit contributions | |
ponds | -14.606 |
edin | -14.471 |
xus | -14.104 |
anooga | -14.004 |
waters | -13.337 |
Token | emotionally |
Token ID | 17991 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
OW | +1.411 |
ORN | +1.339 |
therefore | +1.281 |
olute | +1.245 |
ONES | +1.241 |
Neg logit contributions | |
ponds | -1.239 |
edin | -1.206 |
anooga | -1.177 |
xus | -1.136 |
waters | -1.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
OW | +5.695 |
ORN | +5.194 |
therefore | +5.188 |
olute | +4.787 |
edit | +4.744 |
Neg logit contributions | |
ponds | -7.742 |
edin | -7.678 |
anooga | -7.497 |
xus | -7.404 |
waters | -6.962 |
Token |
|
Token ID | 198 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
OW | +0.494 |
ORN | +0.470 |
therefore | +0.445 |
olute | +0.437 |
arget | +0.432 |
Neg logit contributions | |
ponds | -0.529 |
edin | -0.515 |
anooga | -0.495 |
xus | -0.481 |
waters | -0.467 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
OW | +1.472 |
ORN | +1.330 |
therefore | +1.317 |
edit | +1.235 |
arget | +1.218 |
Neg logit contributions | |
ponds | -2.231 |
anooga | -2.198 |
edin | -2.169 |
xus | -2.121 |
perty | -2.050 |
Token | , |
Token ID | 11 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
OW | +0.013 |
ORN | +0.012 |
therefore | +0.011 |
olute | +0.011 |
arget | +0.011 |
Neg logit contributions | |
ponds | -0.014 |
edin | -0.013 |
anooga | -0.013 |
xus | -0.013 |
waters | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ponds | +1.277 |
edin | +1.216 |
anooga | +1.172 |
xus | +1.159 |
waters | +1.122 |
Neg logit contributions | |
OW | -1.313 |
ORN | -1.247 |
olute | -1.166 |
therefore | -1.163 |
RIC | -1.155 |
Token | BBC |
Token ID | 7823 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ponds | +0.570 |
edin | +0.542 |
anooga | +0.520 |
xus | +0.517 |
waters | +0.492 |
Neg logit contributions | |
OW | -0.747 |
ORN | -0.714 |
therefore | -0.679 |
arget | -0.664 |
olute | -0.664 |
Token | 's |
Token ID | 338 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
OW | +0.986 |
ORN | +0.928 |
therefore | +0.878 |
olute | +0.852 |
arget | +0.845 |
Neg logit contributions | |
ponds | -1.225 |
edin | -1.199 |
anooga | -1.169 |
xus | -1.142 |
waters | -1.092 |
Token | M |
Token ID | 337 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
OW | +2.221 |
ORN | +2.092 |
therefore | +2.040 |
olute | +1.944 |
ONES | +1.944 |
Neg logit contributions | |
ponds | -2.054 |
edin | -2.011 |
anooga | -1.972 |
xus | -1.914 |
waters | -1.795 |
Token | Ily |
Token ID | 49804 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
OW | +0.943 |
ORN | +0.883 |
therefore | +0.848 |
olute | +0.814 |
arget | +0.810 |
Neg logit contributions | |
ponds | -1.106 |
edin | -1.078 |
anooga | -1.057 |
xus | -1.030 |
waters | -0.982 |
Token | as |
Token ID | 292 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
OW | +8.146 |
therefore | +6.736 |
ORN | +6.679 |
arget | +6.667 |
edit | +6.580 |
Neg logit contributions | |
ponds | -11.800 |
anooga | -11.238 |
perty | -11.168 |
xus | -11.119 |
piping | -10.909 |
Token | Khan |
Token ID | 11356 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
OW | +0.780 |
ORN | +0.742 |
therefore | +0.717 |
olute | +0.692 |
ONES | +0.688 |
Neg logit contributions | |
ponds | -0.633 |
edin | -0.616 |
anooga | -0.599 |
xus | -0.580 |
waters | -0.548 |
Token | in |
Token ID | 287 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
edin | +1.712 |
ponds | +1.706 |
anooga | +1.615 |
xus | +1.562 |
waters | +1.520 |
Neg logit contributions | |
OW | -1.914 |
ORN | -1.867 |
therefore | -1.727 |
olute | -1.706 |
ILE | -1.698 |
Token | Islamabad |
Token ID | 36878 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ponds | +1.099 |
edin | +1.067 |
anooga | +1.003 |
xus | +0.993 |
waters | +0.957 |
Neg logit contributions | |
OW | -1.352 |
ORN | -1.291 |
therefore | -1.230 |
olute | -1.203 |
RIC | -1.203 |
Token | reports |
Token ID | 3136 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ponds | +1.547 |
edin | +1.536 |
anooga | +1.474 |
xus | +1.426 |
waters | +1.379 |
Neg logit contributions | |
OW | -1.682 |
ORN | -1.603 |
olute | -1.492 |
therefore | -1.490 |
ILE | -1.487 |
Token | Texas |
Token ID | 3936 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
OW | +0.004 |
ORN | +0.004 |
therefore | +0.003 |
olute | +0.003 |
arget | +0.003 |
Neg logit contributions | |
ponds | -0.003 |
edin | -0.003 |
anooga | -0.003 |
xus | -0.003 |
waters | -0.003 |
Token | Tech |
Token ID | 9634 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
ponds | +2.083 |
edin | +1.924 |
anooga | +1.836 |
xus | +1.724 |
waters | +1.555 |
Neg logit contributions | |
OW | -7.028 |
ORN | -6.710 |
arget | -6.615 |
therefore | -6.600 |
edit | -6.553 |
Token | University |
Token ID | 2059 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
OW | +3.346 |
ORN | +3.161 |
therefore | +3.045 |
olute | +2.908 |
ONES | +2.887 |
Neg logit contributions | |
ponds | -3.483 |
edin | -3.414 |
anooga | -3.340 |
xus | -3.233 |
waters | -3.072 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
OW | +0.504 |
ORN | +0.476 |
therefore | +0.455 |
arget | +0.442 |
ONES | +0.441 |
Neg logit contributions | |
ponds | -0.528 |
edin | -0.514 |
anooga | -0.499 |
xus | -0.487 |
waters | -0.466 |
Token | A |
Token ID | 317 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
OW | +1.043 |
ORN | +0.985 |
therefore | +0.949 |
olute | +0.917 |
arget | +0.912 |
Neg logit contributions | |
ponds | -1.048 |
edin | -1.024 |
anooga | -0.994 |
xus | -0.969 |
waters | -0.927 |
Token | shooting |
Token ID | 4395 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
OW | +0.459 |
ORN | +0.435 |
therefore | +0.420 |
olute | +0.405 |
arget | +0.404 |
Neg logit contributions | |
ponds | -0.419 |
edin | -0.408 |
anooga | -0.397 |
xus | -0.388 |
waters | -0.369 |
Token | has |
Token ID | 468 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
OW | +8.330 |
therefore | +7.799 |
ORN | +7.762 |
olute | +7.129 |
arget | +7.065 |
Neg logit contributions | |
edin | -10.486 |
ponds | -10.399 |
anooga | -10.254 |
xus | -10.106 |
perty | -9.631 |
Token | been |
Token ID | 587 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
OW | +2.895 |
ORN | +2.705 |
therefore | +2.589 |
olute | +2.456 |
ONES | +2.437 |
Neg logit contributions | |
ponds | -4.117 |
edin | -4.036 |
anooga | -3.948 |
xus | -3.862 |
waters | -3.691 |
Token | reported |
Token ID | 2098 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
OW | +2.694 |
ORN | +2.479 |
therefore | +2.371 |
olute | +2.219 |
ONES | +2.188 |
Neg logit contributions | |
ponds | -4.963 |
edin | -4.871 |
anooga | -4.778 |
xus | -4.682 |
waters | -4.493 |
Token | at |
Token ID | 379 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
OW | +0.409 |
ORN | +0.388 |
therefore | +0.368 |
olute | +0.359 |
ONES | +0.358 |
Neg logit contributions | |
ponds | -0.404 |
edin | -0.394 |
anooga | -0.382 |
xus | -0.373 |
waters | -0.356 |
Token | the |
Token ID | 262 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
OW | +2.359 |
ORN | +2.232 |
therefore | +2.152 |
olute | +2.070 |
ONES | +2.059 |
Neg logit contributions | |
ponds | -2.240 |
edin | -2.184 |
anooga | -2.130 |
xus | -2.068 |
waters | -1.963 |
Token | Wrong |
Token ID | 28843 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
OW | +1.363 |
ORN | +1.295 |
therefore | +1.248 |
olute | +1.205 |
ONES | +1.202 |
Neg logit contributions | |
ponds | -1.155 |
edin | -1.121 |
anooga | -1.092 |
xus | -1.063 |
waters | -1.003 |
Token | Eye |
Token ID | 14144 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
ponds | +1.284 |
edin | +1.270 |
anooga | +1.212 |
xus | +1.200 |
waters | +1.131 |
Neg logit contributions | |
OW | -1.400 |
ORN | -1.337 |
therefore | -1.277 |
olute | -1.237 |
ONES | -1.236 |
Token | here |
Token ID | 994 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
OW | +3.458 |
ORN | +3.231 |
therefore | +3.125 |
olute | +2.969 |
edit | +2.954 |
Neg logit contributions | |
ponds | -3.958 |
edin | -3.871 |
anooga | -3.799 |
xus | -3.656 |
waters | -3.515 |
Token | .) |
Token ID | 2014 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
OW | +1.440 |
ORN | +1.356 |
therefore | +1.290 |
olute | +1.239 |
ONES | +1.232 |
Neg logit contributions | |
ponds | -1.832 |
edin | -1.791 |
anooga | -1.750 |
xus | -1.713 |
waters | -1.635 |
Token | When |
Token ID | 1649 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
OW | +2.004 |
ORN | +1.881 |
therefore | +1.813 |
olute | +1.730 |
ONES | +1.721 |
Neg logit contributions | |
ponds | -2.273 |
edin | -2.218 |
anooga | -2.177 |
xus | -2.117 |
waters | -2.016 |
Token | picking |
Token ID | 10868 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ponds | +0.470 |
edin | +0.458 |
anooga | +0.444 |
xus | +0.436 |
bund | +0.415 |
Neg logit contributions | |
OW | -0.462 |
ORN | -0.437 |
therefore | -0.415 |
olute | -0.404 |
ONES | -0.402 |
Token | your |
Token ID | 534 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
OW | +8.323 |
therefore | +7.925 |
ORN | +7.858 |
edit | +7.282 |
olute | +7.194 |
Neg logit contributions | |
ponds | -10.376 |
edin | -10.336 |
anooga | -10.157 |
xus | -9.489 |
amia | -9.338 |
Token | sol |
Token ID | 1540 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
OW | +2.199 |
ORN | +2.080 |
therefore | +2.005 |
olute | +1.929 |
ONES | +1.920 |
Neg logit contributions | |
ponds | -2.092 |
edin | -2.039 |
anooga | -1.988 |
xus | -1.933 |
waters | -1.834 |
Token | os |
Token ID | 418 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
OW | +3.046 |
ORN | +2.835 |
therefore | +2.756 |
olute | +2.640 |
arget | +2.615 |
Neg logit contributions | |
ponds | -3.499 |
edin | -3.402 |
anooga | -3.338 |
xus | -3.227 |
waters | -3.095 |
Token | , |
Token ID | 11 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
OW | +1.919 |
ORN | +1.811 |
therefore | +1.719 |
olute | +1.667 |
ONES | +1.662 |
Neg logit contributions | |
ponds | -2.128 |
edin | -2.081 |
anooga | -2.025 |
xus | -1.985 |
waters | -1.882 |
Token | you |
Token ID | 345 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ponds | +0.238 |
edin | +0.230 |
anooga | +0.221 |
xus | +0.217 |
bund | +0.206 |
Neg logit contributions | |
OW | -0.264 |
ORN | -0.252 |
therefore | -0.237 |
olute | -0.234 |
arget | -0.233 |
Token | The |
Token ID | 383 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
OW | +0.645 |
ORN | +0.613 |
therefore | +0.586 |
olute | +0.566 |
ONES | +0.563 |
Neg logit contributions | |
ponds | -0.688 |
edin | -0.675 |
anooga | -0.651 |
xus | -0.633 |
waters | -0.612 |
Token | woman |
Token ID | 2415 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
OW | +1.699 |
ORN | +1.615 |
therefore | +1.564 |
olute | +1.510 |
ONES | +1.501 |
Neg logit contributions | |
ponds | -1.314 |
edin | -1.278 |
anooga | -1.243 |
xus | -1.204 |
waters | -1.133 |
Token | then |
Token ID | 788 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
OW | +2.152 |
ORN | +2.013 |
therefore | +1.977 |
olute | +1.851 |
ONES | +1.840 |
Neg logit contributions | |
ponds | -2.481 |
edin | -2.437 |
anooga | -2.390 |
xus | -2.325 |
waters | -2.202 |
Token | appears |
Token ID | 3568 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
OW | +0.369 |
ORN | +0.350 |
therefore | +0.331 |
olute | +0.324 |
arget | +0.322 |
Neg logit contributions | |
ponds | -0.374 |
edin | -0.363 |
anooga | -0.353 |
xus | -0.344 |
waters | -0.329 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
OW | +0.188 |
ORN | +0.178 |
therefore | +0.172 |
olute | +0.166 |
ONES | +0.165 |
Neg logit contributions | |
ponds | -0.171 |
edin | -0.167 |
anooga | -0.162 |
xus | -0.157 |
waters | -0.149 |
Token | kicks |
Token ID | 17364 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ponds | +0.590 |
edin | +0.574 |
anooga | +0.542 |
xus | +0.528 |
bund | +0.510 |
Neg logit contributions | |
OW | -0.815 |
ORN | -0.784 |
therefore | -0.738 |
olute | -0.732 |
arget | -0.729 |
Token | him |
Token ID | 683 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
OW | +7.762 |
therefore | +7.182 |
ORN | +7.015 |
olute | +6.648 |
edit | +6.603 |
Neg logit contributions | |
anooga | -10.481 |
edin | -10.435 |
ponds | -10.397 |
xus | -10.092 |
amia | -9.371 |
Token | twice |
Token ID | 5403 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
OW | +2.236 |
ORN | +2.098 |
therefore | +2.037 |
olute | +1.936 |
arget | +1.925 |
Neg logit contributions | |
ponds | -2.445 |
edin | -2.396 |
anooga | -2.346 |
xus | -2.280 |
waters | -2.165 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
OW | +1.449 |
ORN | +1.369 |
therefore | +1.311 |
olute | +1.264 |
arget | +1.257 |
Neg logit contributions | |
ponds | -1.529 |
edin | -1.491 |
anooga | -1.454 |
xus | -1.416 |
waters | -1.351 |
Token | and |
Token ID | 290 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
OW | +1.055 |
ORN | +1.000 |
therefore | +0.952 |
olute | +0.925 |
arget | +0.916 |
Neg logit contributions | |
ponds | -1.100 |
edin | -1.071 |
anooga | -1.044 |
xus | -1.013 |
waters | -0.968 |
Token | he |
Token ID | 339 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ponds | +0.029 |
edin | +0.028 |
anooga | +0.027 |
xus | +0.026 |
bund | +0.025 |
Neg logit contributions | |
OW | -0.027 |
ORN | -0.026 |
therefore | -0.024 |
olute | -0.024 |
arget | -0.024 |
Token | their |
Token ID | 511 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
OW | +1.683 |
ORN | +1.593 |
therefore | +1.536 |
olute | +1.480 |
ONES | +1.471 |
Neg logit contributions | |
ponds | -1.562 |
edin | -1.520 |
anooga | -1.482 |
xus | -1.440 |
waters | -1.366 |
Token | car |
Token ID | 1097 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
OW | +2.236 |
ORN | +2.117 |
therefore | +2.048 |
olute | +1.970 |
ONES | +1.962 |
Neg logit contributions | |
ponds | -1.937 |
edin | -1.898 |
anooga | -1.849 |
xus | -1.795 |
waters | -1.697 |
Token | headlights |
Token ID | 46783 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
OW | +2.598 |
ORN | +2.470 |
therefore | +2.390 |
olute | +2.308 |
ONES | +2.297 |
Neg logit contributions | |
ponds | -2.013 |
edin | -1.957 |
anooga | -1.904 |
xus | -1.843 |
waters | -1.737 |
Token | off |
Token ID | 572 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ponds | +1.477 |
edin | +1.435 |
anooga | +1.374 |
xus | +1.330 |
waters | +1.287 |
Neg logit contributions | |
OW | -1.623 |
ORN | -1.555 |
therefore | -1.460 |
RIC | -1.446 |
ONES | -1.434 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ponds | +0.818 |
edin | +0.790 |
anooga | +0.765 |
xus | +0.746 |
waters | +0.719 |
Neg logit contributions | |
OW | -0.731 |
ORN | -0.697 |
therefore | -0.653 |
olute | -0.641 |
RIC | -0.638 |
Token | shooting |
Token ID | 4395 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
OW | +0.889 |
ORN | +0.846 |
therefore | +0.811 |
olute | +0.789 |
ONES | +0.784 |
Neg logit contributions | |
ponds | -0.732 |
edin | -0.709 |
anooga | -0.688 |
xus | -0.667 |
waters | -0.633 |
Token | you |
Token ID | 345 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
OW | +9.581 |
therefore | +9.026 |
ORN | +8.882 |
oneself | +8.539 |
arget | +8.406 |
Neg logit contributions | |
edin | -8.196 |
anooga | -8.178 |
xus | -7.917 |
ponds | -7.812 |
amia | -7.315 |
Token | if |
Token ID | 611 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
OW | +3.139 |
ORN | +2.925 |
therefore | +2.875 |
olute | +2.697 |
arget | +2.693 |
Neg logit contributions | |
ponds | -3.455 |
edin | -3.415 |
anooga | -3.356 |
xus | -3.265 |
waters | -3.086 |
Token | you |
Token ID | 345 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ponds | +0.486 |
edin | +0.472 |
anooga | +0.459 |
xus | +0.445 |
waters | +0.428 |
Neg logit contributions | |
OW | -0.452 |
ORN | -0.425 |
therefore | -0.403 |
olute | -0.396 |
ONES | -0.394 |
Token | flash |
Token ID | 7644 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ponds | +0.436 |
edin | +0.418 |
anooga | +0.393 |
xus | +0.385 |
bund | +0.365 |
Neg logit contributions | |
OW | -0.609 |
ORN | -0.594 |
therefore | -0.555 |
olute | -0.552 |
RIC | -0.551 |
Token | them |
Token ID | 606 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
OW | +1.285 |
ORN | +1.210 |
therefore | +1.159 |
olute | +1.118 |
ONES | +1.115 |
Neg logit contributions | |
ponds | -1.422 |
edin | -1.391 |
anooga | -1.352 |
xus | -1.309 |
waters | -1.262 |
Token | for |
Token ID | 329 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ponds | +0.651 |
edin | +0.633 |
anooga | +0.611 |
xus | +0.604 |
waters | +0.576 |
Neg logit contributions | |
OW | -0.581 |
ORN | -0.552 |
therefore | -0.516 |
arget | -0.508 |
ONES | -0.508 |
Token | killing |
Token ID | 5170 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ponds | +1.498 |
edin | +1.416 |
anooga | +1.382 |
xus | +1.353 |
bund | +1.306 |
Neg logit contributions | |
OW | -1.589 |
ORN | -1.502 |
therefore | -1.421 |
arget | -1.408 |
ONES | -1.406 |
Token | Emily |
Token ID | 17608 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
OW | +4.898 |
ORN | +4.565 |
therefore | +4.471 |
olute | +4.186 |
ONES | +4.166 |
Neg logit contributions | |
ponds | -5.728 |
edin | -5.673 |
anooga | -5.589 |
xus | -5.399 |
waters | -5.153 |
Token | Sinclair |
Token ID | 34927 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ponds | +0.658 |
edin | +0.642 |
anooga | +0.626 |
xus | +0.613 |
waters | +0.581 |
Neg logit contributions | |
OW | -0.593 |
ORN | -0.565 |
therefore | -0.532 |
arget | -0.520 |
olute | -0.520 |
Token | and |
Token ID | 290 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
OW | +1.927 |
ORN | +1.810 |
therefore | +1.737 |
olute | +1.661 |
ONES | +1.650 |
Neg logit contributions | |
ponds | -2.301 |
edin | -2.249 |
anooga | -2.200 |
xus | -2.143 |
waters | -2.046 |
Token | shooting |
Token ID | 4395 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
OW | +2.726 |
ORN | +2.579 |
therefore | +2.502 |
olute | +2.395 |
ONES | +2.380 |
Neg logit contributions | |
ponds | -2.518 |
edin | -2.458 |
anooga | -2.402 |
xus | -2.329 |
waters | -2.205 |
Token | Ann |
Token ID | 5506 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
OW | +8.549 |
therefore | +7.963 |
ORN | +7.950 |
oneself | +7.406 |
INC | +7.282 |
Neg logit contributions | |
edin | -8.890 |
anooga | -8.864 |
ponds | -8.797 |
xus | -8.534 |
perty | -8.048 |
Token | al |
Token ID | 282 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
OW | +2.144 |
ORN | +1.993 |
therefore | +1.910 |
olute | +1.817 |
arget | +1.802 |
Neg logit contributions | |
ponds | -3.155 |
edin | -3.084 |
anooga | -3.022 |
xus | -2.957 |
waters | -2.834 |
Token | ise |
Token ID | 786 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
OW | +1.537 |
therefore | +1.290 |
ORN | +1.271 |
olute | +1.185 |
arget | +1.173 |
Neg logit contributions | |
ponds | -5.253 |
edin | -5.146 |
anooga | -5.132 |
xus | -4.921 |
bund | -4.846 |
Token | — |
Token ID | 851 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
OW | +2.346 |
ORN | +2.204 |
therefore | +2.126 |
olute | +2.026 |
ONES | +2.014 |
Neg logit contributions | |
ponds | -2.652 |
edin | -2.596 |
anooga | -2.539 |
xus | -2.468 |
waters | -2.353 |
Token | crimes |
Token ID | 6741 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
ponds | +0.035 |
edin | +0.034 |
anooga | +0.033 |
xus | +0.032 |
bund | +0.031 |
Neg logit contributions | |
OW | -0.026 |
ORN | -0.025 |
olute | -0.023 |
therefore | -0.023 |
arget | -0.023 |
Token | by |
Token ID | 416 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
OW | +5.706 |
therefore | +5.344 |
ORN | +5.266 |
edit | +4.879 |
olute | +4.809 |
Neg logit contributions | |
ponds | -7.759 |
anooga | -7.689 |
edin | -7.661 |
xus | -7.404 |
waters | -6.978 |
Token | the |
Token ID | 262 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
OW | +1.056 |
ORN | +1.003 |
therefore | +0.957 |
olute | +0.932 |
arget | +0.927 |
Neg logit contributions | |
ponds | -0.963 |
edin | -0.924 |
anooga | -0.901 |
xus | -0.878 |
waters | -0.837 |
Token | protestors |
Token ID | 36915 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
OW | +0.353 |
ORN | +0.336 |
therefore | +0.320 |
olute | +0.312 |
arget | +0.311 |
Neg logit contributions | |
ponds | -0.317 |
edin | -0.303 |
anooga | -0.295 |
xus | -0.287 |
waters | -0.275 |
Token | and |
Token ID | 290 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ponds | +0.620 |
edin | +0.597 |
anooga | +0.581 |
xus | +0.567 |
waters | +0.550 |
Neg logit contributions | |
OW | -0.537 |
ORN | -0.511 |
therefore | -0.477 |
RIC | -0.468 |
olute | -0.468 |
Token | even |
Token ID | 772 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
OW | +2.236 |
ORN | +2.115 |
therefore | +2.042 |
olute | +1.960 |
ONES | +1.949 |
Neg logit contributions | |
ponds | -2.163 |
edin | -2.112 |
anooga | -2.061 |
xus | -2.002 |
waters | -1.900 |
Token | killing |
Token ID | 5170 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
OW | +2.728 |
ORN | +2.580 |
therefore | +2.493 |
olute | +2.390 |
ONES | +2.378 |
Neg logit contributions | |
ponds | -2.662 |
edin | -2.604 |
anooga | -2.543 |
xus | -2.469 |
waters | -2.343 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
OW | +8.498 |
therefore | +7.998 |
ORN | +7.869 |
oneself | +7.563 |
ONES | +7.392 |
Neg logit contributions | |
edin | -8.837 |
anooga | -8.681 |
ponds | -8.606 |
xus | -8.339 |
amia | -7.921 |
Token | person |
Token ID | 1048 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
OW | +4.843 |
ORN | +4.559 |
therefore | +4.473 |
olute | +4.236 |
ONES | +4.229 |
Neg logit contributions | |
ponds | -4.542 |
edin | -4.540 |
anooga | -4.426 |
xus | -4.281 |
waters | -4.038 |
Token | were |
Token ID | 547 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
OW | +1.658 |
ORN | +1.569 |
therefore | +1.490 |
olute | +1.438 |
ONES | +1.431 |
Neg logit contributions | |
ponds | -1.887 |
edin | -1.833 |
anooga | -1.793 |
xus | -1.749 |
waters | -1.672 |
Token | done |
Token ID | 1760 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
OW | +2.022 |
ORN | +1.904 |
therefore | +1.806 |
olute | +1.746 |
ONES | +1.736 |
Neg logit contributions | |
ponds | -2.425 |
edin | -2.356 |
anooga | -2.314 |
xus | -2.246 |
waters | -2.153 |
Token | in |
Token ID | 287 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ponds | +1.710 |
edin | +1.652 |
anooga | +1.591 |
xus | +1.563 |
bund | +1.488 |
Neg logit contributions | |
OW | -1.787 |
ORN | -1.717 |
RIC | -1.586 |
therefore | -1.581 |
olute | -1.580 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
OW | +1.149 |
ORN | +1.089 |
therefore | +1.051 |
olute | +1.014 |
arget | +1.009 |
Neg logit contributions | |
ponds | -0.996 |
edin | -0.969 |
anooga | -0.942 |
xus | -0.915 |
waters | -0.871 |
Token | ural |
Token ID | 1523 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
OW | +0.410 |
ORN | +0.391 |
therefore | +0.376 |
olute | +0.360 |
ONES | +0.360 |
Neg logit contributions | |
ponds | -0.375 |
edin | -0.368 |
anooga | -0.355 |
xus | -0.344 |
waters | -0.331 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
ponds | +3.404 |
edin | +3.261 |
anooga | +3.157 |
xus | +3.064 |
waters | +3.021 |
Neg logit contributions | |
OW | -3.757 |
ORN | -3.561 |
therefore | -3.426 |
ILE | -3.318 |
ONES | -3.310 |
Token | of |
Token ID | 286 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ponds | +2.241 |
edin | +2.186 |
anooga | +2.137 |
xus | +2.090 |
waters | +2.009 |
Neg logit contributions | |
OW | -2.080 |
ORN | -1.967 |
therefore | -1.890 |
olute | -1.828 |
ONES | -1.809 |
Token | a |
Token ID | 257 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ponds | +0.825 |
edin | +0.801 |
anooga | +0.778 |
xus | +0.756 |
waters | +0.731 |
Neg logit contributions | |
OW | -0.802 |
ORN | -0.756 |
therefore | -0.732 |
olute | -0.701 |
arget | -0.699 |
Token | slashing |
Token ID | 37714 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
OW | +0.094 |
ORN | +0.090 |
therefore | +0.087 |
olute | +0.084 |
arget | +0.083 |
Neg logit contributions | |
ponds | -0.080 |
edin | -0.078 |
anooga | -0.075 |
xus | -0.073 |
waters | -0.070 |
Token | knife |
Token ID | 9845 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
OW | +9.514 |
ORN | +9.010 |
therefore | +8.741 |
olute | +8.357 |
arget | +8.322 |
Neg logit contributions | |
ponds | -7.727 |
anooga | -7.585 |
edin | -7.499 |
xus | -7.406 |
amia | -6.772 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
OW | +5.915 |
ORN | +5.559 |
therefore | +5.391 |
arget | +5.116 |
ONES | +5.074 |
Neg logit contributions | |
ponds | -6.123 |
edin | -5.924 |
anooga | -5.888 |
xus | -5.729 |
amia | -5.360 |
Token | It |
Token ID | 632 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ponds | +1.409 |
edin | +1.393 |
anooga | +1.326 |
xus | +1.281 |
waters | +1.266 |
Neg logit contributions | |
OW | -1.362 |
ORN | -1.284 |
therefore | -1.239 |
olute | -1.216 |
arget | -1.199 |
Token | 's |
Token ID | 338 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
OW | +0.555 |
ORN | +0.525 |
therefore | +0.494 |
olute | +0.481 |
ONES | +0.481 |
Neg logit contributions | |
ponds | -0.612 |
edin | -0.599 |
anooga | -0.580 |
xus | -0.566 |
waters | -0.544 |
Token | anim |
Token ID | 2355 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ponds | +0.123 |
edin | +0.120 |
anooga | +0.117 |
xus | +0.113 |
waters | +0.109 |
Neg logit contributions | |
OW | -0.124 |
ORN | -0.118 |
therefore | -0.111 |
arget | -0.110 |
olute | -0.109 |
Token | be |
Token ID | 307 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
OW | +2.860 |
ORN | +2.717 |
therefore | +2.634 |
olute | +2.541 |
arget | +2.527 |
Neg logit contributions | |
ponds | -2.211 |
edin | -2.149 |
anooga | -2.095 |
xus | -2.026 |
waters | -1.909 |
Token | a |
Token ID | 257 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
OW | +1.018 |
ORN | +0.964 |
therefore | +0.912 |
ONES | +0.894 |
olute | +0.891 |
Neg logit contributions | |
ponds | -1.126 |
edin | -1.093 |
anooga | -1.065 |
xus | -1.032 |
bund | -1.005 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
OW | +0.886 |
ORN | +0.836 |
therefore | +0.804 |
olute | +0.775 |
ONES | +0.772 |
Neg logit contributions | |
ponds | -0.928 |
edin | -0.904 |
anooga | -0.881 |
xus | -0.856 |
waters | -0.820 |
Token | supporter |
Token ID | 15525 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
OW | +4.340 |
ORN | +4.050 |
therefore | +3.898 |
olute | +3.692 |
arget | +3.671 |
Neg logit contributions | |
ponds | -5.685 |
edin | -5.537 |
anooga | -5.449 |
xus | -5.298 |
waters | -5.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
OW | +4.274 |
ORN | +3.956 |
therefore | +3.897 |
olute | +3.657 |
edit | +3.629 |
Neg logit contributions | |
ponds | -5.427 |
edin | -5.342 |
anooga | -5.250 |
xus | -5.092 |
waters | -4.849 |
Token | picking |
Token ID | 10868 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
OW | +1.145 |
ORN | +1.082 |
therefore | +1.009 |
olute | +0.990 |
ONES | +0.985 |
Neg logit contributions | |
ponds | -1.436 |
edin | -1.400 |
anooga | -1.364 |
xus | -1.332 |
bund | -1.280 |
Token | her |
Token ID | 607 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
OW | +8.036 |
ORN | +7.556 |
therefore | +7.464 |
arget | +6.976 |
edit | +6.954 |
Neg logit contributions | |
edin | -9.206 |
ponds | -9.173 |
anooga | -9.038 |
xus | -8.751 |
waters | -8.287 |
Token | over |
Token ID | 625 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
OW | +5.178 |
ORN | +4.900 |
therefore | +4.780 |
olute | +4.529 |
arget | +4.522 |
Neg logit contributions | |
ponds | -5.133 |
edin | -5.062 |
anooga | -4.959 |
xus | -4.815 |
waters | -4.556 |
Token | Barack |
Token ID | 8732 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
OW | +0.654 |
ORN | +0.617 |
therefore | +0.585 |
olute | +0.571 |
ONES | +0.567 |
Neg logit contributions | |
ponds | -0.716 |
edin | -0.695 |
anooga | -0.675 |
xus | -0.656 |
bund | -0.632 |
Token | Obama |
Token ID | 2486 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
OW | +0.171 |
ORN | +0.162 |
therefore | +0.153 |
olute | +0.150 |
arget | +0.149 |
Neg logit contributions | |
ponds | -0.193 |
edin | -0.189 |
anooga | -0.185 |
xus | -0.179 |
waters | -0.171 |
Token | in |
Token ID | 287 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
OW | +0.077 |
ORN | +0.073 |
therefore | +0.069 |
olute | +0.067 |
ONES | +0.067 |
Neg logit contributions | |
ponds | -0.082 |
edin | -0.080 |
anooga | -0.078 |
xus | -0.077 |
bund | -0.073 |
Token | up |
Token ID | 510 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
OW | +0.073 |
ORN | +0.069 |
therefore | +0.065 |
olute | +0.064 |
arget | +0.063 |
Neg logit contributions | |
ponds | -0.081 |
edin | -0.079 |
anooga | -0.077 |
xus | -0.075 |
waters | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ponds | +0.885 |
edin | +0.873 |
anooga | +0.831 |
xus | +0.816 |
bund | +0.780 |
Neg logit contributions | |
OW | -0.889 |
ORN | -0.848 |
therefore | -0.797 |
olute | -0.785 |
arget | -0.782 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ponds | +0.168 |
edin | +0.166 |
anooga | +0.159 |
xus | +0.155 |
waters | +0.149 |
Neg logit contributions | |
OW | -0.153 |
ORN | -0.145 |
therefore | -0.138 |
olute | -0.135 |
arget | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ponds | +1.452 |
edin | +1.423 |
anooga | +1.379 |
xus | +1.350 |
waters | +1.299 |
Neg logit contributions | |
OW | -1.154 |
ORN | -1.088 |
therefore | -1.035 |
olute | -0.996 |
ONES | -0.989 |
Token | An |
Token ID | 2025 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
edin | +1.178 |
ponds | +1.162 |
anooga | +1.124 |
xus | +1.104 |
waters | +1.076 |
Neg logit contributions | |
OW | -0.918 |
ORN | -0.875 |
therefore | -0.869 |
olute | -0.831 |
ONES | -0.805 |
Token | NBC |
Token ID | 9716 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ponds | +1.040 |
edin | +1.027 |
anooga | +0.961 |
xus | +0.947 |
outsourcing | +0.929 |
Neg logit contributions | |
OW | -1.243 |
ORN | -1.206 |
therefore | -1.144 |
ONES | -1.125 |
RIC | -1.119 |
Token | News |
Token ID | 3000 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
OW | +9.374 |
therefore | +8.703 |
ORN | +8.698 |
ONES | +8.173 |
edit | +8.056 |
Neg logit contributions | |
ponds | -7.974 |
edin | -7.699 |
anooga | -7.597 |
xus | -7.160 |
perty | -6.916 |
Token | analysis |
Token ID | 3781 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
OW | +3.780 |
ORN | +3.540 |
therefore | +3.482 |
olute | +3.272 |
edit | +3.265 |
Neg logit contributions | |
ponds | -3.697 |
edin | -3.602 |
anooga | -3.566 |
xus | -3.425 |
waters | -3.247 |
Token | pointed |
Token ID | 6235 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ponds | +0.494 |
edin | +0.482 |
anooga | +0.467 |
xus | +0.457 |
waters | +0.439 |
Neg logit contributions | |
OW | -0.412 |
ORN | -0.392 |
therefore | -0.365 |
olute | -0.358 |
ONES | -0.356 |
Token | to |
Token ID | 284 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ponds | +0.180 |
edin | +0.177 |
anooga | +0.172 |
xus | +0.166 |
waters | +0.159 |
Neg logit contributions | |
OW | -0.184 |
ORN | -0.175 |
therefore | -0.166 |
olute | -0.162 |
ONES | -0.162 |
Token | five |
Token ID | 1936 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ponds | +0.148 |
edin | +0.144 |
anooga | +0.139 |
xus | +0.136 |
waters | +0.130 |
Neg logit contributions | |
OW | -0.152 |
ORN | -0.145 |
therefore | -0.138 |
olute | -0.134 |
ONES | -0.133 |
Token | - |
Token ID | 12 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
OW | +0.975 |
ORN | +0.927 |
therefore | +0.883 |
ONES | +0.862 |
olute | +0.856 |
Neg logit contributions | |
ponds | -0.955 |
edin | -0.930 |
anooga | -0.904 |
xus | -0.887 |
waters | -0.847 |
Token | cr |
Token ID | 6098 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
OW | +0.427 |
ORN | +0.407 |
therefore | +0.389 |
olute | +0.375 |
ONES | +0.375 |
Neg logit contributions | |
ponds | -0.452 |
edin | -0.447 |
anooga | -0.429 |
xus | -0.424 |
waters | -0.409 |
Token | ack |
Token ID | 441 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
OW | +1.089 |
ORN | +1.020 |
therefore | +0.976 |
olute | +0.931 |
ONES | +0.925 |
Neg logit contributions | |
ponds | -1.443 |
edin | -1.413 |
anooga | -1.382 |
xus | -1.349 |
waters | -1.292 |
Token | with |
Token ID | 351 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
OW | +1.089 |
ORN | +1.028 |
therefore | +0.983 |
olute | +0.948 |
ONES | +0.945 |
Neg logit contributions | |
ponds | -1.195 |
edin | -1.166 |
anooga | -1.137 |
xus | -1.112 |
waters | -1.059 |
Token | an |
Token ID | 281 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
OW | +0.780 |
ORN | +0.738 |
therefore | +0.709 |
olute | +0.685 |
ONES | +0.682 |
Neg logit contributions | |
ponds | -0.734 |
edin | -0.711 |
anooga | -0.691 |
xus | -0.675 |
waters | -0.641 |
Token | ax |
Token ID | 7877 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
OW | +0.588 |
ORN | +0.559 |
therefore | +0.534 |
ONES | +0.518 |
arget | +0.516 |
Neg logit contributions | |
ponds | -0.539 |
edin | -0.522 |
anooga | -0.503 |
xus | -0.495 |
outsourcing | -0.470 |
Token | : |
Token ID | 25 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
OW | +8.218 |
therefore | +7.569 |
ORN | +7.552 |
olute | +7.155 |
edit | +7.073 |
Neg logit contributions | |
ponds | -8.989 |
anooga | -8.568 |
edin | -8.530 |
xus | -8.046 |
waters | -7.834 |
Token | a |
Token ID | 257 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
OW | +0.740 |
ORN | +0.697 |
therefore | +0.665 |
olute | +0.643 |
ONES | +0.639 |
Neg logit contributions | |
ponds | -0.840 |
edin | -0.819 |
anooga | -0.797 |
xus | -0.779 |
waters | -0.742 |
Token | wide |
Token ID | 3094 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ponds | +0.154 |
edin | +0.149 |
anooga | +0.145 |
xus | +0.141 |
waters | +0.134 |
Neg logit contributions | |
OW | -0.186 |
ORN | -0.178 |
therefore | -0.171 |
ONES | -0.166 |
olute | -0.165 |
Token | - |
Token ID | 12 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
OW | +3.636 |
ORN | +3.427 |
therefore | +3.322 |
olute | +3.199 |
arget | +3.169 |
Neg logit contributions | |
ponds | -3.337 |
edin | -3.263 |
anooga | -3.198 |
xus | -3.099 |
waters | -2.929 |
Token | eyed |
Token ID | 18834 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
ponds | +0.164 |
edin | +0.161 |
anooga | +0.153 |
xus | +0.150 |
waters | +0.145 |
Neg logit contributions | |
OW | -0.184 |
ORN | -0.178 |
therefore | -0.170 |
ONES | -0.165 |
RIC | -0.164 |
Token | =" |
Token ID | 2625 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
OW | +0.312 |
ORN | +0.296 |
therefore | +0.283 |
ONES | +0.272 |
olute | +0.271 |
Neg logit contributions | |
ponds | -0.368 |
edin | -0.363 |
anooga | -0.352 |
xus | -0.341 |
bund | -0.330 |
Token | phone |
Token ID | 4862 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
OW | +2.575 |
ORN | +2.417 |
therefore | +2.320 |
olute | +2.220 |
ONES | +2.209 |
Neg logit contributions | |
ponds | -3.014 |
edin | -2.936 |
anooga | -2.877 |
xus | -2.805 |
waters | -2.671 |
Token | in |
Token ID | 287 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
OW | +1.913 |
ORN | +1.799 |
therefore | +1.724 |
olute | +1.651 |
arget | +1.642 |
Neg logit contributions | |
ponds | -2.256 |
edin | -2.206 |
anooga | -2.157 |
xus | -2.102 |
waters | -2.007 |
Token | phones |
Token ID | 9512 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
OW | +3.454 |
ORN | +3.270 |
therefore | +3.177 |
olute | +3.057 |
ONES | +3.037 |
Neg logit contributions | |
ponds | -3.070 |
edin | -2.980 |
anooga | -2.925 |
xus | -2.848 |
waters | -2.687 |
Token | "> |
Token ID | 5320 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
OW | +2.575 |
ORN | +2.435 |
therefore | +2.352 |
olute | +2.265 |
ONES | +2.249 |
Neg logit contributions | |
ponds | -2.408 |
edin | -2.347 |
anooga | -2.292 |
xus | -2.227 |
waters | -2.112 |
Token | {{ |
Token ID | 22935 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
OW | +3.836 |
ORN | +3.559 |
therefore | +3.402 |
olute | +3.261 |
edit | +3.246 |
Neg logit contributions | |
ponds | -5.698 |
edin | -5.527 |
anooga | -5.485 |
xus | -5.354 |
waters | -5.120 |
Token | phone |
Token ID | 3072 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
OW | +8.462 |
ORN | +7.946 |
therefore | +7.820 |
edit | +7.539 |
ONES | +7.483 |
Neg logit contributions | |
ponds | -8.384 |
anooga | -8.107 |
edin | -8.055 |
xus | -7.777 |
waters | -7.378 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
OW | +3.673 |
ORN | +3.424 |
therefore | +3.320 |
olute | +3.161 |
edit | +3.142 |
Neg logit contributions | |
ponds | -4.597 |
edin | -4.492 |
anooga | -4.404 |
xus | -4.295 |
waters | -4.099 |
Token | name |
Token ID | 3672 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
OW | +1.466 |
ORN | +1.378 |
therefore | +1.314 |
olute | +1.256 |
arget | +1.245 |
Neg logit contributions | |
ponds | -1.913 |
edin | -1.882 |
anooga | -1.833 |
xus | -1.791 |
waters | -1.718 |
Token | }} |
Token ID | 34949 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
OW | +2.662 |
ORN | +2.508 |
therefore | +2.417 |
olute | +2.319 |
arget | +2.304 |
Neg logit contributions | |
ponds | -2.782 |
edin | -2.713 |
anooga | -2.653 |
xus | -2.582 |
waters | -2.453 |
Token | < |
Token ID | 1279 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
OW | +4.347 |
ORN | +3.932 |
therefore | +3.871 |
olute | +3.544 |
arget | +3.521 |
Neg logit contributions | |
ponds | -9.855 |
anooga | -9.602 |
edin | -9.594 |
xus | -9.387 |
waters | -9.082 |
Token | Make |
Token ID | 6889 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
OW | +0.068 |
ORN | +0.065 |
therefore | +0.061 |
olute | +0.060 |
arget | +0.060 |
Neg logit contributions | |
ponds | -0.070 |
edin | -0.069 |
anooga | -0.066 |
xus | -0.065 |
waters | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
OW | +0.078 |
ORN | +0.074 |
therefore | +0.071 |
olute | +0.070 |
arget | +0.070 |
Neg logit contributions | |
ponds | -0.052 |
edin | -0.050 |
anooga | -0.048 |
xus | -0.047 |
bund | -0.044 |
Token | loop |
Token ID | 9052 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ponds | +1.388 |
edin | +1.328 |
anooga | +1.287 |
xus | +1.260 |
bund | +1.222 |
Neg logit contributions | |
OW | -1.576 |
ORN | -1.493 |
therefore | -1.417 |
arget | -1.392 |
olute | -1.388 |
Token | from |
Token ID | 422 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
OW | +0.683 |
ORN | +0.645 |
therefore | +0.615 |
olute | +0.598 |
arget | +0.597 |
Neg logit contributions | |
ponds | -0.688 |
edin | -0.673 |
anooga | -0.650 |
xus | -0.635 |
waters | -0.605 |
Token | some |
Token ID | 617 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ponds | +0.617 |
edin | +0.597 |
anooga | +0.582 |
xus | +0.568 |
bund | +0.541 |
Neg logit contributions | |
OW | -0.586 |
ORN | -0.550 |
therefore | -0.524 |
olute | -0.514 |
RIC | -0.510 |
Token | RG |
Token ID | 34359 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
ponds | +0.079 |
edin | +0.076 |
anooga | +0.074 |
xus | +0.072 |
waters | +0.069 |
Neg logit contributions | |
OW | -0.085 |
ORN | -0.080 |
therefore | -0.077 |
olute | -0.075 |
arget | -0.074 |
Token | 58 |
Token ID | 3365 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
OW | +9.217 |
ORN | +8.646 |
therefore | +8.356 |
INC | +8.015 |
RIC | +8.004 |
Neg logit contributions | |
edin | -7.769 |
ponds | -7.762 |
anooga | -7.626 |
xus | -7.307 |
perty | -6.987 |
Token | coax |
Token ID | 37700 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
OW | +0.227 |
ORN | +0.215 |
therefore | +0.206 |
olute | +0.200 |
ONES | +0.199 |
Neg logit contributions | |
ponds | -0.235 |
edin | -0.228 |
anooga | -0.221 |
xus | -0.218 |
waters | -0.205 |
Token | by |
Token ID | 416 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ponds | +1.101 |
edin | +1.084 |
anooga | +1.047 |
xus | +1.028 |
bund | +0.981 |
Neg logit contributions | |
OW | -0.984 |
ORN | -0.926 |
therefore | -0.874 |
arget | -0.862 |
ONES | -0.860 |
Token | stripping |
Token ID | 37727 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ponds | +3.070 |
edin | +2.909 |
anooga | +2.844 |
xus | +2.819 |
piping | +2.733 |
Neg logit contributions | |
OW | -3.965 |
ORN | -3.821 |
therefore | -3.603 |
arget | -3.586 |
olute | -3.583 |
Token | back |
Token ID | 736 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
OW | +4.138 |
ORN | +3.902 |
therefore | +3.788 |
olute | +3.563 |
edit | +3.547 |
Neg logit contributions | |
ponds | -4.505 |
edin | -4.435 |
anooga | -4.341 |
xus | -4.203 |
waters | -4.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ponds | +0.081 |
edin | +0.078 |
anooga | +0.076 |
xus | +0.074 |
bund | +0.070 |
Neg logit contributions | |
OW | -0.080 |
ORN | -0.076 |
therefore | -0.071 |
olute | -0.070 |
RIC | -0.070 |
Token | game |
Token ID | 983 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
OW | +0.771 |
ORN | +0.736 |
therefore | +0.704 |
olute | +0.682 |
arget | +0.680 |
Neg logit contributions | |
ponds | -0.636 |
edin | -0.615 |
anooga | -0.597 |
xus | -0.581 |
waters | -0.547 |
Token | asks |
Token ID | 7893 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ponds | +2.900 |
edin | +2.787 |
anooga | +2.712 |
xus | +2.604 |
bund | +2.533 |
Neg logit contributions | |
OW | -2.995 |
ORN | -2.916 |
ONES | -2.670 |
olute | -2.645 |
therefore | -2.635 |
Token | you |
Token ID | 345 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ponds | +2.525 |
edin | +2.418 |
anooga | +2.298 |
xus | +2.292 |
outsourcing | +2.202 |
Neg logit contributions | |
OW | -2.641 |
ORN | -2.547 |
ILE | -2.319 |
RIC | -2.316 |
ONES | -2.309 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ponds | +1.706 |
edin | +1.638 |
anooga | +1.594 |
xus | +1.556 |
bund | +1.464 |
Neg logit contributions | |
OW | -1.964 |
ORN | -1.907 |
therefore | -1.757 |
ONES | -1.743 |
olute | -1.739 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
OW | +0.559 |
ORN | +0.539 |
therefore | +0.505 |
olute | +0.498 |
ONES | +0.495 |
Neg logit contributions | |
ponds | -0.455 |
edin | -0.441 |
anooga | -0.422 |
xus | -0.412 |
bund | -0.390 |
Token | between |
Token ID | 1022 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
OW | +7.618 |
therefore | +7.143 |
ORN | +7.091 |
edit | +6.649 |
arget | +6.647 |
Neg logit contributions | |
edin | -8.944 |
ponds | -8.942 |
anooga | -8.796 |
xus | -8.463 |
amia | -8.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
OW | +0.111 |
ORN | +0.106 |
therefore | +0.100 |
olute | +0.098 |
RIC | +0.098 |
Neg logit contributions | |
ponds | -0.093 |
edin | -0.089 |
anooga | -0.086 |
xus | -0.084 |
outsourcing | -0.080 |
Token | right |
Token ID | 826 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
OW | +1.628 |
ORN | +1.552 |
therefore | +1.492 |
olute | +1.443 |
ONES | +1.439 |
Neg logit contributions | |
ponds | -1.305 |
edin | -1.263 |
anooga | -1.228 |
xus | -1.192 |
waters | -1.123 |
Token | thing |
Token ID | 1517 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ponds | +1.368 |
edin | +1.315 |
anooga | +1.287 |
xus | +1.240 |
outsourcing | +1.183 |
Neg logit contributions | |
OW | -1.538 |
ORN | -1.487 |
therefore | -1.390 |
ONES | -1.358 |
arget | -1.348 |
Token | and |
Token ID | 290 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
OW | +2.215 |
ORN | +2.099 |
therefore | +2.008 |
olute | +1.933 |
ONES | +1.930 |
Neg logit contributions | |
ponds | -2.260 |
edin | -2.207 |
anooga | -2.151 |
xus | -2.092 |
waters | -1.988 |
Token | , |
Token ID | 11 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
OW | +1.406 |
ORN | +1.323 |
therefore | +1.262 |
olute | +1.213 |
ONES | +1.206 |
Neg logit contributions | |
ponds | -1.694 |
edin | -1.653 |
anooga | -1.614 |
xus | -1.574 |
waters | -1.506 |
Token | making |
Token ID | 1642 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ponds | +1.527 |
edin | +1.442 |
anooga | +1.406 |
xus | +1.360 |
outsourcing | +1.334 |
Neg logit contributions | |
OW | -1.568 |
ORN | -1.489 |
olute | -1.392 |
arget | -1.390 |
therefore | -1.390 |
Token | positive |
Token ID | 3967 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
OW | +1.788 |
ORN | +1.696 |
therefore | +1.627 |
olute | +1.576 |
arget | +1.576 |
Neg logit contributions | |
ponds | -1.570 |
edin | -1.507 |
anooga | -1.466 |
xus | -1.427 |
waters | -1.350 |
Token | choices |
Token ID | 7747 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ponds | +1.490 |
edin | +1.398 |
anooga | +1.364 |
xus | +1.312 |
bund | +1.261 |
Neg logit contributions | |
OW | -1.796 |
ORN | -1.714 |
therefore | -1.615 |
arget | -1.600 |
ONES | -1.588 |
Token | about |
Token ID | 546 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
OW | +2.324 |
ORN | +2.180 |
therefore | +2.102 |
olute | +2.006 |
arget | +1.991 |
Neg logit contributions | |
ponds | -2.760 |
edin | -2.698 |
anooga | -2.640 |
xus | -2.576 |
waters | -2.459 |
Token | picking |
Token ID | 10868 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
OW | +2.005 |
ORN | +1.901 |
therefore | +1.819 |
olute | +1.762 |
arget | +1.754 |
Neg logit contributions | |
ponds | -1.899 |
edin | -1.832 |
anooga | -1.782 |
xus | -1.735 |
waters | -1.652 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
OW | +8.017 |
ORN | +7.623 |
therefore | +7.405 |
ONES | +6.973 |
arget | +6.906 |
Neg logit contributions | |
edin | -8.661 |
ponds | -8.480 |
anooga | -8.408 |
xus | -8.221 |
waters | -7.739 |
Token | and |
Token ID | 290 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
OW | +2.529 |
ORN | +2.378 |
therefore | +2.275 |
olute | +2.181 |
ONES | +2.168 |
Neg logit contributions | |
ponds | -3.044 |
edin | -2.974 |
anooga | -2.907 |
xus | -2.834 |
waters | -2.708 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
OW | +0.194 |
ORN | +0.186 |
therefore | +0.173 |
olute | +0.173 |
arget | +0.172 |
Neg logit contributions | |
ponds | -0.171 |
edin | -0.163 |
anooga | -0.158 |
xus | -0.152 |
bund | -0.148 |
Token | importance |
Token ID | 6817 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
OW | +1.330 |
ORN | +1.260 |
therefore | +1.209 |
arget | +1.178 |
olute | +1.176 |
Neg logit contributions | |
ponds | -1.145 |
edin | -1.103 |
anooga | -1.072 |
xus | -1.040 |
waters | -0.988 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
OW | +0.660 |
ORN | +0.620 |
therefore | +0.592 |
olute | +0.569 |
ONES | +0.565 |
Neg logit contributions | |
ponds | -0.805 |
edin | -0.785 |
anooga | -0.769 |
xus | -0.750 |
waters | -0.717 |
Token | of |
Token ID | 286 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ponds | +2.277 |
edin | +2.207 |
anooga | +2.160 |
xus | +2.108 |
waters | +2.027 |
Neg logit contributions | |
OW | -2.089 |
ORN | -1.981 |
therefore | -1.856 |
ONES | -1.830 |
olute | -1.818 |
Token | women |
Token ID | 1466 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
OW | +0.908 |
ORN | +0.854 |
therefore | +0.812 |
olute | +0.784 |
arget | +0.780 |
Neg logit contributions | |
ponds | -1.116 |
edin | -1.086 |
anooga | -1.057 |
xus | -1.036 |
waters | -0.991 |
Token | suffering |
Token ID | 7195 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
OW | +3.413 |
ORN | +3.201 |
therefore | +3.123 |
olute | +2.947 |
ONES | +2.925 |
Neg logit contributions | |
ponds | -3.914 |
edin | -3.829 |
anooga | -3.771 |
xus | -3.641 |
waters | -3.475 |
Token | under |
Token ID | 739 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
OW | +0.864 |
ORN | +0.817 |
therefore | +0.786 |
olute | +0.758 |
ONES | +0.753 |
Neg logit contributions | |
ponds | -0.841 |
edin | -0.820 |
anooga | -0.800 |
xus | -0.778 |
waters | -0.739 |
Token | a |
Token ID | 257 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
OW | +0.787 |
ORN | +0.746 |
therefore | +0.718 |
olute | +0.693 |
ONES | +0.692 |
Neg logit contributions | |
ponds | -0.695 |
edin | -0.677 |
anooga | -0.655 |
xus | -0.641 |
waters | -0.608 |
Token | brutally |
Token ID | 30040 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
OW | +0.944 |
ORN | +0.894 |
therefore | +0.864 |
olute | +0.832 |
arget | +0.827 |
Neg logit contributions | |
ponds | -0.841 |
edin | -0.818 |
anooga | -0.798 |
xus | -0.774 |
waters | -0.733 |
Token | misogyn |
Token ID | 22795 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
OW | +7.519 |
therefore | +7.014 |
ORN | +6.802 |
olute | +6.492 |
arget | +6.401 |
Neg logit contributions | |
ponds | -9.116 |
anooga | -9.097 |
edin | -8.909 |
xus | -8.588 |
amia | -8.243 |
Token | istic |
Token ID | 2569 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
OW | +2.392 |
ORN | +2.262 |
therefore | +2.172 |
olute | +2.080 |
ONES | +2.076 |
Neg logit contributions | |
ponds | -2.555 |
edin | -2.499 |
anooga | -2.438 |
xus | -2.374 |
waters | -2.261 |
Token | cler |
Token ID | 13451 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
OW | +0.762 |
ORN | +0.727 |
therefore | +0.703 |
olute | +0.681 |
ONES | +0.678 |
Neg logit contributions | |
ponds | -0.531 |
edin | -0.515 |
anooga | -0.498 |
xus | -0.482 |
waters | -0.454 |
Token | ical |
Token ID | 605 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
OW | +2.843 |
ORN | +2.568 |
therefore | +2.460 |
olute | +2.327 |
arget | +2.295 |
Neg logit contributions | |
ponds | -5.884 |
edin | -5.733 |
anooga | -5.647 |
xus | -5.511 |
waters | -5.332 |
Token | culture |
Token ID | 3968 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
OW | +2.054 |
ORN | +1.963 |
therefore | +1.906 |
olute | +1.847 |
ONES | +1.839 |
Neg logit contributions | |
ponds | -1.234 |
edin | -1.194 |
anooga | -1.156 |
xus | -1.112 |
waters | -1.037 |
Token | becomes |
Token ID | 4329 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ponds | +3.405 |
edin | +3.105 |
xus | +2.843 |
waters | +2.842 |
bund | +2.817 |
Neg logit contributions | |
OW | -5.582 |
ORN | -5.542 |
ILE | -5.105 |
ONES | -5.098 |
arget | -5.082 |
Token | older |
Token ID | 4697 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ponds | +1.502 |
edin | +1.442 |
anooga | +1.392 |
xus | +1.350 |
bund | +1.307 |
Neg logit contributions | |
OW | -1.923 |
ORN | -1.835 |
ILE | -1.733 |
therefore | -1.729 |
ONES | -1.726 |
Token | and |
Token ID | 290 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
ponds | +0.179 |
edin | +0.173 |
anooga | +0.168 |
xus | +0.166 |
bund | +0.158 |
Neg logit contributions | |
OW | -0.165 |
ORN | -0.157 |
ONES | -0.145 |
olute | -0.144 |
therefore | -0.144 |
Token | more |
Token ID | 517 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
ponds | +0.301 |
edin | +0.291 |
anooga | +0.277 |
xus | +0.277 |
bund | +0.264 |
Neg logit contributions | |
OW | -0.333 |
ORN | -0.318 |
olute | -0.294 |
ONES | -0.294 |
arget | -0.292 |
Token | ethn |
Token ID | 33961 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
OW | +2.377 |
ORN | +2.252 |
therefore | +2.158 |
olute | +2.087 |
ONES | +2.081 |
Neg logit contributions | |
ponds | -2.237 |
edin | -2.180 |
anooga | -2.120 |
xus | -2.061 |
waters | -1.958 |
Token | ically |
Token ID | 1146 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
OW | +3.568 |
ORN | +3.185 |
therefore | +2.986 |
olute | +2.842 |
arget | +2.787 |
Neg logit contributions | |
ponds | -9.012 |
edin | -8.738 |
anooga | -8.623 |
xus | -8.478 |
bund | -8.217 |
Token | diverse |
Token ID | 10084 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
OW | +6.435 |
therefore | +6.140 |
ORN | +5.962 |
olute | +5.500 |
IND | +5.454 |
Neg logit contributions | |
anooga | -9.986 |
ponds | -9.981 |
edin | -9.940 |
xus | -9.628 |
perty | -9.393 |
Token | , |
Token ID | 11 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ponds | +0.764 |
edin | +0.733 |
anooga | +0.711 |
xus | +0.695 |
bund | +0.666 |
Neg logit contributions | |
OW | -0.771 |
ORN | -0.728 |
ONES | -0.678 |
olute | -0.678 |
therefore | -0.675 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
OW | +1.283 |
ORN | +1.217 |
therefore | +1.142 |
olute | +1.129 |
ONES | +1.120 |
Neg logit contributions | |
ponds | -1.216 |
edin | -1.180 |
anooga | -1.142 |
xus | -1.119 |
waters | -1.061 |
Token | additional |
Token ID | 3224 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
OW | +0.936 |
ORN | +0.891 |
therefore | +0.856 |
olute | +0.834 |
ONES | +0.829 |
Neg logit contributions | |
ponds | -0.727 |
edin | -0.701 |
anooga | -0.679 |
xus | -0.663 |
waters | -0.625 |
Token | challenges |
Token ID | 6459 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ponds | +0.063 |
edin | +0.060 |
anooga | +0.059 |
xus | +0.057 |
waters | +0.054 |
Neg logit contributions | |
OW | -0.080 |
ORN | -0.076 |
therefore | -0.074 |
olute | -0.072 |
ONES | -0.071 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
OW | +3.161 |
ORN | +2.900 |
therefore | +2.729 |
olute | +2.562 |
arget | +2.550 |
Neg logit contributions | |
ponds | -6.365 |
edin | -6.206 |
anooga | -6.128 |
xus | -5.971 |
waters | -5.752 |
Token | - |
Token ID | 12 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
OW | +2.557 |
ORN | +2.410 |
therefore | +2.316 |
olute | +2.222 |
ONES | +2.209 |
Neg logit contributions | |
ponds | -2.792 |
edin | -2.726 |
anooga | -2.663 |
xus | -2.593 |
waters | -2.471 |
Token | ethyl |
Token ID | 21610 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
OW | +3.038 |
ORN | +2.869 |
therefore | +2.760 |
olute | +2.647 |
ONES | +2.634 |
Neg logit contributions | |
ponds | -3.180 |
edin | -3.109 |
anooga | -3.027 |
xus | -2.952 |
waters | -2.807 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ponds | +1.485 |
edin | +1.480 |
anooga | +1.423 |
xus | +1.388 |
waters | +1.336 |
Neg logit contributions | |
OW | -1.345 |
ORN | -1.260 |
therefore | -1.207 |
ONES | -1.156 |
olute | -1.155 |
Token | N |
Token ID | 45 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
OW | +2.587 |
ORN | +2.363 |
therefore | +2.216 |
olute | +2.079 |
arget | +2.063 |
Neg logit contributions | |
ponds | -5.496 |
edin | -5.372 |
anooga | -5.300 |
xus | -5.174 |
waters | -4.993 |
Token | -( |
Token ID | 30420 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
OW | +1.975 |
ORN | +1.865 |
therefore | +1.797 |
olute | +1.724 |
ONES | +1.715 |
Neg logit contributions | |
ponds | -2.030 |
edin | -1.983 |
anooga | -1.934 |
xus | -1.887 |
waters | -1.792 |
Token | t |
Token ID | 83 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
OW | +6.273 |
ORN | +5.611 |
therefore | +5.337 |
edit | +5.274 |
arget | +5.125 |
Neg logit contributions | |
ponds | -10.467 |
anooga | -10.139 |
edin | -10.006 |
xus | -9.737 |
outsourcing | -9.448 |
Token | et |
Token ID | 316 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
OW | +3.122 |
ORN | +2.921 |
therefore | +2.793 |
olute | +2.662 |
ONES | +2.646 |
Neg logit contributions | |
ponds | -4.203 |
edin | -4.113 |
anooga | -4.026 |
xus | -3.931 |
waters | -3.763 |
Token | rah |
Token ID | 11392 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
ponds | +1.012 |
edin | +1.001 |
anooga | +0.972 |
xus | +0.951 |
waters | +0.918 |
Neg logit contributions | |
OW | -0.773 |
ORN | -0.730 |
therefore | -0.687 |
ILE | -0.657 |
olute | -0.654 |
Token | yd |
Token ID | 5173 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
OW | +0.159 |
ORN | +0.150 |
therefore | +0.144 |
RIC | +0.137 |
ONES | +0.137 |
Neg logit contributions | |
ponds | -0.202 |
edin | -0.201 |
anooga | -0.193 |
xus | -0.191 |
waters | -0.181 |
Token | ro |
Token ID | 305 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ponds | +0.050 |
edin | +0.049 |
anooga | +0.047 |
xus | +0.046 |
waters | +0.044 |
Neg logit contributions | |
OW | -0.057 |
ORN | -0.055 |
therefore | -0.053 |
ONES | -0.051 |
olute | -0.050 |
Token | : |
Token ID | 25 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
ponds | +1.355 |
edin | +1.315 |
anooga | +1.269 |
xus | +1.247 |
bund | +1.192 |
Neg logit contributions | |
OW | -1.332 |
ORN | -1.279 |
therefore | -1.182 |
olute | -1.173 |
ONES | -1.166 |
Token |
|
Token ID | 198 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
OW | +1.647 |
ORN | +1.560 |
therefore | +1.484 |
olute | +1.434 |
arget | +1.426 |
Neg logit contributions | |
ponds | -1.847 |
edin | -1.796 |
anooga | -1.743 |
xus | -1.709 |
waters | -1.623 |
Token |
|
Token ID | 198 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
OW | +1.745 |
ORN | +1.566 |
therefore | +1.561 |
edit | +1.463 |
arget | +1.434 |
Neg logit contributions | |
ponds | -2.675 |
anooga | -2.643 |
edin | -2.603 |
xus | -2.545 |
perty | -2.459 |
Token | Own |
Token ID | 23858 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
OW | +1.650 |
ORN | +1.560 |
therefore | +1.507 |
olute | +1.433 |
ONES | +1.423 |
Neg logit contributions | |
ponds | -2.067 |
edin | -2.031 |
anooga | -1.981 |
xus | -1.941 |
waters | -1.856 |
Token | ed |
Token ID | 276 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
OW | +1.807 |
ORN | +1.731 |
therefore | +1.654 |
ONES | +1.599 |
olute | +1.595 |
Neg logit contributions | |
ponds | -1.641 |
edin | -1.599 |
anooga | -1.538 |
xus | -1.501 |
waters | -1.429 |
Token | < |
Token ID | 27 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
OW | +1.968 |
ORN | +1.864 |
therefore | +1.779 |
olute | +1.711 |
ONES | +1.702 |
Neg logit contributions | |
ponds | -2.236 |
edin | -2.175 |
anooga | -2.117 |
xus | -2.072 |
waters | -1.974 |
Token | T |
Token ID | 51 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
OW | +7.695 |
ORN | +7.023 |
therefore | +6.645 |
edit | +6.419 |
arget | +6.395 |
Neg logit contributions | |
ponds | -9.083 |
edin | -8.957 |
anooga | -8.929 |
xus | -8.478 |
waters | -8.139 |
Token | > |
Token ID | 29 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
OW | +3.364 |
ORN | +3.136 |
therefore | +2.991 |
olute | +2.845 |
ONES | +2.828 |
Neg logit contributions | |
ponds | -4.789 |
edin | -4.685 |
anooga | -4.595 |
xus | -4.487 |
waters | -4.301 |
Token | , |
Token ID | 837 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
OW | +5.818 |
ORN | +5.345 |
therefore | +5.237 |
olute | +4.970 |
arget | +4.915 |
Neg logit contributions | |
ponds | -7.009 |
edin | -6.906 |
anooga | -6.832 |
xus | -6.603 |
waters | -6.338 |
Token | akin |
Token ID | 22107 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
OW | +2.284 |
ORN | +2.158 |
therefore | +2.054 |
olute | +1.985 |
ONES | +1.976 |
Neg logit contributions | |
ponds | -2.534 |
edin | -2.468 |
anooga | -2.401 |
xus | -2.349 |
waters | -2.233 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
OW | +0.566 |
ORN | +0.538 |
therefore | +0.516 |
olute | +0.498 |
ONES | +0.498 |
Neg logit contributions | |
ponds | -0.507 |
edin | -0.496 |
anooga | -0.481 |
xus | -0.468 |
waters | -0.442 |
Token | professionally |
Token ID | 28049 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
OW | +0.308 |
ORN | +0.294 |
therefore | +0.279 |
olute | +0.273 |
arget | +0.273 |
Neg logit contributions | |
ponds | -0.269 |
edin | -0.259 |
anooga | -0.250 |
xus | -0.244 |
bund | -0.233 |
Token | packaged |
Token ID | 25555 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
OW | +2.354 |
ORN | +2.229 |
therefore | +2.145 |
olute | +2.068 |
ONES | +2.058 |
Neg logit contributions | |
ponds | -2.204 |
edin | -2.145 |
anooga | -2.091 |
xus | -2.032 |
waters | -1.929 |
Token | — |
Token ID | 851 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ponds | +5.870 |
edin | +5.414 |
piping | +5.193 |
bund | +5.112 |
mand | +5.108 |
Neg logit contributions | |
OW | -6.063 |
ORN | -5.802 |
ONES | -5.426 |
olute | -5.402 |
arget | -5.354 |
Token | little |
Token ID | 1310 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
ponds | +1.167 |
edin | +1.120 |
anooga | +1.084 |
xus | +1.057 |
bund | +1.022 |
Neg logit contributions | |
OW | -1.206 |
ORN | -1.140 |
therefore | -1.071 |
olute | -1.066 |
ONES | -1.061 |
Token | ch |
Token ID | 442 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ponds | +3.132 |
edin | +2.934 |
anooga | +2.766 |
xus | +2.731 |
bund | +2.678 |
Neg logit contributions | |
OW | -4.151 |
ORN | -4.007 |
therefore | -3.738 |
olute | -3.719 |
arget | -3.700 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ponds | +1.433 |
edin | +1.400 |
anooga | +1.349 |
xus | +1.300 |
waters | +1.254 |
Neg logit contributions | |
OW | -1.607 |
ORN | -1.580 |
therefore | -1.488 |
ONES | -1.431 |
RIC | -1.426 |
Token | ates |
Token ID | 689 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
edin | +5.279 |
ponds | +5.097 |
xus | +4.628 |
anooga | +4.608 |
amia | +4.583 |
Neg logit contributions | |
ORN | -6.478 |
OW | -6.451 |
therefore | -5.910 |
RIC | -5.866 |
ILE | -5.829 |
Token | , |
Token ID | 11 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ponds | +3.442 |
edin | +3.255 |
anooga | +3.109 |
xus | +3.059 |
piping | +3.018 |
Neg logit contributions | |
OW | -3.433 |
ORN | -3.296 |
ONES | -3.067 |
arget | -3.025 |
RIC | -3.020 |
Token | little |
Token ID | 1310 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ponds | +2.648 |
edin | +2.502 |
anooga | +2.388 |
xus | +2.332 |
bund | +2.292 |
Neg logit contributions | |
OW | -3.240 |
ORN | -3.082 |
olute | -2.878 |
therefore | -2.875 |
ONES | -2.872 |
Token | mint |
Token ID | 21043 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ponds | +3.960 |
edin | +3.681 |
anooga | +3.425 |
bund | +3.406 |
piping | +3.396 |
Neg logit contributions | |
OW | -5.500 |
ORN | -5.307 |
therefore | -4.950 |
olute | -4.940 |
ILE | -4.922 |
Token | s |
Token ID | 82 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
OW | +0.433 |
ORN | +0.405 |
therefore | +0.382 |
olute | +0.366 |
ONES | +0.365 |
Neg logit contributions | |
ponds | -0.606 |
edin | -0.590 |
anooga | -0.573 |
xus | -0.562 |
waters | -0.544 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
OW | +1.419 |
ORN | +1.331 |
therefore | +1.280 |
olute | +1.221 |
ONES | +1.213 |
Neg logit contributions | |
ponds | -1.737 |
edin | -1.700 |
anooga | -1.664 |
xus | -1.621 |
waters | -1.548 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ponds | +1.233 |
edin | +1.217 |
anooga | +1.153 |
xus | +1.113 |
waters | +1.092 |
Neg logit contributions | |
OW | -1.167 |
ORN | -1.112 |
therefore | -1.048 |
olute | -1.033 |
arget | -1.027 |
Token |
|
Token ID | 198 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ponds | +1.637 |
edin | +1.605 |
anooga | +1.554 |
xus | +1.520 |
waters | +1.465 |
Neg logit contributions | |
OW | -1.313 |
ORN | -1.241 |
therefore | -1.177 |
olute | -1.135 |
ONES | -1.127 |
Token | Scroll |
Token ID | 29261 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
edin | +1.393 |
ponds | +1.376 |
anooga | +1.337 |
xus | +1.292 |
waters | +1.266 |
Neg logit contributions | |
OW | -1.076 |
ORN | -1.024 |
therefore | -1.012 |
olute | -0.966 |
ONES | -0.939 |
Token | to |
Token ID | 284 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ponds | +2.904 |
edin | +2.866 |
anooga | +2.704 |
xus | +2.566 |
waters | +2.516 |
Neg logit contributions | |
OW | -4.094 |
ORN | -3.968 |
therefore | -3.725 |
ONES | -3.711 |
arget | -3.701 |
Token | continue |
Token ID | 2555 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ponds | +2.740 |
edin | +2.667 |
xus | +2.512 |
anooga | +2.488 |
waters | +2.360 |
Neg logit contributions | |
OW | -2.920 |
ORN | -2.821 |
therefore | -2.630 |
olute | -2.579 |
RIC | -2.573 |
Token | with |
Token ID | 351 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ponds | +4.629 |
edin | +4.551 |
anooga | +4.256 |
xus | +4.168 |
weaving | +4.076 |
Neg logit contributions | |
OW | -5.568 |
ORN | -5.356 |
therefore | -5.070 |
RIC | -5.061 |
ONES | -4.991 |
Token | content |
Token ID | 2695 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ponds | +1.323 |
edin | +1.275 |
anooga | +1.227 |
xus | +1.194 |
waters | +1.143 |
Neg logit contributions | |
OW | -1.345 |
ORN | -1.288 |
therefore | -1.219 |
olute | -1.185 |
ONES | -1.180 |
Token | Ad |
Token ID | 1215 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ponds | +4.809 |
edin | +4.771 |
anooga | +4.496 |
xus | +4.382 |
outsourcing | +4.219 |
Neg logit contributions | |
OW | -4.456 |
ORN | -4.300 |
therefore | -4.030 |
ONES | -3.944 |
olute | -3.935 |
Token |
|
Token ID | 198 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ponds | +4.715 |
edin | +4.698 |
anooga | +4.486 |
xus | +4.287 |
bund | +4.183 |
Neg logit contributions | |
OW | -4.462 |
ORN | -4.287 |
therefore | -4.070 |
ONES | -4.027 |
RIC | -3.961 |
Token |
|
Token ID | 198 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ponds | +1.890 |
edin | +1.855 |
anooga | +1.787 |
xus | +1.748 |
waters | +1.690 |
Neg logit contributions | |
OW | -1.538 |
ORN | -1.456 |
therefore | -1.381 |
olute | -1.334 |
ONES | -1.325 |
Token | 's |
Token ID | 338 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
OW | +1.638 |
ORN | +1.542 |
therefore | +1.478 |
olute | +1.417 |
ONES | +1.408 |
Neg logit contributions | |
ponds | -1.894 |
edin | -1.850 |
anooga | -1.807 |
xus | -1.762 |
waters | -1.681 |
Token | response |
Token ID | 2882 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ponds | +0.736 |
edin | +0.704 |
anooga | +0.676 |
xus | +0.664 |
outsourcing | +0.632 |
Neg logit contributions | |
OW | -0.917 |
ORN | -0.877 |
therefore | -0.834 |
arget | -0.818 |
olute | -0.814 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ponds | +2.674 |
edin | +2.583 |
anooga | +2.466 |
xus | +2.426 |
outsourcing | +2.338 |
Neg logit contributions | |
OW | -2.652 |
ORN | -2.561 |
arget | -2.357 |
ONES | -2.348 |
therefore | -2.338 |
Token | The |
Token ID | 383 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ponds | +1.635 |
edin | +1.631 |
anooga | +1.538 |
xus | +1.485 |
waters | +1.444 |
Neg logit contributions | |
OW | -1.657 |
ORN | -1.587 |
therefore | -1.494 |
olute | -1.483 |
arget | -1.467 |
Token | words |
Token ID | 2456 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
ponds | +0.854 |
edin | +0.827 |
anooga | +0.798 |
xus | +0.772 |
bund | +0.743 |
Neg logit contributions | |
OW | -0.932 |
ORN | -0.893 |
therefore | -0.845 |
arget | -0.828 |
olute | -0.826 |
Token | belonged |
Token ID | 19611 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ponds | +0.230 |
edin | +0.224 |
anooga | +0.217 |
xus | +0.211 |
waters | +0.202 |
Neg logit contributions | |
OW | -0.225 |
ORN | -0.215 |
therefore | -0.203 |
olute | -0.197 |
ONES | -0.197 |
Token | to |
Token ID | 284 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ponds | +4.461 |
edin | +4.390 |
anooga | +4.173 |
xus | +4.046 |
waters | +3.916 |
Neg logit contributions | |
OW | -5.640 |
ORN | -5.422 |
ONES | -5.051 |
olute | -5.039 |
ILE | -5.022 |
Token | Ferry |
Token ID | 42609 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
ponds | +0.098 |
edin | +0.095 |
anooga | +0.092 |
xus | +0.089 |
waters | +0.086 |
Neg logit contributions | |
OW | -0.083 |
ORN | -0.079 |
therefore | -0.073 |
olute | -0.072 |
ILE | -0.071 |
Token | because |
Token ID | 780 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
OW | +0.027 |
ORN | +0.025 |
therefore | +0.024 |
arget | +0.023 |
olute | +0.023 |
Neg logit contributions | |
ponds | -0.034 |
edin | -0.033 |
anooga | -0.032 |
xus | -0.032 |
waters | -0.030 |
Token | no |
Token ID | 645 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ponds | +2.425 |
edin | +2.336 |
anooga | +2.244 |
xus | +2.184 |
bund | +2.112 |
Neg logit contributions | |
OW | -2.561 |
ORN | -2.468 |
olute | -2.280 |
therefore | -2.277 |
arget | -2.270 |
Token | one |
Token ID | 530 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ponds | +0.106 |
edin | +0.103 |
anooga | +0.100 |
xus | +0.099 |
outsourcing | +0.094 |
Neg logit contributions | |
OW | -0.081 |
ORN | -0.077 |
therefore | -0.072 |
arget | -0.070 |
olute | -0.070 |
Token | home |
Token ID | 1363 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ponds | +1.655 |
edin | +1.609 |
anooga | +1.520 |
xus | +1.484 |
bund | +1.428 |
Neg logit contributions | |
OW | -1.766 |
ORN | -1.684 |
therefore | -1.563 |
ONES | -1.556 |
RIC | -1.555 |
Token | from |
Token ID | 422 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ponds | +1.818 |
edin | +1.760 |
anooga | +1.676 |
xus | +1.652 |
waters | +1.594 |
Neg logit contributions | |
OW | -1.727 |
ORN | -1.666 |
RIC | -1.529 |
arget | -1.517 |
therefore | -1.515 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ponds | +0.712 |
edin | +0.690 |
anooga | +0.658 |
xus | +0.648 |
outsourcing | +0.612 |
Neg logit contributions | |
OW | -0.832 |
ORN | -0.792 |
therefore | -0.755 |
olute | -0.737 |
ONES | -0.735 |
Token | World |
Token ID | 2159 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ponds | +1.089 |
edin | +1.041 |
xus | +0.982 |
anooga | +0.980 |
outsourcing | +0.923 |
Neg logit contributions | |
OW | -1.397 |
ORN | -1.330 |
therefore | -1.288 |
arget | -1.261 |
olute | -1.255 |
Token | Cup |
Token ID | 5454 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
OW | +2.694 |
ORN | +2.531 |
therefore | +2.448 |
olute | +2.348 |
ONES | +2.326 |
Neg logit contributions | |
ponds | -2.758 |
edin | -2.690 |
anooga | -2.631 |
xus | -2.559 |
waters | -2.429 |
Token | due |
Token ID | 2233 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
OW | +2.471 |
ORN | +2.307 |
therefore | +2.242 |
olute | +2.129 |
ONES | +2.111 |
Neg logit contributions | |
ponds | -2.886 |
edin | -2.827 |
anooga | -2.767 |
xus | -2.694 |
waters | -2.562 |
Token | to |
Token ID | 284 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
edin | +4.467 |
ponds | +4.465 |
anooga | +4.060 |
xus | +3.977 |
waters | +3.865 |
Neg logit contributions | |
OW | -5.999 |
ORN | -5.870 |
ONES | -5.508 |
olute | -5.460 |
arget | -5.442 |
Token | an |
Token ID | 281 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
ponds | +1.024 |
edin | +0.990 |
anooga | +0.941 |
xus | +0.934 |
outsourcing | +0.898 |
Neg logit contributions | |
OW | -1.048 |
ORN | -0.997 |
therefore | -0.938 |
olute | -0.922 |
ONES | -0.919 |
Token | omission |
Token ID | 35725 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ponds | +0.150 |
edin | +0.147 |
anooga | +0.140 |
xus | +0.138 |
outsourcing | +0.132 |
Neg logit contributions | |
OW | -0.154 |
ORN | -0.145 |
therefore | -0.138 |
ONES | -0.135 |
arget | -0.135 |
Token | from |
Token ID | 422 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
OW | +2.262 |
ORN | +2.118 |
therefore | +2.039 |
olute | +1.938 |
arget | +1.927 |
Neg logit contributions | |
ponds | -2.823 |
edin | -2.762 |
anooga | -2.712 |
xus | -2.640 |
waters | -2.522 |
Token | Team |
Token ID | 4816 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
OW | +2.112 |
ORN | +1.989 |
therefore | +1.917 |
olute | +1.833 |
ONES | +1.822 |
Neg logit contributions | |
ponds | -2.300 |
edin | -2.246 |
anooga | -2.199 |
xus | -2.139 |
waters | -2.039 |
Token | committee |
Token ID | 5583 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ponds | +1.757 |
anooga | +1.633 |
edin | +1.631 |
xus | +1.590 |
waters | +1.532 |
Neg logit contributions | |
OW | -2.039 |
ORN | -1.946 |
therefore | -1.855 |
olute | -1.826 |
edit | -1.819 |
Token | believes |
Token ID | 5804 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
OW | +1.318 |
ORN | +1.260 |
therefore | +1.230 |
olute | +1.193 |
ONES | +1.187 |
Neg logit contributions | |
ponds | -0.634 |
edin | -0.615 |
anooga | -0.594 |
xus | -0.564 |
waters | -0.515 |
Token | it |
Token ID | 340 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ponds | +0.371 |
edin | +0.365 |
anooga | +0.355 |
xus | +0.349 |
waters | +0.329 |
Neg logit contributions | |
OW | -0.324 |
ORN | -0.304 |
therefore | -0.295 |
olute | -0.280 |
RIC | -0.279 |
Token | has |
Token ID | 468 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
OW | +3.116 |
ORN | +2.918 |
therefore | +2.913 |
olute | +2.618 |
OLD | +2.615 |
Neg logit contributions | |
ponds | -3.896 |
edin | -3.841 |
xus | -3.792 |
anooga | -3.791 |
ascript | -3.482 |
Token | evidence |
Token ID | 2370 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
OW | +0.639 |
ORN | +0.601 |
therefore | +0.578 |
olute | +0.554 |
ONES | +0.551 |
Neg logit contributions | |
ponds | -0.707 |
edin | -0.691 |
anooga | -0.675 |
xus | -0.658 |
waters | -0.626 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ponds | +3.155 |
anooga | +2.977 |
edin | +2.859 |
waters | +2.806 |
outsourcing | +2.751 |
Neg logit contributions | |
OW | -3.603 |
ORN | -3.470 |
ONES | -3.270 |
ILE | -3.246 |
therefore | -3.218 |
Token | requested |
Token ID | 9167 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ponds | +4.779 |
edin | +4.564 |
anooga | +4.284 |
xus | +4.192 |
piping | +4.186 |
Neg logit contributions | |
OW | -4.874 |
ORN | -4.674 |
arget | -4.390 |
olute | -4.314 |
edit | -4.312 |
Token | putting |
Token ID | 5137 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ponds | +0.836 |
edin | +0.790 |
anooga | +0.776 |
bund | +0.752 |
outsourcing | +0.728 |
Neg logit contributions | |
OW | -1.145 |
ORN | -1.099 |
arget | -1.033 |
therefore | -1.030 |
edit | -1.023 |
Token | ally |
Token ID | 12525 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
OW | +3.762 |
ORN | +3.624 |
therefore | +3.472 |
RIC | +3.448 |
arget | +3.417 |
Neg logit contributions | |
ponds | -3.702 |
anooga | -3.700 |
xus | -3.644 |
edin | -3.620 |
waters | -3.346 |
Token | in |
Token ID | 287 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
OW | +2.345 |
therefore | +2.146 |
ORN | +2.142 |
OLD | +2.045 |
IND | +2.029 |
Neg logit contributions | |
ponds | -2.963 |
xus | -2.925 |
anooga | -2.904 |
edin | -2.850 |
ascript | -2.715 |
Token | charge |
Token ID | 3877 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
OW | +3.065 |
therefore | +3.035 |
ORN | +2.807 |
edit | +2.720 |
olute | +2.641 |
Neg logit contributions | |
edin | -3.479 |
xus | -3.463 |
anooga | -3.438 |
ascript | -3.299 |
ponds | -3.294 |
Token | aware |
Token ID | 3910 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
OW | +0.766 |
ORN | +0.729 |
therefore | +0.709 |
olute | +0.683 |
ONES | +0.679 |
Neg logit contributions | |
ponds | -0.561 |
edin | -0.544 |
anooga | -0.531 |
xus | -0.514 |
waters | -0.481 |
Token | of |
Token ID | 286 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
OW | +3.059 |
ORN | +2.851 |
therefore | +2.780 |
olute | +2.613 |
ONES | +2.586 |
Neg logit contributions | |
ponds | -4.053 |
edin | -3.991 |
anooga | -3.904 |
xus | -3.818 |
waters | -3.626 |
Token | a |
Token ID | 257 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
OW | +3.326 |
ORN | +3.113 |
therefore | +3.058 |
olute | +2.901 |
ONES | +2.887 |
Neg logit contributions | |
ponds | -3.603 |
edin | -3.561 |
anooga | -3.502 |
xus | -3.402 |
waters | -3.196 |
Token | number |
Token ID | 1271 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
OW | +0.187 |
ORN | +0.177 |
therefore | +0.169 |
olute | +0.163 |
ONES | +0.162 |
Neg logit contributions | |
ponds | -0.199 |
edin | -0.194 |
anooga | -0.189 |
xus | -0.184 |
waters | -0.176 |
Token | of |
Token ID | 286 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
OW | +0.796 |
ORN | +0.732 |
therefore | +0.722 |
arget | +0.670 |
olute | +0.669 |
Neg logit contributions | |
ponds | -1.084 |
edin | -1.076 |
anooga | -1.070 |
xus | -1.030 |
perty | -0.985 |
Token | messages |
Token ID | 6218 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
OW | +0.300 |
ORN | +0.286 |
therefore | +0.274 |
olute | +0.265 |
arget | +0.264 |
Neg logit contributions | |
ponds | -0.247 |
edin | -0.238 |
anooga | -0.230 |
xus | -0.224 |
waters | -0.212 |
Token | which |
Token ID | 543 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ponds | +3.826 |
edin | +3.737 |
anooga | +3.532 |
xus | +3.392 |
bund | +3.370 |
Neg logit contributions | |
OW | -3.884 |
ORN | -3.728 |
olute | -3.487 |
RIC | -3.442 |
ONES | -3.429 |
Token | have |
Token ID | 423 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ponds | +0.925 |
edin | +0.900 |
anooga | +0.876 |
xus | +0.848 |
waters | +0.811 |
Neg logit contributions | |
OW | -0.935 |
ORN | -0.885 |
therefore | -0.838 |
olute | -0.825 |
arget | -0.817 |
Token | been |
Token ID | 587 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
OW | +0.245 |
ORN | +0.231 |
therefore | +0.220 |
olute | +0.216 |
ONES | +0.214 |
Neg logit contributions | |
ponds | -0.235 |
edin | -0.229 |
anooga | -0.223 |
xus | -0.216 |
waters | -0.206 |
Token | posted |
Token ID | 4481 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
OW | +0.235 |
ORN | +0.223 |
therefore | +0.212 |
olute | +0.208 |
ONES | +0.206 |
Neg logit contributions | |
ponds | -0.221 |
edin | -0.216 |
anooga | -0.209 |
xus | -0.203 |
waters | -0.194 |
Token | on |
Token ID | 319 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ponds | +4.685 |
edin | +4.641 |
anooga | +4.234 |
xus | +4.104 |
weaving | +4.088 |
Neg logit contributions | |
OW | -6.397 |
ORN | -6.215 |
olute | -5.898 |
RIC | -5.876 |
ONES | -5.756 |
Token | exhibited |
Token ID | 25212 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ponds | +0.265 |
edin | +0.255 |
anooga | +0.250 |
xus | +0.243 |
waters | +0.233 |
Neg logit contributions | |
OW | -0.246 |
ORN | -0.234 |
ONES | -0.214 |
therefore | -0.214 |
olute | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ponds | +2.713 |
edin | +2.595 |
anooga | +2.528 |
xus | +2.441 |
outsourcing | +2.377 |
Neg logit contributions | |
OW | -2.736 |
ORN | -2.655 |
ONES | -2.417 |
arget | -2.412 |
therefore | -2.375 |
Token | great |
Token ID | 1049 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ponds | +0.885 |
edin | +0.861 |
anooga | +0.834 |
xus | +0.807 |
waters | +0.774 |
Neg logit contributions | |
OW | -0.952 |
ORN | -0.915 |
therefore | -0.859 |
ONES | -0.841 |
arget | -0.838 |
Token | sense |
Token ID | 2565 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
OW | +0.798 |
ORN | +0.762 |
therefore | +0.732 |
olute | +0.710 |
ONES | +0.709 |
Neg logit contributions | |
ponds | -0.622 |
edin | -0.602 |
anooga | -0.587 |
xus | -0.564 |
waters | -0.534 |
Token | of |
Token ID | 286 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
OW | +1.313 |
ORN | +1.228 |
therefore | +1.181 |
olute | +1.126 |
arget | +1.117 |
Neg logit contributions | |
ponds | -1.655 |
edin | -1.618 |
anooga | -1.583 |
xus | -1.545 |
waters | -1.476 |
Token | calm |
Token ID | 9480 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
OW | +1.931 |
ORN | +1.832 |
therefore | +1.765 |
olute | +1.702 |
ONES | +1.694 |
Neg logit contributions | |
ponds | -1.708 |
edin | -1.662 |
anooga | -1.619 |
xus | -1.571 |
waters | -1.489 |
Token | in |
Token ID | 287 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ponds | +1.558 |
edin | +1.492 |
anooga | +1.458 |
xus | +1.425 |
waters | +1.377 |
Neg logit contributions | |
OW | -1.375 |
ORN | -1.319 |
ONES | -1.205 |
therefore | -1.200 |
arget | -1.197 |
Token | regards |
Token ID | 13957 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
OW | +0.723 |
ORN | +0.686 |
therefore | +0.652 |
olute | +0.630 |
arget | +0.630 |
Neg logit contributions | |
ponds | -0.757 |
edin | -0.734 |
anooga | -0.714 |
xus | -0.698 |
waters | -0.669 |
Token | to |
Token ID | 284 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ponds | +0.075 |
edin | +0.073 |
anooga | +0.072 |
xus | +0.070 |
waters | +0.066 |
Neg logit contributions | |
OW | -0.078 |
ORN | -0.074 |
therefore | -0.072 |
olute | -0.068 |
arget | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
OW | +0.923 |
ORN | +0.875 |
therefore | +0.829 |
olute | +0.802 |
arget | +0.800 |
Neg logit contributions | |
ponds | -0.993 |
edin | -0.961 |
anooga | -0.934 |
xus | -0.914 |
waters | -0.879 |
Token | Arab |
Token ID | 4498 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
OW | +0.365 |
ORN | +0.347 |
therefore | +0.332 |
olute | +0.322 |
arget | +0.321 |
Neg logit contributions | |
ponds | -0.314 |
edin | -0.301 |
anooga | -0.292 |
xus | -0.285 |
waters | -0.273 |
Token | companies |
Token ID | 2706 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ponds | +2.290 |
edin | +2.166 |
anooga | +2.062 |
xus | +2.031 |
bund | +2.012 |
Neg logit contributions | |
OW | -3.206 |
ORN | -3.083 |
therefore | -2.929 |
olute | -2.890 |
arget | -2.872 |
Token | faced |
Token ID | 7452 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ponds | +2.298 |
edin | +2.234 |
anooga | +2.133 |
xus | +2.079 |
outsourcing | +2.064 |
Neg logit contributions | |
OW | -2.290 |
ORN | -2.182 |
arget | -2.019 |
ONES | -2.013 |
therefore | -2.012 |
Token | global |
Token ID | 3298 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
ponds | +0.040 |
edin | +0.039 |
anooga | +0.037 |
xus | +0.036 |
outsourcing | +0.034 |
Neg logit contributions | |
OW | -0.045 |
ORN | -0.042 |
therefore | -0.041 |
olute | -0.039 |
ONES | -0.039 |
Token | attacks |
Token ID | 3434 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ponds | +2.808 |
edin | +2.633 |
anooga | +2.527 |
xus | +2.520 |
outsourcing | +2.484 |
Neg logit contributions | |
OW | -4.213 |
ORN | -4.065 |
therefore | -3.863 |
ONES | -3.835 |
arget | -3.808 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ponds | +0.689 |
edin | +0.674 |
anooga | +0.649 |
xus | +0.637 |
waters | +0.613 |
Neg logit contributions | |
OW | -0.592 |
ORN | -0.560 |
therefore | -0.526 |
ONES | -0.513 |
olute | -0.513 |
Token | the |
Token ID | 262 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
ponds | +1.081 |
edin | +1.039 |
anooga | +0.988 |
xus | +0.979 |
outsourcing | +0.942 |
Neg logit contributions | |
OW | -1.425 |
ORN | -1.362 |
therefore | -1.272 |
olute | -1.271 |
ONES | -1.270 |
Token | French |
Token ID | 4141 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
OW | +0.018 |
ORN | +0.017 |
therefore | +0.016 |
olute | +0.016 |
ONES | +0.016 |
Neg logit contributions | |
ponds | -0.014 |
edin | -0.013 |
anooga | -0.013 |
xus | -0.012 |
waters | -0.012 |
Token | supermarket |
Token ID | 26454 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ponds | +2.759 |
edin | +2.647 |
anooga | +2.586 |
xus | +2.478 |
outsourcing | +2.451 |
Neg logit contributions | |
OW | -3.108 |
ORN | -2.965 |
olute | -2.742 |
arget | -2.740 |
therefore | -2.737 |
Token | chain |
Token ID | 6333 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ponds | +0.587 |
edin | +0.565 |
anooga | +0.544 |
xus | +0.523 |
bund | +0.491 |
Neg logit contributions | |
OW | -1.035 |
ORN | -0.991 |
therefore | -0.954 |
ONES | -0.932 |
arget | -0.932 |
Token | Car |
Token ID | 1879 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
ponds | +1.605 |
edin | +1.560 |
anooga | +1.512 |
xus | +1.478 |
bund | +1.413 |
Neg logit contributions | |
OW | -1.752 |
ORN | -1.665 |
therefore | -1.575 |
olute | -1.552 |
arget | -1.550 |
Token | ref |
Token ID | 5420 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ponds | +2.969 |
edin | +2.923 |
anooga | +2.826 |
xus | +2.777 |
amia | +2.704 |
Neg logit contributions | |
OW | -2.512 |
ORN | -2.401 |
therefore | -2.246 |
ONES | -2.206 |
olute | -2.168 |
Token | European |
Token ID | 3427 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
OW | +0.334 |
ORN | +0.319 |
therefore | +0.305 |
olute | +0.297 |
ONES | +0.295 |
Neg logit contributions | |
ponds | -0.279 |
edin | -0.269 |
anooga | -0.259 |
xus | -0.254 |
waters | -0.241 |
Token | Arrest |
Token ID | 35080 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ponds | +4.741 |
bund | +4.093 |
edin | +4.077 |
outsourcing | +4.058 |
anooga | +4.036 |
Neg logit contributions | |
OW | -7.140 |
ORN | -7.038 |
RIC | -6.666 |
ILE | -6.597 |
therefore | -6.564 |
Token | Warrant |
Token ID | 33872 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
OW | +1.117 |
ORN | +1.064 |
therefore | +1.015 |
ONES | +0.992 |
olute | +0.988 |
Neg logit contributions | |
ponds | -0.967 |
edin | -0.944 |
anooga | -0.904 |
xus | -0.879 |
waters | -0.845 |
Token | among |
Token ID | 1871 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ponds | +0.791 |
edin | +0.765 |
xus | +0.728 |
anooga | +0.728 |
bund | +0.703 |
Neg logit contributions | |
OW | -0.681 |
ORN | -0.649 |
olute | -0.606 |
therefore | -0.601 |
ONES | -0.596 |
Token | European |
Token ID | 3427 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ponds | +2.200 |
edin | +2.098 |
xus | +2.030 |
anooga | +2.008 |
outsourcing | +1.941 |
Neg logit contributions | |
OW | -2.230 |
ORN | -2.140 |
therefore | -2.004 |
olute | -1.971 |
edit | -1.971 |
Token | Union |
Token ID | 4479 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ponds | +4.758 |
bund | +4.164 |
outsourcing | +4.103 |
edin | +4.052 |
mand | +4.008 |
Neg logit contributions | |
OW | -7.520 |
ORN | -7.289 |
RIC | -7.022 |
therefore | -6.870 |
INC | -6.869 |
Token | member |
Token ID | 2888 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ponds | +4.032 |
edin | +3.609 |
bund | +3.575 |
mand | +3.511 |
anooga | +3.510 |
Neg logit contributions | |
OW | -4.605 |
ORN | -4.426 |
olute | -4.169 |
therefore | -4.161 |
RIC | -4.146 |
Token | states |
Token ID | 2585 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ponds | +1.486 |
edin | +1.391 |
anooga | +1.354 |
xus | +1.308 |
waters | +1.272 |
Neg logit contributions | |
OW | -2.066 |
ORN | -1.995 |
therefore | -1.878 |
olute | -1.868 |
arget | -1.865 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
OW | +0.603 |
ORN | +0.569 |
therefore | +0.537 |
olute | +0.524 |
ONES | +0.521 |
Neg logit contributions | |
ponds | -0.684 |
edin | -0.667 |
anooga | -0.647 |
xus | -0.635 |
waters | -0.606 |
Token | Assange |
Token ID | 21882 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ponds | +1.442 |
edin | +1.368 |
anooga | +1.324 |
xus | +1.319 |
outsourcing | +1.279 |
Neg logit contributions | |
OW | -1.356 |
ORN | -1.286 |
RIC | -1.187 |
arget | -1.186 |
olute | -1.186 |
Token | would |
Token ID | 561 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ponds | +0.989 |
edin | +0.953 |
anooga | +0.920 |
xus | +0.905 |
bund | +0.868 |
Neg logit contributions | |
OW | -0.945 |
ORN | -0.898 |
arget | -0.834 |
olute | -0.831 |
RIC | -0.825 |
Token | , |
Token ID | 11 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
OW | +1.436 |
ORN | +1.352 |
therefore | +1.294 |
olute | +1.245 |
ONES | +1.240 |
Neg logit contributions | |
ponds | -1.613 |
edin | -1.574 |
anooga | -1.539 |
xus | -1.498 |
waters | -1.431 |
Token | Wells |
Token ID | 18292 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
OW | +0.042 |
ORN | +0.040 |
therefore | +0.039 |
olute | +0.038 |
ONES | +0.038 |
Neg logit contributions | |
ponds | -0.031 |
edin | -0.029 |
anooga | -0.028 |
xus | -0.028 |
bund | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
OW | +3.818 |
ORN | +3.565 |
therefore | +3.449 |
olute | +3.282 |
edit | +3.249 |
Neg logit contributions | |
ponds | -4.380 |
edin | -4.293 |
anooga | -4.175 |
xus | -4.112 |
waters | -3.892 |
Token | ordered |
Token ID | 6149 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
OW | +0.780 |
ORN | +0.741 |
therefore | +0.705 |
olute | +0.688 |
ONES | +0.686 |
Neg logit contributions | |
ponds | -0.730 |
edin | -0.708 |
anooga | -0.691 |
xus | -0.667 |
waters | -0.637 |
Token | to |
Token ID | 284 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
OW | +1.018 |
ORN | +0.960 |
therefore | +0.930 |
olute | +0.887 |
arget | +0.881 |
Neg logit contributions | |
ponds | -0.999 |
edin | -0.975 |
anooga | -0.950 |
xus | -0.928 |
waters | -0.882 |
Token | pay |
Token ID | 1414 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
OW | +1.943 |
ORN | +1.865 |
therefore | +1.804 |
olute | +1.758 |
ONES | +1.752 |
Neg logit contributions | |
ponds | -1.058 |
edin | -1.019 |
anooga | -0.979 |
xus | -0.942 |
waters | -0.873 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
OW | +0.024 |
ORN | +0.023 |
therefore | +0.022 |
olute | +0.021 |
ONES | +0.021 |
Neg logit contributions | |
ponds | -0.021 |
edin | -0.020 |
anooga | -0.020 |
xus | -0.019 |
waters | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
OW | +2.290 |
ORN | +2.127 |
therefore | +2.064 |
olute | +1.951 |
arget | +1.928 |
Neg logit contributions | |
ponds | -3.039 |
edin | -2.984 |
anooga | -2.916 |
xus | -2.845 |
waters | -2.720 |
Token | millions |
Token ID | 5242 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ponds | +1.415 |
edin | +1.358 |
anooga | +1.317 |
xus | +1.289 |
bund | +1.250 |
Neg logit contributions | |
OW | -1.365 |
ORN | -1.310 |
therefore | -1.225 |
edit | -1.216 |
olute | -1.205 |
Token | of |
Token ID | 286 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
OW | +1.249 |
ORN | +1.172 |
therefore | +1.126 |
olute | +1.076 |
arget | +1.069 |
Neg logit contributions | |
ponds | -1.487 |
edin | -1.454 |
anooga | -1.424 |
xus | -1.386 |
waters | -1.323 |
Token | dollars |
Token ID | 5054 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ponds | +1.211 |
edin | +1.171 |
anooga | +1.072 |
xus | +1.048 |
bund | +1.004 |
Neg logit contributions | |
OW | -2.710 |
ORN | -2.628 |
olute | -2.506 |
ONES | -2.492 |
therefore | -2.488 |
Token | giving |
Token ID | 3501 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
ponds | +1.794 |
edin | +1.739 |
anooga | +1.633 |
xus | +1.590 |
bund | +1.583 |
Neg logit contributions | |
OW | -2.388 |
ORN | -2.316 |
olute | -2.160 |
therefore | -2.152 |
RIC | -2.145 |
Token | out |
Token ID | 503 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
OW | +3.307 |
ORN | +3.113 |
therefore | +3.010 |
olute | +2.873 |
ONES | +2.859 |
Neg logit contributions | |
ponds | -3.448 |
edin | -3.365 |
anooga | -3.309 |
xus | -3.204 |
waters | -3.060 |
Token | a |
Token ID | 257 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
OW | +0.455 |
ORN | +0.434 |
therefore | +0.416 |
olute | +0.405 |
ONES | +0.402 |
Neg logit contributions | |
ponds | -0.369 |
edin | -0.358 |
anooga | -0.344 |
xus | -0.335 |
bund | -0.317 |
Token | T |
Token ID | 309 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
OW | +1.153 |
ORN | +1.098 |
therefore | +1.062 |
olute | +1.027 |
ONES | +1.022 |
Neg logit contributions | |
ponds | -0.873 |
edin | -0.849 |
anooga | -0.823 |
xus | -0.797 |
waters | -0.751 |
Token | - |
Token ID | 12 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
OW | +2.343 |
ORN | +2.212 |
therefore | +2.149 |
olute | +2.067 |
arget | +2.044 |
Neg logit contributions | |
ponds | -2.560 |
edin | -2.514 |
anooga | -2.443 |
xus | -2.379 |
waters | -2.261 |
Token | shirt |
Token ID | 15600 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
OW | +1.812 |
ORN | +1.668 |
therefore | +1.575 |
olute | +1.481 |
arget | +1.460 |
Neg logit contributions | |
ponds | -3.675 |
edin | -3.620 |
anooga | -3.546 |
xus | -3.476 |
waters | -3.358 |
Token | that |
Token ID | 326 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
OW | +2.696 |
ORN | +2.523 |
therefore | +2.445 |
olute | +2.306 |
arget | +2.303 |
Neg logit contributions | |
ponds | -3.123 |
edin | -3.043 |
anooga | -3.006 |
xus | -2.913 |
waters | -2.781 |
Token | you |
Token ID | 345 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ponds | +1.755 |
edin | +1.711 |
anooga | +1.636 |
xus | +1.606 |
bund | +1.549 |
Neg logit contributions | |
OW | -1.765 |
ORN | -1.688 |
olute | -1.578 |
therefore | -1.574 |
ONES | -1.557 |
Token | really |
Token ID | 1107 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ponds | +0.524 |
edin | +0.508 |
anooga | +0.484 |
xus | +0.475 |
bund | +0.447 |
Neg logit contributions | |
OW | -0.718 |
ORN | -0.695 |
therefore | -0.659 |
olute | -0.652 |
arget | -0.647 |
Token | want |
Token ID | 765 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ponds | +1.307 |
edin | +1.252 |
anooga | +1.149 |
xus | +1.137 |
bund | +1.056 |
Neg logit contributions | |
OW | -2.716 |
ORN | -2.686 |
olute | -2.539 |
arget | -2.516 |
therefore | -2.508 |
Token | in |
Token ID | 287 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ponds | +0.067 |
edin | +0.066 |
anooga | +0.064 |
xus | +0.062 |
bund | +0.059 |
Neg logit contributions | |
OW | -0.078 |
ORN | -0.074 |
therefore | -0.070 |
olute | -0.069 |
arget | -0.069 |
Token | Henry |
Token ID | 8616 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
OW | +0.440 |
ORN | +0.418 |
therefore | +0.402 |
olute | +0.390 |
ONES | +0.387 |
Neg logit contributions | |
ponds | -0.384 |
edin | -0.374 |
anooga | -0.360 |
xus | -0.350 |
waters | -0.334 |
Token | R |
Token ID | 371 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ponds | +0.042 |
edin | +0.041 |
anooga | +0.040 |
xus | +0.039 |
waters | +0.037 |
Neg logit contributions | |
OW | -0.051 |
ORN | -0.048 |
therefore | -0.047 |
olute | -0.045 |
ONES | -0.045 |
Token | ugg |
Token ID | 6837 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ponds | +0.217 |
edin | +0.212 |
anooga | +0.207 |
xus | +0.200 |
waters | +0.194 |
Neg logit contributions | |
OW | -0.174 |
ORN | -0.165 |
therefore | -0.159 |
ONES | -0.151 |
RIC | -0.150 |
Token | s |
Token ID | 82 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ponds | +2.975 |
edin | +2.934 |
anooga | +2.827 |
xus | +2.740 |
waters | +2.698 |
Neg logit contributions | |
OW | -1.859 |
ORN | -1.777 |
therefore | -1.642 |
ONES | -1.640 |
olute | -1.621 |
Token | III |
Token ID | 6711 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
OW | +0.857 |
ORN | +0.818 |
therefore | +0.792 |
olute | +0.766 |
arget | +0.764 |
Neg logit contributions | |
ponds | -0.606 |
edin | -0.589 |
anooga | -0.569 |
xus | -0.551 |
waters | -0.519 |
Token | WR |
Token ID | 11342 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ponds | +0.709 |
edin | +0.692 |
anooga | +0.659 |
xus | +0.636 |
waters | +0.607 |
Neg logit contributions | |
OW | -1.005 |
ORN | -0.964 |
therefore | -0.929 |
olute | -0.906 |
arget | -0.904 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
OW | +1.362 |
ORN | +1.290 |
therefore | +1.247 |
olute | +1.205 |
ONES | +1.197 |
Neg logit contributions | |
ponds | -1.278 |
edin | -1.250 |
anooga | -1.213 |
xus | -1.177 |
waters | -1.123 |
Token | ' |
Token ID | 6 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ponds | +0.547 |
edin | +0.534 |
anooga | +0.519 |
xus | +0.504 |
waters | +0.480 |
Neg logit contributions | |
OW | -0.581 |
ORN | -0.551 |
therefore | -0.531 |
olute | -0.512 |
ONES | -0.509 |
Token | 0 |
Token ID | 15 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
edin | +4.910 |
ponds | +4.887 |
xus | +4.644 |
anooga | +4.616 |
waters | +4.555 |
Neg logit contributions | |
OW | -2.422 |
ORN | -2.277 |
therefore | -2.116 |
olute | -2.100 |
ILE | -2.056 |
Token | / |
Token ID | 14 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ponds | +1.940 |
edin | +1.905 |
anooga | +1.845 |
xus | +1.818 |
waters | +1.757 |
Neg logit contributions | |
OW | -1.177 |
ORN | -1.099 |
therefore | -1.032 |
olute | -0.993 |
ONES | -0.982 |
Token | 175 |
Token ID | 17430 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
ponds | +1.291 |
edin | +1.285 |
anooga | +1.219 |
xus | +1.214 |
waters | +1.193 |
Neg logit contributions | |
OW | -0.711 |
ORN | -0.662 |
therefore | -0.636 |
olute | -0.609 |
arget | -0.594 |
Token | E |
Token ID | 36 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
OW | +0.812 |
ORN | +0.763 |
therefore | +0.734 |
olute | +0.700 |
arget | +0.692 |
Neg logit contributions | |
ponds | -1.162 |
edin | -1.152 |
anooga | -1.119 |
xus | -1.095 |
waters | -1.061 |
Token | ad |
Token ID | 324 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
edin | +3.730 |
ponds | +3.691 |
anooga | +3.531 |
xus | +3.480 |
waters | +3.343 |
Neg logit contributions | |
OW | -3.339 |
ORN | -3.229 |
therefore | -3.093 |
ONES | -3.045 |
arget | -2.987 |
Token | gar |
Token ID | 4563 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
ponds | +1.084 |
edin | +1.059 |
anooga | +1.012 |
xus | +0.984 |
waters | +0.916 |
Neg logit contributions | |
OW | -2.031 |
ORN | -1.945 |
therefore | -1.876 |
ONES | -1.835 |
olute | -1.820 |
Token | A |
Token ID | 317 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ponds | +0.036 |
edin | +0.035 |
anooga | +0.034 |
xus | +0.033 |
waters | +0.032 |
Neg logit contributions | |
OW | -0.034 |
ORN | -0.032 |
therefore | -0.030 |
olute | -0.030 |
ONES | -0.030 |
Token | ethe |
Token ID | 10567 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ponds | +0.690 |
edin | +0.673 |
anooga | +0.640 |
xus | +0.620 |
waters | +0.576 |
Neg logit contributions | |
OW | -1.330 |
ORN | -1.279 |
therefore | -1.236 |
ONES | -1.205 |
olute | -1.198 |
Token | ling |
Token ID | 1359 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ponds | +0.915 |
edin | +0.900 |
anooga | +0.876 |
xus | +0.860 |
waters | +0.828 |
Neg logit contributions | |
OW | -0.633 |
ORN | -0.591 |
therefore | -0.562 |
ONES | -0.535 |
olute | -0.535 |
Token | fled |
Token ID | 11468 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
OW | +1.392 |
ORN | +1.320 |
therefore | +1.244 |
olute | +1.213 |
ONES | +1.211 |
Neg logit contributions | |
ponds | -1.560 |
edin | -1.522 |
anooga | -1.478 |
xus | -1.451 |
waters | -1.382 |
Token | to |
Token ID | 284 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ponds | +1.484 |
edin | +1.444 |
xus | +1.361 |
anooga | +1.361 |
waters | +1.304 |
Neg logit contributions | |
OW | -1.678 |
ORN | -1.591 |
therefore | -1.485 |
arget | -1.483 |
ONES | -1.480 |
Token | Scotland |
Token ID | 8838 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
OW | +1.279 |
ORN | +1.212 |
therefore | +1.167 |
olute | +1.127 |
arget | +1.126 |
Neg logit contributions | |
ponds | -1.095 |
edin | -1.063 |
anooga | -1.029 |
xus | -1.002 |
waters | -0.951 |
Token | with |
Token ID | 351 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ponds | +2.360 |
edin | +2.295 |
anooga | +2.175 |
xus | +2.163 |
waters | +2.100 |
Neg logit contributions | |
OW | -2.290 |
ORN | -2.183 |
therefore | -2.018 |
arget | -2.015 |
ONES | -2.013 |
Token | his |
Token ID | 465 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
OW | +0.935 |
ORN | +0.885 |
therefore | +0.841 |
arget | +0.815 |
ONES | +0.812 |
Neg logit contributions | |
ponds | -0.959 |
edin | -0.932 |
anooga | -0.906 |
xus | -0.885 |
waters | -0.844 |
Token | opposed |
Token ID | 6886 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ponds | +1.305 |
edin | +1.266 |
anooga | +1.218 |
xus | +1.203 |
waters | +1.147 |
Neg logit contributions | |
OW | -1.271 |
ORN | -1.233 |
arget | -1.128 |
olute | -1.125 |
RIC | -1.122 |
Token | being |
Token ID | 852 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
OW | +1.085 |
ORN | +1.027 |
therefore | +0.974 |
ONES | +0.947 |
olute | +0.946 |
Neg logit contributions | |
ponds | -1.137 |
edin | -1.111 |
anooga | -1.078 |
xus | -1.056 |
waters | -1.005 |
Token | cons |
Token ID | 762 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
OW | +2.101 |
ORN | +1.994 |
therefore | +1.907 |
olute | +1.850 |
ONES | +1.843 |
Neg logit contributions | |
ponds | -1.986 |
edin | -1.935 |
anooga | -1.883 |
xus | -1.831 |
waters | -1.739 |
Token | cript |
Token ID | 6519 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
OW | +1.942 |
ORN | +1.820 |
therefore | +1.750 |
olute | +1.679 |
arget | +1.664 |
Neg logit contributions | |
ponds | -2.322 |
edin | -2.268 |
anooga | -2.223 |
xus | -2.162 |
waters | -2.065 |
Token | ed |
Token ID | 276 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
OW | +2.121 |
ORN | +2.008 |
therefore | +1.892 |
ONES | +1.843 |
olute | +1.836 |
Neg logit contributions | |
ponds | -2.374 |
edin | -2.346 |
anooga | -2.254 |
xus | -2.209 |
waters | -2.126 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
OW | +1.384 |
ORN | +1.306 |
therefore | +1.226 |
olute | +1.195 |
ONES | +1.191 |
Neg logit contributions | |
ponds | -1.713 |
edin | -1.677 |
anooga | -1.627 |
xus | -1.596 |
waters | -1.531 |
Token | 28 |
Token ID | 2078 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
OW | +3.029 |
ORN | +2.788 |
therefore | +2.667 |
edit | +2.537 |
RIC | +2.501 |
Neg logit contributions | |
ponds | -4.929 |
edin | -4.792 |
anooga | -4.765 |
xus | -4.613 |
outsourcing | -4.394 |
Token | ] |
Token ID | 60 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ponds | +2.390 |
edin | +2.357 |
anooga | +2.190 |
xus | +2.171 |
waters | +2.038 |
Neg logit contributions | |
OW | -3.976 |
ORN | -3.827 |
therefore | -3.670 |
olute | -3.606 |
ONES | -3.602 |
Token | Aut |
Token ID | 5231 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
OW | +0.898 |
ORN | +0.850 |
therefore | +0.807 |
olute | +0.786 |
arget | +0.779 |
Neg logit contributions | |
ponds | -1.004 |
edin | -0.986 |
anooga | -0.949 |
xus | -0.932 |
waters | -0.893 |
Token | onomous |
Token ID | 38175 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
OW | +3.123 |
ORN | +2.923 |
therefore | +2.811 |
olute | +2.708 |
arget | +2.686 |
Neg logit contributions | |
ponds | -3.511 |
edin | -3.429 |
anooga | -3.352 |
xus | -3.263 |
waters | -3.114 |
Token | military |
Token ID | 2422 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
OW | +0.636 |
ORN | +0.604 |
therefore | +0.575 |
olute | +0.563 |
arget | +0.562 |
Neg logit contributions | |
ponds | -0.565 |
edin | -0.544 |
anooga | -0.524 |
xus | -0.515 |
waters | -0.489 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
OW | +0.442 |
ORN | +0.421 |
therefore | +0.396 |
arget | +0.388 |
olute | +0.386 |
Neg logit contributions | |
ponds | -0.440 |
edin | -0.421 |
anooga | -0.408 |
xus | -0.399 |
waters | -0.387 |
Token | love |
Token ID | 1842 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
OW | +0.454 |
ORN | +0.430 |
therefore | +0.413 |
arget | +0.402 |
ONES | +0.400 |
Neg logit contributions | |
ponds | -0.348 |
edin | -0.335 |
anooga | -0.325 |
xus | -0.317 |
waters | -0.300 |
Token | ? |
Token ID | 30 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
OW | +1.271 |
ORN | +1.201 |
therefore | +1.140 |
olute | +1.100 |
arget | +1.094 |
Neg logit contributions | |
ponds | -1.475 |
edin | -1.434 |
anooga | -1.399 |
xus | -1.368 |
waters | -1.309 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
OW | +1.106 |
ORN | +1.042 |
therefore | +0.996 |
olute | +0.974 |
arget | +0.962 |
Neg logit contributions | |
ponds | -1.242 |
edin | -1.220 |
anooga | -1.176 |
xus | -1.149 |
waters | -1.107 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
OW | +0.989 |
ORN | +0.904 |
therefore | +0.884 |
edit | +0.832 |
arget | +0.822 |
Neg logit contributions | |
ponds | -1.454 |
anooga | -1.421 |
edin | -1.412 |
xus | -1.377 |
perty | -1.321 |
Token | R |
Token ID | 49 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
OW | +0.375 |
therefore | +0.347 |
ORN | +0.346 |
olute | +0.329 |
arget | +0.319 |
Neg logit contributions | |
ponds | -0.608 |
edin | -0.608 |
anooga | -0.590 |
xus | -0.581 |
waters | -0.563 |
Token | USE |
Token ID | 19108 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
OW | +1.383 |
ORN | +1.264 |
therefore | +1.176 |
olute | +1.102 |
ONES | +1.101 |
Neg logit contributions | |
ponds | -2.938 |
edin | -2.873 |
anooga | -2.835 |
xus | -2.774 |
waters | -2.671 |
Token | LL |
Token ID | 3069 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
OW | +1.073 |
ORN | +0.945 |
therefore | +0.839 |
ONES | +0.776 |
ILE | +0.770 |
Neg logit contributions | |
ponds | -3.331 |
edin | -3.253 |
anooga | -3.238 |
xus | -3.169 |
perty | -3.068 |
Token | : |
Token ID | 25 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
OW | +2.675 |
ORN | +2.446 |
therefore | +2.361 |
ONES | +2.230 |
edit | +2.202 |
Neg logit contributions | |
ponds | -3.685 |
anooga | -3.653 |
edin | -3.597 |
xus | -3.491 |
perty | -3.398 |
Token | That |
Token ID | 1320 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
OW | +2.358 |
ORN | +2.225 |
therefore | +2.139 |
olute | +2.055 |
ONES | +2.043 |
Neg logit contributions | |
ponds | -2.474 |
edin | -2.415 |
anooga | -2.356 |
xus | -2.293 |
waters | -2.184 |
Token | is |
Token ID | 318 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
OW | +3.627 |
ORN | +3.404 |
therefore | +3.281 |
olute | +3.102 |
ONES | +3.092 |
Neg logit contributions | |
ponds | -4.500 |
edin | -4.403 |
anooga | -4.323 |
xus | -4.224 |
waters | -4.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
ponds | +1.907 |
edin | +1.840 |
anooga | +1.756 |
xus | +1.735 |
bund | +1.684 |
Neg logit contributions | |
OW | -1.941 |
ORN | -1.838 |
therefore | -1.735 |
arget | -1.707 |
ONES | -1.704 |
Token | next |
Token ID | 1306 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
OW | +0.076 |
ORN | +0.072 |
therefore | +0.070 |
olute | +0.068 |
arget | +0.068 |
Neg logit contributions | |
ponds | -0.059 |
edin | -0.057 |
anooga | -0.055 |
xus | -0.054 |
waters | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
ponds | +1.745 |
edin | +1.677 |
anooga | +1.625 |
xus | +1.613 |
waters | +1.549 |
Neg logit contributions | |
OW | -1.700 |
ORN | -1.592 |
therefore | -1.548 |
edit | -1.492 |
olute | -1.482 |
Token | generation |
Token ID | 20158 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
ponds | +2.755 |
edin | +2.693 |
xus | +2.611 |
anooga | +2.598 |
waters | +2.518 |
Neg logit contributions | |
OW | -3.757 |
ORN | -3.571 |
therefore | -3.470 |
ILE | -3.369 |
olute | -3.365 |
Token | Twin |
Token ID | 14968 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ponds | +0.340 |
edin | +0.328 |
anooga | +0.314 |
xus | +0.311 |
bund | +0.295 |
Neg logit contributions | |
OW | -0.380 |
ORN | -0.362 |
therefore | -0.346 |
ONES | -0.337 |
arget | -0.336 |
Token | Fro |
Token ID | 9734 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
OW | +4.048 |
ORN | +3.773 |
therefore | +3.636 |
olute | +3.498 |
arget | +3.469 |
Neg logit contributions | |
ponds | -4.624 |
edin | -4.500 |
anooga | -4.468 |
xus | -4.330 |
waters | -4.090 |
Token | z |
Token ID | 89 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
OW | +4.451 |
ORN | +3.650 |
therefore | +3.628 |
edit | +3.425 |
arget | +3.378 |
Neg logit contributions | |
ponds | -9.786 |
anooga | -9.776 |
edin | -9.437 |
perty | -9.104 |
bund | -9.096 |
Token | r |
Token ID | 81 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
OW | +3.811 |
ORN | +3.540 |
therefore | +3.464 |
arget | +3.357 |
edit | +3.318 |
Neg logit contributions | |
anooga | -4.009 |
ponds | -3.977 |
edin | -3.881 |
xus | -3.698 |
perty | -3.637 |
Token | IV |
Token ID | 8363 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
OW | +2.636 |
ORN | +2.483 |
therefore | +2.395 |
olute | +2.296 |
ONES | +2.280 |
Neg logit contributions | |
ponds | -2.723 |
edin | -2.663 |
anooga | -2.605 |
xus | -2.528 |
waters | -2.406 |
Token | Thermal |
Token ID | 41590 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
OW | +1.989 |
ORN | +1.896 |
therefore | +1.823 |
olute | +1.767 |
ONES | +1.765 |
Neg logit contributions | |
ponds | -1.565 |
edin | -1.516 |
anooga | -1.466 |
xus | -1.431 |
waters | -1.350 |
Token | Design |
Token ID | 8495 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
OW | +0.514 |
ORN | +0.495 |
therefore | +0.477 |
olute | +0.466 |
ONES | +0.465 |
Neg logit contributions | |
ponds | -0.282 |
edin | -0.273 |
anooga | -0.259 |
xus | -0.250 |
waters | -0.233 |
Token | - |
Token ID | 12 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
ponds | +1.899 |
edin | +1.869 |
anooga | +1.797 |
xus | +1.742 |
waters | +1.680 |
Neg logit contributions | |
OW | -1.943 |
ORN | -1.846 |
therefore | -1.736 |
olute | -1.710 |
ONES | -1.702 |
Token | technology |
Token ID | 45503 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ponds | +0.194 |
edin | +0.192 |
anooga | +0.184 |
xus | +0.180 |
waters | +0.172 |
Neg logit contributions | |
OW | -0.233 |
ORN | -0.222 |
therefore | -0.214 |
olute | -0.208 |
ONES | -0.207 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
ponds | +3.109 |
edin | +3.049 |
anooga | +2.937 |
xus | +2.874 |
waters | +2.760 |
Neg logit contributions | |
OW | -2.754 |
ORN | -2.613 |
therefore | -2.435 |
olute | -2.397 |
ONES | -2.390 |
Token | The |
Token ID | 464 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
OW | +2.042 |
ORN | +1.914 |
therefore | +1.840 |
olute | +1.755 |
ONES | +1.738 |
Neg logit contributions | |
ponds | -2.693 |
edin | -2.644 |
anooga | -2.583 |
xus | -2.524 |
waters | -2.420 |
Token | People |
Token ID | 4380 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
OW | +1.350 |
ORN | +1.284 |
therefore | +1.241 |
olute | +1.197 |
ONES | +1.192 |
Neg logit contributions | |
ponds | -1.115 |
edin | -1.081 |
anooga | -1.051 |
xus | -1.022 |
waters | -0.966 |
Token | v |
Token ID | 410 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
OW | +0.090 |
ORN | +0.087 |
therefore | +0.081 |
ILE | +0.079 |
olute | +0.079 |
Neg logit contributions | |
ponds | -0.104 |
edin | -0.102 |
anooga | -0.099 |
xus | -0.097 |
waters | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
OW | +7.072 |
ORN | +6.516 |
therefore | +6.174 |
arget | +6.082 |
ONES | +6.001 |
Neg logit contributions | |
ponds | -8.955 |
xus | -8.648 |
edin | -8.630 |
anooga | -8.443 |
bund | -8.107 |
Token | O |
Token ID | 440 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
OW | +5.907 |
ORN | +5.506 |
therefore | +5.398 |
arget | +5.170 |
ILE | +5.155 |
Neg logit contributions | |
ponds | -4.796 |
edin | -4.613 |
xus | -4.469 |
anooga | -4.467 |
ascript | -4.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
OW | +1.381 |
ORN | +1.301 |
therefore | +1.250 |
olute | +1.196 |
arget | +1.191 |
Neg logit contributions | |
ponds | -1.589 |
edin | -1.553 |
anooga | -1.514 |
xus | -1.477 |
waters | -1.414 |
Token | J |
Token ID | 41 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
OW | +3.094 |
ORN | +2.870 |
therefore | +2.735 |
olute | +2.581 |
ONES | +2.571 |
Neg logit contributions | |
ponds | -4.925 |
edin | -4.829 |
anooga | -4.728 |
xus | -4.631 |
waters | -4.441 |
Token | . |
Token ID | 13 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
ponds | +0.321 |
edin | +0.314 |
anooga | +0.307 |
xus | +0.299 |
waters | +0.286 |
Neg logit contributions | |
OW | -0.254 |
ORN | -0.239 |
therefore | -0.229 |
olute | -0.219 |
arget | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
OW | +1.472 |
ORN | +1.330 |
therefore | +1.317 |
edit | +1.235 |
arget | +1.218 |
Neg logit contributions | |
ponds | -2.231 |
anooga | -2.198 |
edin | -2.169 |
xus | -2.121 |
perty | -2.050 |
Token | Some |
Token ID | 4366 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
OW | +0.706 |
ORN | +0.666 |
therefore | +0.645 |
olute | +0.616 |
ONES | +0.604 |
Neg logit contributions | |
ponds | -0.959 |
edin | -0.948 |
anooga | -0.920 |
xus | -0.898 |
waters | -0.873 |
Token | people |
Token ID | 661 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
OW | +1.502 |
ORN | +1.436 |
therefore | +1.383 |
olute | +1.341 |
arget | +1.336 |
Neg logit contributions | |
ponds | -1.139 |
edin | -1.093 |
anooga | -1.066 |
xus | -1.031 |
waters | -0.979 |
Token | , |
Token ID | 11 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ponds | +0.753 |
edin | +0.722 |
anooga | +0.690 |
xus | +0.669 |
bund | +0.643 |
Neg logit contributions | |
OW | -0.902 |
ORN | -0.869 |
therefore | -0.809 |
olute | -0.806 |
arget | -0.802 |
Token | like |
Token ID | 588 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
OW | +1.695 |
ORN | +1.599 |
therefore | +1.512 |
olute | +1.470 |
arget | +1.463 |
Neg logit contributions | |
ponds | -1.910 |
edin | -1.856 |
anooga | -1.810 |
xus | -1.763 |
waters | -1.685 |
Token | Dani |
Token ID | 22254 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
OW | +1.027 |
ORN | +0.971 |
therefore | +0.927 |
olute | +0.897 |
arget | +0.894 |
Neg logit contributions | |
ponds | -1.063 |
edin | -1.032 |
anooga | -0.998 |
xus | -0.978 |
waters | -0.932 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
OW | +5.919 |
ORN | +5.529 |
therefore | +5.415 |
olute | +5.081 |
edit | +5.027 |
Neg logit contributions | |
ponds | -7.440 |
edin | -7.298 |
anooga | -7.198 |
xus | -6.824 |
perty | -6.625 |
Token | will |
Token ID | 481 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
OW | +1.551 |
ORN | +1.477 |
therefore | +1.420 |
olute | +1.377 |
arget | +1.371 |
Neg logit contributions | |
ponds | -1.251 |
edin | -1.214 |
anooga | -1.178 |
xus | -1.142 |
waters | -1.079 |
Token | prefer |
Token ID | 4702 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
OW | +0.916 |
ORN | +0.877 |
therefore | +0.838 |
olute | +0.818 |
ONES | +0.814 |
Neg logit contributions | |
ponds | -0.710 |
edin | -0.690 |
anooga | -0.666 |
xus | -0.644 |
waters | -0.610 |
Token | spectator |
Token ID | 43893 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
OW | +2.245 |
ORN | +2.127 |
therefore | +2.056 |
olute | +1.977 |
ONES | +1.965 |
Neg logit contributions | |
ponds | -2.039 |
edin | -1.990 |
anooga | -1.942 |
xus | -1.884 |
waters | -1.785 |
Token | activities |
Token ID | 4568 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ponds | +0.531 |
edin | +0.503 |
anooga | +0.488 |
xus | +0.479 |
bund | +0.461 |
Neg logit contributions | |
OW | -0.558 |
ORN | -0.537 |
therefore | -0.505 |
olute | -0.496 |
arget | -0.490 |
Token | name |
Token ID | 3672 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
OW | +1.466 |
ORN | +1.378 |
therefore | +1.314 |
olute | +1.256 |
arget | +1.245 |
Neg logit contributions | |
ponds | -1.913 |
edin | -1.882 |
anooga | -1.833 |
xus | -1.791 |
waters | -1.718 |
Token | }} |
Token ID | 34949 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
OW | +2.662 |
ORN | +2.508 |
therefore | +2.417 |
olute | +2.319 |
arget | +2.304 |
Neg logit contributions | |
ponds | -2.782 |
edin | -2.713 |
anooga | -2.653 |
xus | -2.582 |
waters | -2.453 |
Token | < |
Token ID | 1279 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
OW | +4.347 |
ORN | +3.932 |
therefore | +3.871 |
olute | +3.544 |
arget | +3.521 |
Neg logit contributions | |
ponds | -9.855 |
anooga | -9.602 |
edin | -9.594 |
xus | -9.387 |
waters | -9.082 |
Token | p |
Token ID | 79 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
OW | +6.365 |
ORN | +5.857 |
therefore | +5.711 |
edit | +5.538 |
olute | +5.420 |
Neg logit contributions | |
ponds | -9.094 |
anooga | -8.830 |
edin | -8.789 |
xus | -8.513 |
waters | -8.152 |
Token | > |
Token ID | 29 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
OW | +3.810 |
ORN | +3.526 |
therefore | +3.389 |
olute | +3.219 |
edit | +3.194 |
Neg logit contributions | |
ponds | -5.603 |
edin | -5.471 |
anooga | -5.391 |
xus | -5.273 |
waters | -5.015 |
Token | {{ |
Token ID | 27007 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
OW | +5.445 |
ORN | +5.053 |
therefore | +4.847 |
edit | +4.690 |
arget | +4.635 |
Neg logit contributions | |
ponds | -6.831 |
edin | -6.528 |
anooga | -6.495 |
xus | -6.325 |
waters | -6.037 |
Token | phone |
Token ID | 3072 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
OW | +8.504 |
ORN | +8.013 |
therefore | +7.978 |
edit | +7.567 |
olute | +7.543 |
Neg logit contributions | |
ponds | -7.859 |
anooga | -7.625 |
edin | -7.599 |
xus | -7.310 |
waters | -6.991 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
OW | +3.705 |
ORN | +3.449 |
therefore | +3.352 |
olute | +3.174 |
edit | +3.171 |
Neg logit contributions | |
ponds | -5.076 |
edin | -4.967 |
anooga | -4.874 |
xus | -4.752 |
waters | -4.552 |
Token | sn |
Token ID | 16184 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
OW | +2.155 |
ORN | +2.019 |
therefore | +1.934 |
olute | +1.847 |
ONES | +1.836 |
Neg logit contributions | |
ponds | -2.741 |
edin | -2.680 |
anooga | -2.623 |
xus | -2.559 |
waters | -2.446 |
Token | ipp |
Token ID | 3974 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
OW | +2.071 |
ORN | +1.920 |
therefore | +1.827 |
olute | +1.732 |
arget | +1.730 |
Neg logit contributions | |
ponds | -3.140 |
edin | -3.073 |
anooga | -3.018 |
xus | -2.948 |
waters | -2.824 |
Token | et |
Token ID | 316 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
OW | +2.168 |
ORN | +2.004 |
therefore | +1.909 |
arget | +1.813 |
olute | +1.812 |
Neg logit contributions | |
ponds | -3.378 |
edin | -3.292 |
anooga | -3.246 |
xus | -3.168 |
waters | -3.037 |
Token | on |
Token ID | 319 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ponds | +0.309 |
edin | +0.299 |
anooga | +0.289 |
xus | +0.284 |
waters | +0.272 |
Neg logit contributions | |
OW | -0.312 |
ORN | -0.296 |
therefore | -0.282 |
olute | -0.275 |
arget | -0.273 |
Token | the |
Token ID | 262 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ponds | +0.585 |
edin | +0.565 |
anooga | +0.544 |
xus | +0.534 |
waters | +0.514 |
Neg logit contributions | |
OW | -0.595 |
ORN | -0.560 |
therefore | -0.541 |
olute | -0.523 |
arget | -0.518 |
Token | night |
Token ID | 1755 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ponds | +0.211 |
edin | +0.202 |
anooga | +0.195 |
xus | +0.191 |
waters | +0.183 |
Neg logit contributions | |
OW | -0.255 |
ORN | -0.242 |
therefore | -0.234 |
olute | -0.228 |
arget | -0.226 |
Token | of |
Token ID | 286 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
OW | +0.623 |
ORN | +0.589 |
therefore | +0.562 |
olute | +0.545 |
arget | +0.540 |
Neg logit contributions | |
ponds | -0.705 |
edin | -0.686 |
anooga | -0.665 |
xus | -0.652 |
waters | -0.629 |
Token | her |
Token ID | 607 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
OW | +1.857 |
ORN | +1.757 |
therefore | +1.694 |
olute | +1.625 |
ONES | +1.616 |
Neg logit contributions | |
ponds | -1.815 |
edin | -1.774 |
anooga | -1.736 |
xus | -1.683 |
waters | -1.594 |
Token | fatal |
Token ID | 10800 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
OW | +2.505 |
ORN | +2.364 |
therefore | +2.285 |
olute | +2.176 |
ONES | +2.165 |
Neg logit contributions | |
ponds | -2.643 |
edin | -2.609 |
anooga | -2.567 |
xus | -2.479 |
waters | -2.345 |
Token | car |
Token ID | 1097 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
OW | +6.767 |
ORN | +6.395 |
therefore | +6.259 |
RIC | +5.955 |
edit | +5.910 |
Neg logit contributions | |
edin | -6.029 |
ponds | -5.993 |
anooga | -5.936 |
xus | -5.763 |
waters | -5.278 |
Token | crash |
Token ID | 7014 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
OW | +4.516 |
ORN | +4.315 |
therefore | +4.185 |
olute | +4.050 |
edit | +4.024 |
Neg logit contributions | |
ponds | -2.844 |
edin | -2.753 |
anooga | -2.684 |
xus | -2.585 |
waters | -2.398 |
Token | ) |
Token ID | 8 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
OW | +2.814 |
ORN | +2.647 |
therefore | +2.570 |
olute | +2.430 |
ONES | +2.424 |
Neg logit contributions | |
ponds | -3.103 |
edin | -3.035 |
anooga | -2.999 |
xus | -2.914 |
waters | -2.727 |
Token | got |
Token ID | 1392 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ponds | +0.124 |
edin | +0.120 |
anooga | +0.116 |
xus | +0.113 |
waters | +0.108 |
Neg logit contributions | |
OW | -0.121 |
ORN | -0.116 |
therefore | -0.108 |
olute | -0.107 |
arget | -0.106 |
Token | his |
Token ID | 465 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ponds | +0.152 |
edin | +0.148 |
anooga | +0.144 |
xus | +0.140 |
waters | +0.134 |
Neg logit contributions | |
OW | -0.140 |
ORN | -0.133 |
therefore | -0.126 |
olute | -0.122 |
ONES | -0.122 |