Token | more |
Token ID | 517 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Rudolph | +0.022 |
Fl | +0.021 |
Nib | +0.020 |
Sn | +0.020 |
Fl | +0.020 |
Neg logit contributions | |
listener | -0.025 |
joy | -0.024 |
itting | -0.024 |
working | -0.024 |
ogs | -0.024 |
Token | important |
Token ID | 1593 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
joy | +0.032 |
ogs | +0.031 |
listener | +0.031 |
itting | +0.030 |
working | +0.030 |
Neg logit contributions | |
Rudolph | -0.039 |
Fl | -0.037 |
Fl | -0.036 |
Sn | -0.036 |
Nib | -0.036 |
Token | than |
Token ID | 621 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
Rudolph | +0.010 |
Fl | +0.010 |
Sn | +0.010 |
Nib | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
itting | -0.008 |
listener | -0.008 |
joy | -0.007 |
working | -0.007 |
ogs | -0.007 |
Token | any |
Token ID | 597 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
listener | +0.113 |
ogs | +0.111 |
itting | +0.111 |
joy | +0.110 |
working | +0.108 |
Neg logit contributions | |
Rudolph | -0.101 |
Fl | -0.099 |
Nib | -0.095 |
Sn | -0.094 |
Frost | -0.091 |
Token | cr |
Token ID | 1067 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
ogs | +0.091 |
itting | +0.089 |
ogged | +0.089 |
ule | +0.083 |
listener | +0.082 |
Neg logit contributions | |
Fl | -0.072 |
from | -0.070 |
Rudolph | -0.068 |
extingu | -0.066 |
Nib | -0.064 |
Token | ay |
Token ID | 323 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
joy | +0.083 |
listener | +0.082 |
runner | +0.067 |
working | +0.064 |
ogs | +0.061 |
Neg logit contributions | |
extingu | -0.164 |
ified | -0.158 |
Sn | -0.157 |
Rudolph | -0.157 |
Fl | -0.154 |
Token | on |
Token ID | 261 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
listener | +0.262 |
runner | +0.236 |
joy | +0.232 |
ogs | +0.219 |
kicker | +0.215 |
Neg logit contributions | |
extingu | -0.166 |
ion | -0.162 |
Frost | -0.160 |
� | -0.159 |
soda | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
joy | +0.086 |
listener | +0.082 |
ogs | +0.075 |
ogged | +0.074 |
runner | +0.073 |
Neg logit contributions | |
Rudolph | -0.061 |
from | -0.059 |
Fl | -0.059 |
extingu | -0.057 |
Sn | -0.055 |
Token | From |
Token ID | 3574 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
joy | +0.023 |
listener | +0.022 |
itting | +0.022 |
ogs | +0.022 |
working | +0.021 |
Neg logit contributions | |
Rudolph | -0.020 |
Fl | -0.019 |
Fl | -0.019 |
Sn | -0.019 |
Nib | -0.019 |
Token | then |
Token ID | 788 |
Feature activation | -2.28e-03 |
Pos logit contributions | |
Sn | +0.031 |
Fl | +0.030 |
sc | +0.030 |
extingu | +0.030 |
Fl | +0.029 |
Neg logit contributions | |
friends | -0.025 |
working | -0.023 |
joy | -0.022 |
listener | -0.022 |
ogs | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Sn | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
working | -0.004 |
itting | -0.004 |
ogs | -0.004 |
Token | book |
Token ID | 1492 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
itting | +0.035 |
ogs | +0.033 |
listener | +0.033 |
joy | +0.032 |
ogged | +0.031 |
Neg logit contributions | |
Fl | -0.035 |
Rudolph | -0.035 |
extingu | -0.035 |
Nib | -0.034 |
Frost | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
joy | +0.015 |
listener | +0.015 |
itting | +0.014 |
working | +0.014 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.014 |
Fl | -0.014 |
Sn | -0.013 |
Nib | -0.013 |
Fl | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
listener | +0.005 |
joy | +0.005 |
itting | +0.005 |
working | +0.005 |
ogs | +0.005 |
Neg logit contributions | |
Rudolph | -0.005 |
Fl | -0.005 |
Nib | -0.004 |
Sn | -0.004 |
Fl | -0.004 |
Token | new |
Token ID | 649 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
ogs | +0.024 |
itting | +0.024 |
listener | +0.023 |
working | +0.023 |
joy | +0.023 |
Neg logit contributions | |
Rudolph | -0.026 |
Fl | -0.026 |
Nib | -0.025 |
Sn | -0.025 |
Fl | -0.024 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
itting | +0.061 |
ogs | +0.058 |
listener | +0.056 |
ogged | +0.056 |
working | +0.055 |
Neg logit contributions | |
Fl | -0.062 |
Rudolph | -0.059 |
Nib | -0.057 |
extingu | -0.057 |
Flor | -0.057 |
Token | ay |
Token ID | 323 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
joy | +0.058 |
listener | +0.049 |
working | +0.040 |
ogs | +0.037 |
runner | +0.037 |
Neg logit contributions | |
Rudolph | -0.143 |
extingu | -0.141 |
Sn | -0.140 |
Fl | -0.139 |
Fl | -0.137 |
Token | on |
Token ID | 261 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
joy | +0.237 |
listener | +0.216 |
itting | +0.208 |
runner | +0.192 |
ogs | +0.183 |
Neg logit contributions | |
Rudolph | -0.182 |
ion | -0.177 |
from | -0.175 |
Fl | -0.172 |
Fl | -0.171 |
Token | ." |
Token ID | 526 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
joy | +0.076 |
listener | +0.071 |
itting | +0.071 |
ogs | +0.067 |
working | +0.065 |
Neg logit contributions | |
Rudolph | -0.051 |
Fl | -0.049 |
extingu | -0.047 |
Sn | -0.047 |
Nib | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
listener | +0.009 |
working | +0.009 |
itting | +0.009 |
joy | +0.009 |
ogs | +0.008 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.006 |
Nib | -0.006 |
Sn | -0.006 |
Fl | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
Rudolph | +0.002 |
Fl | +0.002 |
Sn | +0.002 |
Nib | +0.002 |
Fl | +0.002 |
Neg logit contributions | |
listener | -0.002 |
joy | -0.002 |
working | -0.002 |
itting | -0.002 |
ogs | -0.002 |
Token | Ben |
Token ID | 11696 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
Rudolph | +0.012 |
Fl | +0.012 |
Fl | +0.012 |
Sn | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
listener | -0.011 |
joy | -0.011 |
working | -0.011 |
itting | -0.011 |
ogs | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
listener | +0.007 |
itting | +0.007 |
working | +0.007 |
joy | +0.007 |
ogs | +0.006 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Sn | -0.006 |
Nib | -0.006 |
Fl | -0.005 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
listener | +0.032 |
itting | +0.032 |
joy | +0.032 |
working | +0.030 |
oom | +0.030 |
Neg logit contributions | |
Fl | -0.031 |
Rudolph | -0.030 |
Nib | -0.029 |
Fl | -0.029 |
Sn | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-04 |
Pos logit contributions | |
Rudolph | +0.022 |
Fl | +0.021 |
Nib | +0.021 |
Sn | +0.021 |
Fl | +0.020 |
Neg logit contributions | |
listener | -0.020 |
joy | -0.020 |
itting | -0.020 |
working | -0.019 |
ogs | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
listener | +0.001 |
joy | +0.001 |
itting | +0.001 |
ogs | +0.001 |
working | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Nib | -0.001 |
Sn | -0.000 |
Fl | -0.000 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ogs | +0.029 |
itting | +0.028 |
listener | +0.028 |
ogged | +0.027 |
working | +0.027 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.029 |
Sn | -0.027 |
Nib | -0.027 |
Fl | -0.027 |
Token | ay |
Token ID | 323 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
joy | +0.042 |
listener | +0.039 |
working | +0.034 |
ogs | +0.031 |
runner | +0.029 |
Neg logit contributions | |
Rudolph | -0.152 |
extingu | -0.150 |
Fl | -0.149 |
Sn | -0.149 |
Nib | -0.149 |
Token | on |
Token ID | 261 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
joy | +0.212 |
listener | +0.208 |
runner | +0.189 |
itting | +0.182 |
ogs | +0.179 |
Neg logit contributions | |
ion | -0.191 |
Fl | -0.188 |
extingu | -0.186 |
Fl | -0.185 |
Rudolph | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-04 |
Pos logit contributions | |
joy | +0.074 |
listener | +0.070 |
itting | +0.068 |
ogs | +0.067 |
working | +0.065 |
Neg logit contributions | |
Rudolph | -0.072 |
Fl | -0.071 |
Nib | -0.069 |
Sn | -0.068 |
extingu | -0.066 |
Token | She |
Token ID | 1375 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Rudolph | +0.000 |
Fl | +0.000 |
Nib | +0.000 |
Fl | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
listener | -0.000 |
joy | -0.000 |
working | -0.000 |
itting | -0.000 |
ogs | -0.000 |
Token | wrote |
Token ID | 2630 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
joy | +0.018 |
listener | +0.018 |
itting | +0.017 |
ogs | +0.017 |
working | +0.017 |
Neg logit contributions | |
Rudolph | -0.016 |
Fl | -0.016 |
Nib | -0.015 |
Flor | -0.015 |
Sn | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Rudolph | +0.036 |
Fl | +0.035 |
Nib | +0.034 |
Sn | +0.033 |
Fl | +0.033 |
Neg logit contributions | |
listener | -0.048 |
joy | -0.047 |
working | -0.047 |
itting | -0.047 |
ogs | -0.046 |
Token | colorful |
Token ID | 20239 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
listener | +0.001 |
itting | +0.001 |
working | +0.001 |
joy | +0.001 |
ogs | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Nib | -0.001 |
Fl | -0.001 |
Sn | -0.001 |
Token | things |
Token ID | 1243 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
listener | +0.053 |
itting | +0.052 |
working | +0.050 |
joy | +0.050 |
ogs | +0.048 |
Neg logit contributions | |
Fl | -0.049 |
Rudolph | -0.049 |
Nib | -0.047 |
Fl | -0.047 |
Sn | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
listener | +0.049 |
working | +0.049 |
joy | +0.048 |
itting | +0.048 |
ogs | +0.047 |
Neg logit contributions | |
Rudolph | -0.067 |
Fl | -0.065 |
Fl | -0.065 |
Sn | -0.064 |
Nib | -0.064 |
Token | like |
Token ID | 588 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
listener | +0.062 |
itting | +0.060 |
joy | +0.060 |
ogs | +0.059 |
working | +0.059 |
Neg logit contributions | |
Rudolph | -0.054 |
Fl | -0.053 |
Nib | -0.051 |
Sn | -0.051 |
Fl | -0.050 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
listener | +0.067 |
itting | +0.065 |
working | +0.064 |
ogs | +0.063 |
joy | +0.063 |
Neg logit contributions | |
Rudolph | -0.060 |
Fl | -0.059 |
Nib | -0.056 |
Sn | -0.056 |
Fl | -0.054 |
Token | ay |
Token ID | 323 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
listener | +0.058 |
joy | +0.055 |
working | +0.053 |
ogs | +0.048 |
itting | +0.048 |
Neg logit contributions | |
Rudolph | -0.140 |
Fl | -0.137 |
Nib | -0.136 |
Fl | -0.136 |
Sn | -0.135 |
Token | ons |
Token ID | 684 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
listener | +0.205 |
runner | +0.178 |
working | +0.173 |
reader | +0.169 |
joy | +0.161 |
Neg logit contributions | |
Fl | -0.215 |
Fl | -0.211 |
Nib | -0.209 |
Rudolph | -0.201 |
Frost | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
listener | +0.086 |
joy | +0.084 |
itting | +0.082 |
ogs | +0.081 |
working | +0.080 |
Neg logit contributions | |
Rudolph | -0.089 |
Fl | -0.086 |
Nib | -0.083 |
Sn | -0.082 |
Fl | -0.080 |
Token | paint |
Token ID | 7521 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
joy | +0.042 |
listener | +0.042 |
working | +0.041 |
itting | +0.040 |
ogs | +0.040 |
Neg logit contributions | |
Rudolph | -0.052 |
Fl | -0.051 |
Fl | -0.050 |
Sn | -0.050 |
Nib | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
listener | +0.020 |
joy | +0.020 |
working | +0.020 |
itting | +0.019 |
ogs | +0.019 |
Neg logit contributions | |
Rudolph | -0.025 |
Fl | -0.024 |
Sn | -0.024 |
Fl | -0.024 |
Nib | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
listener | +0.042 |
joy | +0.041 |
working | +0.041 |
itting | +0.040 |
ogs | +0.039 |
Neg logit contributions | |
Rudolph | -0.050 |
Fl | -0.049 |
Nib | -0.048 |
Sn | -0.048 |
Fl | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
listener | +0.072 |
itting | +0.070 |
joy | +0.069 |
working | +0.068 |
ogs | +0.067 |
Neg logit contributions | |
Rudolph | -0.069 |
Fl | -0.068 |
Nib | -0.065 |
Frost | -0.064 |
Sn | -0.063 |
Token | looks |
Token ID | 3073 |
Feature activation | +6.50e-04 |
Pos logit contributions | |
working | +0.019 |
listener | +0.019 |
itting | +0.018 |
joy | +0.018 |
friends | +0.018 |
Neg logit contributions | |
Rudolph | -0.024 |
extingu | -0.023 |
Nib | -0.023 |
Sn | -0.023 |
Fl | -0.023 |
Token | like |
Token ID | 588 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
joy | +0.001 |
listener | +0.001 |
friends | +0.001 |
working | +0.001 |
itting | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
extingu | -0.001 |
Fl | -0.001 |
Sn | -0.001 |
Das | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
listener | +0.053 |
itting | +0.052 |
working | +0.052 |
joy | +0.051 |
ogs | +0.051 |
Neg logit contributions | |
Rudolph | -0.036 |
Fl | -0.035 |
Nib | -0.034 |
Sn | -0.033 |
Fl | -0.033 |
Token | cr |
Token ID | 1067 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ogs | +0.035 |
itting | +0.035 |
listener | +0.035 |
working | +0.034 |
joy | +0.034 |
Neg logit contributions | |
Rudolph | -0.041 |
Fl | -0.040 |
Nib | -0.039 |
Sn | -0.038 |
Fl | -0.038 |
Token | ay |
Token ID | 323 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
listener | +0.039 |
joy | +0.038 |
working | +0.033 |
ogs | +0.030 |
itting | +0.029 |
Neg logit contributions | |
Rudolph | -0.187 |
Fl | -0.184 |
Nib | -0.183 |
Fl | -0.182 |
Sn | -0.182 |
Token | on |
Token ID | 261 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
listener | +0.226 |
joy | +0.221 |
ogs | +0.210 |
itting | +0.206 |
runner | +0.203 |
Neg logit contributions | |
Fl | -0.181 |
Frost | -0.177 |
Fl | -0.168 |
Nib | -0.168 |
Rudolph | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
joy | +0.061 |
listener | +0.060 |
ogs | +0.058 |
itting | +0.058 |
working | +0.056 |
Neg logit contributions | |
Fl | -0.064 |
Rudolph | -0.064 |
Nib | -0.061 |
Sn | -0.060 |
Frost | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
joy | +0.017 |
listener | +0.017 |
working | +0.016 |
ogs | +0.016 |
itting | +0.016 |
Neg logit contributions | |
Rudolph | -0.018 |
Fl | -0.017 |
Sn | -0.017 |
Fl | -0.017 |
extingu | -0.017 |
Token | wants |
Token ID | 3382 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
listener | +0.013 |
joy | +0.013 |
working | +0.013 |
itting | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.018 |
Fl | -0.018 |
Sn | -0.018 |
Fl | -0.018 |
Nib | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
listener | +0.041 |
joy | +0.041 |
working | +0.040 |
friends | +0.038 |
ogs | +0.037 |
Neg logit contributions | |
Rudolph | -0.072 |
Fl | -0.072 |
Sn | -0.071 |
Fl | -0.070 |
Nib | -0.069 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Sn | +0.003 |
Fl | +0.003 |
Neg logit contributions | |
listener | -0.003 |
itting | -0.003 |
working | -0.003 |
ogs | -0.003 |
joy | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
listener | +0.045 |
working | +0.044 |
itting | +0.044 |
ogs | +0.043 |
joy | +0.042 |
Neg logit contributions | |
Fl | -0.036 |
Sn | -0.036 |
Rudolph | -0.035 |
from | -0.033 |
Nib | -0.032 |
Token | But |
Token ID | 887 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
listener | +0.012 |
joy | +0.012 |
itting | +0.011 |
friends | +0.011 |
working | +0.011 |
Neg logit contributions | |
Rudolph | -0.016 |
ified | -0.016 |
versa | -0.016 |
Tenn | -0.015 |
Nib | -0.015 |
Token | most |
Token ID | 749 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
listener | +0.005 |
working | +0.005 |
joy | +0.005 |
itting | +0.005 |
friends | +0.005 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Sn | -0.006 |
extingu | -0.006 |
Fl | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
joy | +0.120 |
ogs | +0.119 |
listener | +0.114 |
working | +0.111 |
oom | +0.111 |
Neg logit contributions | |
Fl | -0.128 |
Rudolph | -0.128 |
Fl | -0.124 |
Nib | -0.120 |
Frost | -0.120 |
Token | all |
Token ID | 477 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
working | +0.147 |
itting | +0.146 |
listener | +0.146 |
joy | +0.143 |
ogs | +0.140 |
Neg logit contributions | |
Rudolph | -0.183 |
Fl | -0.179 |
Frost | -0.171 |
Nib | -0.170 |
Sn | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
joy | +0.222 |
listener | +0.214 |
itting | +0.212 |
working | +0.193 |
ogs | +0.192 |
Neg logit contributions | |
Rudolph | -0.183 |
Fl | -0.175 |
Frost | -0.165 |
Sunny | -0.163 |
Rudy | -0.162 |
Token | they |
Token ID | 484 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
listener | +0.093 |
itting | +0.092 |
joy | +0.091 |
ogs | +0.090 |
working | +0.090 |
Neg logit contributions | |
Fl | -0.063 |
Rudolph | -0.058 |
Nib | -0.056 |
Frost | -0.056 |
Sn | -0.055 |
Token | have |
Token ID | 423 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
joy | +0.056 |
listener | +0.051 |
itting | +0.051 |
ugs | +0.051 |
ogs | +0.050 |
Neg logit contributions | |
Rudolph | -0.047 |
Nib | -0.044 |
Fl | -0.043 |
Flor | -0.042 |
Das | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
listener | +0.045 |
working | +0.044 |
itting | +0.043 |
ogs | +0.043 |
joy | +0.042 |
Neg logit contributions | |
Rudolph | -0.033 |
Fl | -0.033 |
Nib | -0.030 |
Sn | -0.029 |
Flor | -0.029 |
Token | new |
Token ID | 649 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
itting | +0.021 |
ogs | +0.021 |
working | +0.020 |
ugs | +0.019 |
ogged | +0.019 |
Neg logit contributions | |
Fl | -0.030 |
Rudolph | -0.030 |
Nib | -0.029 |
Sn | -0.028 |
Flor | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
joy | +0.027 |
listener | +0.026 |
itting | +0.025 |
rav | +0.024 |
working | +0.023 |
Neg logit contributions | |
Rudolph | -0.033 |
Fl | -0.033 |
from | -0.031 |
Nib | -0.031 |
Fl | -0.031 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
itting | +0.037 |
listener | +0.037 |
ogs | +0.035 |
working | +0.035 |
joy | +0.035 |
Neg logit contributions | |
Rudolph | -0.034 |
Fl | -0.033 |
Nib | -0.032 |
Sn | -0.031 |
Das | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
Rudolph | +0.032 |
Fl | +0.031 |
Nib | +0.030 |
Sn | +0.030 |
Fl | +0.029 |
Neg logit contributions | |
listener | -0.032 |
joy | -0.032 |
itting | -0.031 |
working | -0.030 |
ogs | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Rudolph | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Sn | +0.005 |
Fl | +0.004 |
Neg logit contributions | |
itting | -0.005 |
joy | -0.005 |
listener | -0.005 |
ogs | -0.005 |
working | -0.005 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
ogs | +0.027 |
itting | +0.027 |
listener | +0.026 |
ogged | +0.026 |
working | +0.026 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.028 |
Sn | -0.027 |
Fl | -0.027 |
Nib | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
joy | +0.043 |
listener | +0.041 |
working | +0.034 |
ogs | +0.030 |
friends | +0.028 |
Neg logit contributions | |
Rudolph | -0.150 |
extingu | -0.146 |
Sn | -0.145 |
Fl | -0.145 |
Fl | -0.144 |
Token | on |
Token ID | 261 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
listener | +0.218 |
joy | +0.211 |
itting | +0.182 |
working | +0.182 |
ogs | +0.175 |
Neg logit contributions | |
ion | -0.174 |
Rudolph | -0.173 |
Fl | -0.165 |
Fl | -0.164 |
from | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
joy | +0.065 |
listener | +0.062 |
itting | +0.059 |
ogs | +0.058 |
working | +0.056 |
Neg logit contributions | |
Rudolph | -0.057 |
Fl | -0.057 |
Sn | -0.054 |
Nib | -0.053 |
Fl | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-04 |
Pos logit contributions | |
listener | +0.016 |
joy | +0.016 |
itting | +0.016 |
working | +0.016 |
ogs | +0.016 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.011 |
extingu | -0.011 |
Fl | -0.011 |
Nib | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
listener | +0.001 |
joy | +0.001 |
itting | +0.001 |
working | +0.001 |
ogs | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Nib | -0.001 |
Sn | -0.001 |
extingu | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -1.50e-03 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.007 |
Nib | +0.007 |
extingu | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
listener | -0.008 |
itting | -0.007 |
joy | -0.007 |
working | -0.007 |
ogs | -0.007 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
itting | +0.038 |
ogs | +0.037 |
ugs | +0.035 |
listener | +0.034 |
ule | +0.034 |
Neg logit contributions | |
Fl | -0.037 |
Nib | -0.035 |
Rudolph | -0.035 |
Sn | -0.034 |
Flor | -0.033 |
Token | so |
Token ID | 523 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
listener | +0.020 |
joy | +0.020 |
working | +0.020 |
itting | +0.020 |
ogs | +0.019 |
Neg logit contributions | |
Rudolph | -0.018 |
Fl | -0.018 |
Nib | -0.017 |
Sn | -0.017 |
Fl | -0.017 |
Token | good |
Token ID | 922 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
listener | +0.018 |
itting | +0.018 |
ogs | +0.018 |
working | +0.017 |
joy | +0.017 |
Neg logit contributions | |
Fl | -0.017 |
Rudolph | -0.017 |
Flor | -0.016 |
Nib | -0.016 |
Sn | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
from | +0.011 |
Rudolph | +0.010 |
Fl | +0.010 |
Sn | +0.010 |
Nib | +0.009 |
Neg logit contributions | |
itting | -0.011 |
ogs | -0.011 |
oom | -0.011 |
listener | -0.010 |
ite | -0.010 |
Token | y |
Token ID | 331 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
working | +0.032 |
listener | +0.032 |
runner | +0.031 |
itting | +0.031 |
joy | +0.030 |
Neg logit contributions | |
Fl | -0.016 |
Sn | -0.015 |
Rudolph | -0.015 |
Fl | -0.014 |
Nib | -0.014 |
Token | ay |
Token ID | 323 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
listener | +0.071 |
joy | +0.070 |
working | +0.068 |
runner | +0.063 |
ogs | +0.061 |
Neg logit contributions | |
Fl | -0.095 |
Rudolph | -0.094 |
Nib | -0.092 |
Sn | -0.092 |
Fl | -0.092 |
Token | ! |
Token ID | 0 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
itting | +0.203 |
listener | +0.199 |
joy | +0.198 |
working | +0.195 |
ogs | +0.177 |
Neg logit contributions | |
Fl | -0.194 |
Rudolph | -0.188 |
Sn | -0.182 |
Frost | -0.175 |
Fl | -0.175 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
working | +0.062 |
listener | +0.062 |
itting | +0.059 |
joy | +0.058 |
runner | +0.058 |
Neg logit contributions | |
Fl | -0.031 |
Sn | -0.029 |
Rudolph | -0.028 |
Fl | -0.027 |
Nib | -0.027 |
Token | There |
Token ID | 1858 |
Feature activation | -8.59e-03 |
Pos logit contributions | |
listener | +0.020 |
joy | +0.020 |
working | +0.020 |
itting | +0.019 |
ogs | +0.019 |
Neg logit contributions | |
Rudolph | -0.018 |
Fl | -0.018 |
Nib | -0.017 |
Sn | -0.017 |
Fl | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Fl | +0.011 |
Rudolph | +0.010 |
Sn | +0.009 |
Nib | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
listener | -0.018 |
itting | -0.018 |
working | -0.018 |
joy | -0.017 |
ogs | -0.017 |
Token | once |
Token ID | 1752 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.018 |
Nib | +0.017 |
Sn | +0.017 |
Fl | +0.017 |
Neg logit contributions | |
listener | -0.031 |
joy | -0.030 |
working | -0.030 |
itting | -0.030 |
ogs | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
listener | +0.044 |
joy | +0.043 |
ogs | +0.042 |
working | +0.042 |
itting | +0.042 |
Neg logit contributions | |
Rudolph | -0.053 |
Fl | -0.053 |
Sn | -0.052 |
Nib | -0.051 |
Fl | -0.051 |
Token | With |
Token ID | 2080 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
listener | +0.003 |
itting | +0.003 |
working | +0.003 |
joy | +0.003 |
ogs | +0.003 |
Neg logit contributions | |
Fl | -0.002 |
Rudolph | -0.002 |
Sn | -0.002 |
Nib | -0.002 |
Flor | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
Rudolph | +0.088 |
Fl | +0.086 |
Nib | +0.083 |
Sn | +0.083 |
Fl | +0.082 |
Neg logit contributions | |
listener | -0.090 |
joy | -0.088 |
working | -0.087 |
itting | -0.087 |
ogs | -0.085 |
Token | red |
Token ID | 2266 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
ogs | +0.023 |
working | +0.023 |
itting | +0.022 |
listener | +0.022 |
ogged | +0.021 |
Neg logit contributions | |
Fl | -0.021 |
Rudolph | -0.020 |
Fl | -0.019 |
Sn | -0.019 |
extingu | -0.019 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
listener | +0.132 |
ogs | +0.128 |
working | +0.126 |
joy | +0.125 |
itting | +0.120 |
Neg logit contributions | |
extingu | -0.101 |
Fl | -0.100 |
Nib | -0.094 |
Sn | -0.092 |
Fl | -0.092 |
Token | ay |
Token ID | 323 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
joy | +0.046 |
listener | +0.045 |
working | +0.041 |
runner | +0.034 |
ogs | +0.034 |
Neg logit contributions | |
extingu | -0.132 |
Fl | -0.131 |
Rudolph | -0.131 |
Fl | -0.130 |
Nib | -0.130 |
Token | on |
Token ID | 261 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
joy | +0.225 |
listener | +0.218 |
working | +0.201 |
runner | +0.199 |
neighborhood | +0.186 |
Neg logit contributions | |
ion | -0.157 |
Fl | -0.145 |
from | -0.145 |
Fl | -0.144 |
extingu | -0.139 |
Token | she |
Token ID | 673 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
joy | +0.063 |
listener | +0.060 |
working | +0.056 |
itting | +0.055 |
ogs | +0.055 |
Neg logit contributions | |
Fl | -0.046 |
from | -0.046 |
Nib | -0.042 |
Rudolph | -0.042 |
extingu | -0.042 |
Token | carefully |
Token ID | 7773 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
ogs | +0.058 |
listener | +0.055 |
joy | +0.054 |
itting | +0.054 |
runner | +0.052 |
Neg logit contributions | |
Fl | -0.030 |
Flor | -0.028 |
Fl | -0.027 |
Sn | -0.027 |
called | -0.026 |
Token | drew |
Token ID | 9859 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Fl | +0.012 |
Nib | +0.012 |
extingu | +0.012 |
from | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
listener | -0.016 |
ogs | -0.016 |
itting | -0.015 |
ule | -0.015 |
joy | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
listener | +0.039 |
working | +0.037 |
joy | +0.035 |
itting | +0.035 |
ogs | +0.035 |
Neg logit contributions | |
Fl | -0.021 |
from | -0.020 |
Flor | -0.019 |
Nib | -0.019 |
Rudolph | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
joy | +0.003 |
listener | +0.002 |
itting | +0.002 |
working | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.001 |
Nib | -0.001 |
Fl | -0.001 |
Flor | -0.001 |
Frost | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Rudolph | +0.006 |
Fl | +0.006 |
Sn | +0.006 |
Fl | +0.006 |
extingu | +0.006 |
Neg logit contributions | |
listener | -0.007 |
working | -0.007 |
joy | -0.007 |
friends | -0.007 |
itting | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
listener | +0.016 |
joy | +0.016 |
itting | +0.016 |
ogs | +0.016 |
working | +0.016 |
Neg logit contributions | |
Rudolph | -0.016 |
Fl | -0.016 |
Nib | -0.015 |
Sn | -0.015 |
Fl | -0.015 |
Token | special |
Token ID | 2041 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
listener | +0.022 |
joy | +0.022 |
itting | +0.022 |
working | +0.022 |
ogs | +0.021 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.028 |
Nib | -0.027 |
Sn | -0.027 |
Fl | -0.027 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
itting | +0.022 |
ogs | +0.022 |
working | +0.022 |
listener | +0.022 |
joy | +0.022 |
Neg logit contributions | |
Rudolph | -0.031 |
Fl | -0.031 |
Nib | -0.030 |
Sn | -0.030 |
extingu | -0.029 |
Token | ay |
Token ID | 323 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
joy | +0.043 |
listener | +0.041 |
working | +0.035 |
ogs | +0.032 |
runner | +0.029 |
Neg logit contributions | |
Rudolph | -0.166 |
extingu | -0.165 |
Sn | -0.163 |
Fl | -0.163 |
Nib | -0.163 |
Token | on |
Token ID | 261 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
joy | +0.193 |
listener | +0.188 |
ogs | +0.175 |
itting | +0.170 |
working | +0.163 |
Neg logit contributions | |
from | -0.189 |
extingu | -0.189 |
Fl | -0.181 |
Rudolph | -0.178 |
Sn | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
joy | +0.061 |
listener | +0.058 |
ogs | +0.056 |
itting | +0.056 |
working | +0.054 |
Neg logit contributions | |
Fl | -0.054 |
Rudolph | -0.054 |
Nib | -0.051 |
Sn | -0.050 |
extingu | -0.050 |
Token | but |
Token ID | 475 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
listener | +0.069 |
working | +0.068 |
joy | +0.067 |
itting | +0.067 |
ogs | +0.066 |
Neg logit contributions | |
Rudolph | -0.045 |
Fl | -0.045 |
Nib | -0.043 |
Sn | -0.042 |
Fl | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
listener | +0.020 |
joy | +0.019 |
working | +0.019 |
itting | +0.019 |
ogs | +0.019 |
Neg logit contributions | |
Rudolph | -0.021 |
Fl | -0.021 |
Nib | -0.020 |
Sn | -0.020 |
Fl | -0.020 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
listener | +0.054 |
ogs | +0.054 |
itting | +0.054 |
working | +0.054 |
joy | +0.053 |
Neg logit contributions | |
Rudolph | -0.068 |
Fl | -0.068 |
Nib | -0.066 |
Sn | -0.065 |
Fl | -0.065 |
Token | on |
Token ID | 261 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
joy | +0.181 |
listener | +0.178 |
runner | +0.162 |
ogs | +0.157 |
working | +0.156 |
Neg logit contributions | |
Fl | -0.162 |
Fl | -0.158 |
Nib | -0.157 |
Frost | -0.155 |
extingu | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -8.89e-04 |
Pos logit contributions | |
joy | +0.043 |
listener | +0.042 |
ogs | +0.039 |
itting | +0.039 |
working | +0.039 |
Neg logit contributions | |
Fl | -0.040 |
Rudolph | -0.039 |
Nib | -0.038 |
Sn | -0.037 |
extingu | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Rudolph | +0.001 |
Fl | +0.001 |
Nib | +0.001 |
Sn | +0.001 |
Frost | +0.001 |
Neg logit contributions | |
listener | -0.002 |
itting | -0.002 |
joy | -0.002 |
ogs | -0.002 |
working | -0.002 |
Token | black |
Token ID | 2042 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
ogs | +0.037 |
listener | +0.035 |
itting | +0.035 |
ogged | +0.035 |
working | +0.034 |
Neg logit contributions | |
Fl | -0.033 |
Rudolph | -0.033 |
Nib | -0.031 |
Sn | -0.031 |
Fl | -0.031 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
listener | +0.105 |
itting | +0.102 |
ogs | +0.102 |
working | +0.099 |
joy | +0.099 |
Neg logit contributions | |
extingu | -0.097 |
Fl | -0.097 |
Rudolph | -0.096 |
Nib | -0.092 |
Frost | -0.091 |
Token | ay |
Token ID | 323 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
listener | +0.027 |
joy | +0.026 |
working | +0.023 |
ogs | +0.020 |
itting | +0.019 |
Neg logit contributions | |
Rudolph | -0.156 |
Fl | -0.154 |
Nib | -0.153 |
Sn | -0.152 |
Fl | -0.152 |
Token | on |
Token ID | 261 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
joy | +0.205 |
listener | +0.201 |
ogs | +0.191 |
runner | +0.179 |
itting | +0.178 |
Neg logit contributions | |
Fl | -0.185 |
Frost | -0.177 |
Fl | -0.175 |
Nib | -0.172 |
extingu | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
joy | +0.061 |
listener | +0.058 |
ogs | +0.055 |
itting | +0.054 |
working | +0.053 |
Neg logit contributions | |
Fl | -0.054 |
Nib | -0.051 |
Rudolph | -0.051 |
extingu | -0.050 |
Sn | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
listener | +0.006 |
working | +0.006 |
itting | +0.006 |
joy | +0.006 |
ogs | +0.005 |
Neg logit contributions | |
Fl | -0.004 |
Rudolph | -0.003 |
Nib | -0.003 |
Frost | -0.003 |
Sn | -0.003 |
Token | makes |
Token ID | 1838 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
listener | +0.010 |
joy | +0.010 |
itting | +0.010 |
working | +0.010 |
ogs | +0.010 |
Neg logit contributions | |
Rudolph | -0.010 |
Fl | -0.009 |
Nib | -0.009 |
Sn | -0.009 |
Fl | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.008 |
Nib | +0.008 |
Frost | +0.008 |
Sn | +0.007 |
Neg logit contributions | |
listener | -0.017 |
itting | -0.017 |
joy | -0.016 |
working | -0.016 |
ogs | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
joy | +0.026 |
listener | +0.026 |
working | +0.025 |
itting | +0.024 |
ogs | +0.023 |
Neg logit contributions | |
Fl | -0.047 |
Rudolph | -0.047 |
Nib | -0.045 |
Fl | -0.045 |
Sn | -0.045 |
Token | wood |
Token ID | 4898 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
listener | +0.039 |
itting | +0.039 |
joy | +0.039 |
working | +0.037 |
ogs | +0.037 |
Neg logit contributions | |
Rudolph | -0.035 |
Fl | -0.034 |
Nib | -0.033 |
Sn | -0.033 |
Das | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
listener | +0.005 |
working | +0.005 |
joy | +0.005 |
itting | +0.004 |
ogs | +0.004 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.007 |
Fl | -0.007 |
Sn | -0.006 |
Nib | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Rudolph | +0.012 |
Fl | +0.012 |
Nib | +0.011 |
Sn | +0.011 |
Fl | +0.011 |
Neg logit contributions | |
listener | -0.012 |
joy | -0.012 |
working | -0.012 |
itting | -0.012 |
ogs | -0.012 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
ogs | +0.026 |
listener | +0.026 |
itting | +0.025 |
working | +0.025 |
joy | +0.025 |
Neg logit contributions | |
Rudolph | -0.027 |
Fl | -0.026 |
Nib | -0.026 |
Sn | -0.025 |
Fl | -0.025 |
Token | ay |
Token ID | 323 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
joy | +0.041 |
listener | +0.039 |
working | +0.033 |
ogs | +0.029 |
runner | +0.027 |
Neg logit contributions | |
Rudolph | -0.151 |
extingu | -0.150 |
Fl | -0.148 |
Fl | -0.148 |
Nib | -0.148 |
Token | on |
Token ID | 261 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
listener | +0.185 |
joy | +0.184 |
itting | +0.163 |
ogs | +0.161 |
working | +0.161 |
Neg logit contributions | |
Fl | -0.205 |
Fl | -0.203 |
Rudolph | -0.201 |
extingu | -0.200 |
Frost | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
joy | +0.052 |
listener | +0.051 |
itting | +0.049 |
working | +0.049 |
ogs | +0.048 |
Neg logit contributions | |
Fl | -0.055 |
Rudolph | -0.055 |
Nib | -0.054 |
Sn | -0.053 |
extingu | -0.052 |
Token | She |
Token ID | 1375 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
listener | +0.010 |
working | +0.010 |
joy | +0.010 |
itting | +0.010 |
ogs | +0.010 |
Neg logit contributions | |
Fl | -0.009 |
Rudolph | -0.009 |
Nib | -0.009 |
Sn | -0.009 |
Fl | -0.009 |
Token | wrote |
Token ID | 2630 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
listener | +0.027 |
joy | +0.027 |
itting | +0.026 |
working | +0.026 |
ogs | +0.026 |
Neg logit contributions | |
Rudolph | -0.027 |
Fl | -0.026 |
Sn | -0.025 |
Nib | -0.025 |
Fl | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Rudolph | +0.035 |
Fl | +0.034 |
Nib | +0.033 |
Sn | +0.032 |
Fl | +0.032 |
Neg logit contributions | |
listener | -0.042 |
working | -0.041 |
joy | -0.040 |
itting | -0.040 |
ogs | -0.040 |
Token | amazing |
Token ID | 4998 |
Feature activation | +1.38e-04 |
Pos logit contributions | |
Rudolph | +0.071 |
Fl | +0.067 |
Sn | +0.067 |
Fl | +0.067 |
Nib | +0.067 |
Neg logit contributions | |
listener | -0.068 |
joy | -0.068 |
working | -0.067 |
itting | -0.067 |
ogs | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
listener | +0.000 |
joy | +0.000 |
working | +0.000 |
itting | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Nib | -0.000 |
Sn | -0.000 |
Fl | -0.000 |
Token | A |
Token ID | 317 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
Rudolph | +0.004 |
Fl | +0.004 |
Fl | +0.004 |
Sn | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
working | -0.004 |
ogs | -0.004 |
Token | real |
Token ID | 1103 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Rudolph | +0.009 |
Fl | +0.009 |
Sn | +0.008 |
Nib | +0.008 |
Fl | +0.008 |
Neg logit contributions | |
listener | -0.007 |
itting | -0.007 |
ogs | -0.007 |
working | -0.007 |
joy | -0.007 |
Token | aer |
Token ID | 9551 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
ogs | +0.040 |
itting | +0.040 |
listener | +0.039 |
joy | +0.038 |
working | +0.038 |
Neg logit contributions | |
Fl | -0.038 |
Rudolph | -0.038 |
Nib | -0.036 |
Sn | -0.035 |
Flor | -0.035 |
Token | opl |
Token ID | 20106 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
listener | +0.106 |
joy | +0.099 |
itting | +0.094 |
runner | +0.091 |
ogs | +0.089 |
Neg logit contributions | |
Fl | -0.132 |
Nib | -0.128 |
Rudolph | -0.125 |
Fl | -0.125 |
ified | -0.123 |
Token | ane |
Token ID | 1531 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
listener | +0.139 |
joy | +0.130 |
working | +0.114 |
friends | +0.113 |
ogs | +0.113 |
Neg logit contributions | |
extingu | -0.220 |
ified | -0.219 |
fly | -0.215 |
Frost | -0.214 |
from | -0.214 |
Token | was |
Token ID | 373 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
listener | +0.045 |
joy | +0.044 |
ogs | +0.042 |
itting | +0.042 |
working | +0.041 |
Neg logit contributions | |
Fl | -0.040 |
Rudolph | -0.040 |
Sn | -0.038 |
Fl | -0.038 |
Nib | -0.038 |
Token | flying |
Token ID | 7348 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
listener | +0.013 |
joy | +0.013 |
working | +0.012 |
itting | +0.012 |
ogs | +0.012 |
Neg logit contributions | |
Rudolph | -0.014 |
Fl | -0.013 |
Fl | -0.013 |
Nib | -0.013 |
Sn | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
listener | +0.037 |
joy | +0.036 |
working | +0.036 |
itting | +0.035 |
ogs | +0.035 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.028 |
Sn | -0.027 |
Fl | -0.027 |
Nib | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Rudolph | +0.039 |
Fl | +0.037 |
Nib | +0.037 |
Sn | +0.036 |
Fl | +0.036 |
Neg logit contributions | |
joy | -0.039 |
listener | -0.037 |
working | -0.036 |
friends | -0.035 |
itting | -0.035 |
Token | toys |
Token ID | 14958 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Rudolph | +0.001 |
Fl | +0.001 |
Nib | +0.001 |
Sn | +0.001 |
Fl | +0.001 |
Neg logit contributions | |
listener | -0.001 |
joy | -0.001 |
working | -0.001 |
itting | -0.001 |
ogs | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
listener | +0.038 |
joy | +0.037 |
itting | +0.036 |
working | +0.036 |
ogs | +0.035 |
Neg logit contributions | |
Rudolph | -0.037 |
Fl | -0.036 |
Nib | -0.035 |
Sn | -0.035 |
Fl | -0.034 |
Token | puzzles |
Token ID | 24367 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
listener | +0.003 |
itting | +0.003 |
joy | +0.003 |
working | +0.003 |
ogs | +0.003 |
Neg logit contributions | |
Rudolph | -0.004 |
Fl | -0.004 |
Nib | -0.003 |
Sn | -0.003 |
Fl | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
listener | +0.005 |
joy | +0.005 |
itting | +0.005 |
working | +0.004 |
ogs | +0.004 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Nib | -0.005 |
Sn | -0.005 |
Fl | -0.005 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
listener | +0.015 |
joy | +0.015 |
itting | +0.015 |
working | +0.015 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.018 |
Fl | -0.017 |
Nib | -0.017 |
Sn | -0.017 |
Fl | -0.017 |
Token | ay |
Token ID | 323 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
listener | +0.052 |
joy | +0.051 |
working | +0.047 |
itting | +0.042 |
runner | +0.042 |
Neg logit contributions | |
Rudolph | -0.117 |
Fl | -0.114 |
Nib | -0.113 |
Sn | -0.112 |
Fl | -0.112 |
Token | ons |
Token ID | 684 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
listener | +0.192 |
runner | +0.176 |
joy | +0.171 |
working | +0.155 |
itting | +0.155 |
Neg logit contributions | |
Fl | -0.208 |
Fl | -0.207 |
ion | -0.206 |
Rudolph | -0.204 |
Nib | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
listener | +0.077 |
joy | +0.075 |
itting | +0.073 |
ogs | +0.070 |
working | +0.070 |
Neg logit contributions | |
Rudolph | -0.075 |
Fl | -0.072 |
Nib | -0.070 |
Frost | -0.069 |
Sn | -0.068 |
Token | There |
Token ID | 1318 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
listener | +0.013 |
joy | +0.013 |
itting | +0.013 |
working | +0.013 |
ogs | +0.012 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.011 |
Fl | -0.011 |
Sn | -0.011 |
Nib | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Fl | +0.016 |
Rudolph | +0.016 |
Nib | +0.015 |
Frost | +0.015 |
Sunny | +0.015 |
Neg logit contributions | |
joy | -0.022 |
listener | -0.021 |
itting | -0.020 |
working | -0.020 |
runner | -0.019 |
Token | hats |
Token ID | 23910 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
Rudolph | +0.019 |
Fl | +0.019 |
Nib | +0.018 |
Sn | +0.018 |
Fl | +0.018 |
Neg logit contributions | |
listener | -0.017 |
joy | -0.017 |
working | -0.017 |
itting | -0.016 |
ogs | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
listener | +0.111 |
working | +0.099 |
joy | +0.099 |
itting | +0.099 |
runner | +0.098 |
Neg logit contributions | |
Nib | -0.089 |
extingu | -0.086 |
Flor | -0.086 |
Fl | -0.085 |
Rudolph | -0.084 |
Token | green |
Token ID | 4077 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
listener | +0.040 |
joy | +0.040 |
working | +0.039 |
itting | +0.039 |
ogs | +0.038 |
Neg logit contributions | |
Rudolph | -0.055 |
Fl | -0.053 |
Sn | -0.052 |
Nib | -0.052 |
Fl | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
listener | +0.080 |
itting | +0.076 |
joy | +0.073 |
ogs | +0.073 |
working | +0.072 |
Neg logit contributions | |
Nib | -0.067 |
Fl | -0.066 |
Flor | -0.064 |
Rudolph | -0.064 |
extingu | -0.062 |
Token | red |
Token ID | 2266 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
listener | +0.019 |
working | +0.019 |
joy | +0.019 |
itting | +0.018 |
ogs | +0.017 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.028 |
Sn | -0.027 |
Fl | -0.027 |
Nib | -0.027 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
listener | +0.113 |
itting | +0.106 |
joy | +0.103 |
ogs | +0.102 |
working | +0.102 |
Neg logit contributions | |
Nib | -0.093 |
Fl | -0.090 |
extingu | -0.089 |
Flor | -0.088 |
Rudolph | -0.087 |
Token | ay |
Token ID | 323 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
listener | +0.023 |
joy | +0.021 |
working | +0.020 |
itting | +0.017 |
ogs | +0.017 |
Neg logit contributions | |
Rudolph | -0.143 |
Fl | -0.141 |
Nib | -0.140 |
Sn | -0.139 |
Fl | -0.138 |
Token | ons |
Token ID | 684 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
listener | +0.177 |
joy | +0.158 |
runner | +0.156 |
working | +0.145 |
kicker | +0.144 |
Neg logit contributions | |
Nib | -0.206 |
Fl | -0.203 |
Frost | -0.202 |
extingu | -0.201 |
Rudolph | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
listener | +0.077 |
joy | +0.077 |
itting | +0.073 |
ogs | +0.072 |
working | +0.072 |
Neg logit contributions | |
Rudolph | -0.079 |
Fl | -0.079 |
Nib | -0.077 |
Sn | -0.074 |
Frost | -0.074 |
Token | They |
Token ID | 1119 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
listener | +0.015 |
working | +0.015 |
joy | +0.014 |
itting | +0.014 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.008 |
Fl | -0.008 |
Nib | -0.007 |
Sn | -0.007 |
Frost | -0.007 |
Token | are |
Token ID | 389 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
joy | +0.008 |
listener | +0.007 |
ogs | +0.007 |
itting | +0.007 |
ule | +0.007 |
Neg logit contributions | |
Rudolph | -0.006 |
Flor | -0.006 |
Nib | -0.006 |
Fl | -0.006 |
Frost | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.018 |
Nib | +0.018 |
Flor | +0.017 |
Frost | +0.017 |
Neg logit contributions | |
ogs | -0.021 |
itting | -0.021 |
listener | -0.021 |
joy | -0.021 |
working | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
Rudolph | +0.016 |
Fl | +0.016 |
Sn | +0.015 |
Nib | +0.015 |
Fl | +0.015 |
Neg logit contributions | |
listener | -0.012 |
itting | -0.012 |
working | -0.012 |
joy | -0.012 |
ogs | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
listener | +0.014 |
working | +0.014 |
joy | +0.014 |
itting | +0.014 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.015 |
Fl | -0.015 |
Nib | -0.015 |
Sn | -0.015 |
Fl | -0.014 |
Token | dreamed |
Token ID | 27947 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
listener | +0.026 |
joy | +0.026 |
itting | +0.025 |
working | +0.025 |
ogs | +0.025 |
Neg logit contributions | |
Rudolph | -0.028 |
Fl | -0.027 |
Nib | -0.026 |
Sn | -0.026 |
Fl | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
working | +0.086 |
listener | +0.086 |
joy | +0.083 |
itting | +0.083 |
oom | +0.082 |
Neg logit contributions | |
Fl | -0.081 |
Rudolph | -0.078 |
Nib | -0.075 |
Flor | -0.074 |
from | -0.074 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
itting | +0.071 |
listener | +0.071 |
working | +0.070 |
ogs | +0.069 |
oom | +0.067 |
Neg logit contributions | |
Fl | -0.062 |
Rudolph | -0.060 |
Nib | -0.059 |
Sn | -0.057 |
Flor | -0.057 |
Token | ay |
Token ID | 323 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
listener | +0.042 |
joy | +0.041 |
working | +0.037 |
runner | +0.033 |
ogs | +0.029 |
Neg logit contributions | |
Rudolph | -0.136 |
extingu | -0.133 |
Fl | -0.133 |
Fl | -0.133 |
Sn | -0.133 |
Token | ons |
Token ID | 684 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
listener | +0.208 |
runner | +0.193 |
joy | +0.191 |
itting | +0.175 |
working | +0.173 |
Neg logit contributions | |
Fl | -0.179 |
Fl | -0.178 |
Frost | -0.175 |
Rudolph | -0.170 |
Nib | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
joy | +0.089 |
listener | +0.086 |
itting | +0.083 |
working | +0.083 |
ogs | +0.081 |
Neg logit contributions | |
Fl | -0.070 |
Rudolph | -0.068 |
Sunny | -0.065 |
from | -0.064 |
Nib | -0.063 |
Token | colors |
Token ID | 7577 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
itting | +0.006 |
listener | +0.006 |
joy | +0.006 |
ogs | +0.006 |
oom | +0.006 |
Neg logit contributions | |
Fl | -0.007 |
Rudolph | -0.006 |
Nib | -0.006 |
Flor | -0.006 |
Sn | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-03 |
Pos logit contributions | |
listener | +0.108 |
joy | +0.107 |
working | +0.102 |
ogs | +0.101 |
itting | +0.101 |
Neg logit contributions | |
Fl | -0.098 |
Rudolph | -0.098 |
Nib | -0.093 |
Sn | -0.092 |
Fl | -0.090 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
listener | +0.006 |
working | +0.006 |
joy | +0.006 |
itting | +0.006 |
ogs | +0.006 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.007 |
Nib | -0.007 |
Sn | -0.007 |
Fl | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
joy | +0.033 |
listener | +0.032 |
working | +0.030 |
itting | +0.030 |
ogs | +0.028 |
Neg logit contributions | |
Fl | -0.050 |
Rudolph | -0.050 |
Nib | -0.048 |
Fl | -0.047 |
Frost | -0.046 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
listener | +0.049 |
joy | +0.048 |
working | +0.048 |
itting | +0.048 |
ogs | +0.047 |
Neg logit contributions | |
Rudolph | -0.044 |
Fl | -0.043 |
Nib | -0.042 |
Sn | -0.041 |
Fl | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
Rudolph | +0.028 |
Fl | +0.027 |
Nib | +0.027 |
Sn | +0.027 |
Fl | +0.027 |
Neg logit contributions | |
listener | -0.023 |
joy | -0.023 |
working | -0.022 |
itting | -0.022 |
ogs | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Rudolph | +0.007 |
Fl | +0.007 |
Sn | +0.007 |
Fl | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
listener | -0.007 |
working | -0.007 |
joy | -0.007 |
itting | -0.006 |
ogs | -0.006 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
listener | +0.028 |
itting | +0.028 |
ogs | +0.028 |
working | +0.028 |
joy | +0.027 |
Neg logit contributions | |
Rudolph | -0.029 |
Fl | -0.028 |
Nib | -0.027 |
Fl | -0.027 |
Sn | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
listener | +0.036 |
joy | +0.035 |
working | +0.033 |
itting | +0.029 |
ogs | +0.028 |
Neg logit contributions | |
Rudolph | -0.155 |
Fl | -0.152 |
Fl | -0.151 |
Nib | -0.150 |
Sn | -0.150 |
Token | on |
Token ID | 261 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
listener | +0.173 |
joy | +0.173 |
itting | +0.159 |
working | +0.155 |
ogs | +0.143 |
Neg logit contributions | |
Rudolph | -0.218 |
Fl | -0.216 |
Fl | -0.213 |
Frost | -0.207 |
Nib | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
joy | +0.056 |
listener | +0.055 |
itting | +0.052 |
working | +0.051 |
ogs | +0.050 |
Neg logit contributions | |
Rudolph | -0.058 |
Fl | -0.057 |
Nib | -0.055 |
Sn | -0.054 |
Frost | -0.053 |
Token | They |
Token ID | 1119 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
joy | +0.006 |
ogs | +0.006 |
listener | +0.006 |
itting | +0.006 |
friends | +0.006 |
Neg logit contributions | |
extingu | -0.007 |
Rudolph | -0.007 |
mant | -0.007 |
ified | -0.007 |
Fl | -0.007 |
Token | write |
Token ID | 3551 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Rudolph | +0.004 |
Fl | +0.004 |
Nib | +0.004 |
Sn | +0.004 |
Frost | +0.004 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
ogs | -0.004 |
working | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Rudolph | +0.033 |
Fl | +0.032 |
Sn | +0.031 |
Fl | +0.031 |
Nib | +0.031 |
Neg logit contributions | |
listener | -0.039 |
joy | -0.039 |
working | -0.038 |
itting | -0.038 |
ogs | -0.037 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
Rudolph | +0.004 |
extingu | +0.004 |
Nib | +0.004 |
Fl | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
ogs | -0.004 |
working | -0.004 |
Token | has |
Token ID | 468 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
joy | +0.052 |
listener | +0.052 |
itting | +0.051 |
working | +0.050 |
ogs | +0.049 |
Neg logit contributions | |
Rudolph | -0.062 |
Fl | -0.061 |
Nib | -0.059 |
Sn | -0.058 |
Fl | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Nib | +0.002 |
Sn | +0.002 |
Das | +0.002 |
Neg logit contributions | |
listener | -0.005 |
itting | -0.005 |
ogs | -0.005 |
joy | -0.005 |
working | -0.005 |
Token | red |
Token ID | 2266 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
ogs | +0.022 |
ogged | +0.021 |
itting | +0.021 |
listener | +0.020 |
working | +0.020 |
Neg logit contributions | |
Rudolph | -0.021 |
Fl | -0.020 |
Nib | -0.020 |
Sn | -0.018 |
Flor | -0.018 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
listener | +0.136 |
joy | +0.131 |
ogs | +0.130 |
itting | +0.130 |
working | +0.127 |
Neg logit contributions | |
Nib | -0.128 |
Fl | -0.128 |
extingu | -0.123 |
Rudolph | -0.123 |
Sn | -0.122 |
Token | ay |
Token ID | 323 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
joy | +0.036 |
listener | +0.035 |
working | +0.030 |
ogs | +0.027 |
runner | +0.025 |
Neg logit contributions | |
Rudolph | -0.145 |
Fl | -0.142 |
Nib | -0.142 |
Fl | -0.142 |
Sn | -0.142 |
Token | on |
Token ID | 261 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
listener | +0.199 |
joy | +0.198 |
runner | +0.179 |
ogs | +0.175 |
working | +0.172 |
Neg logit contributions | |
Nib | -0.175 |
Fl | -0.175 |
Fl | -0.174 |
extingu | -0.171 |
Rudolph | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
joy | +0.060 |
listener | +0.059 |
itting | +0.056 |
ogs | +0.056 |
working | +0.055 |
Neg logit contributions | |
Rudolph | -0.062 |
Fl | -0.061 |
Nib | -0.060 |
Sn | -0.059 |
Fl | -0.058 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
listener | +0.023 |
itting | +0.023 |
joy | +0.023 |
ogs | +0.022 |
working | +0.022 |
Neg logit contributions | |
Rudolph | -0.015 |
Fl | -0.014 |
Nib | -0.014 |
Sn | -0.013 |
Fl | -0.013 |
Token | has |
Token ID | 468 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
joy | +0.033 |
listener | +0.032 |
ogs | +0.032 |
itting | +0.032 |
runner | +0.029 |
Neg logit contributions | |
Fl | -0.022 |
Rudolph | -0.022 |
Sn | -0.021 |
Nib | -0.021 |
Fl | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Rudolph | +0.010 |
Fl | +0.010 |
Nib | +0.009 |
Sn | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
listener | -0.017 |
itting | -0.016 |
ogs | -0.016 |
joy | -0.016 |
working | -0.016 |
Token | when |
Token ID | 618 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
Rudolph | +0.013 |
Fl | +0.013 |
Sn | +0.013 |
Nib | +0.013 |
Fl | +0.012 |
Neg logit contributions | |
listener | -0.012 |
joy | -0.012 |
working | -0.012 |
itting | -0.012 |
ogs | -0.012 |
Token | flying |
Token ID | 7348 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
listener | +0.011 |
itting | +0.011 |
joy | +0.010 |
udding | +0.010 |
working | +0.010 |
Neg logit contributions | |
Fl | -0.007 |
Rudolph | -0.007 |
Sn | -0.006 |
Sunny | -0.006 |
Rudy | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
listener | +0.068 |
joy | +0.067 |
itting | +0.065 |
working | +0.065 |
ogs | +0.063 |
Neg logit contributions | |
Rudolph | -0.061 |
Fl | -0.059 |
Sn | -0.057 |
Fl | -0.057 |
Nib | -0.057 |
Token | an |
Token ID | 281 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
Rudolph | +0.005 |
Nib | +0.005 |
Fl | +0.005 |
Fl | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
joy | -0.005 |
listener | -0.005 |
working | -0.005 |
ogs | -0.005 |
itting | -0.005 |
Token | aer |
Token ID | 9551 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
listener | +0.014 |
joy | +0.014 |
itting | +0.013 |
working | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.017 |
Fl | -0.016 |
Nib | -0.016 |
Sn | -0.016 |
Fl | -0.016 |
Token | opl |
Token ID | 20106 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
listener | +0.089 |
joy | +0.081 |
working | +0.079 |
itting | +0.078 |
runner | +0.078 |
Neg logit contributions | |
Fl | -0.131 |
Fl | -0.127 |
Rudolph | -0.127 |
Nib | -0.126 |
Das | -0.124 |
Token | ane |
Token ID | 1531 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
listener | +0.142 |
joy | +0.138 |
friends | +0.119 |
ies | +0.117 |
working | +0.116 |
Neg logit contributions | |
ified | -0.202 |
Rudolph | -0.201 |
Nib | -0.199 |
from | -0.199 |
Sn | -0.197 |
Token | ." |
Token ID | 526 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
joy | +0.016 |
listener | +0.016 |
itting | +0.015 |
working | +0.014 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.012 |
Sn | -0.011 |
Fl | -0.011 |
Nib | -0.011 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Fl | +0.009 |
Fl | +0.008 |
Nib | +0.008 |
Flor | +0.008 |
Rudolph | +0.008 |
Neg logit contributions | |
working | -0.013 |
listener | -0.012 |
itting | -0.012 |
joy | -0.012 |
runner | -0.012 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
joy | +0.027 |
listener | +0.026 |
working | +0.026 |
itting | +0.026 |
ogs | +0.025 |
Neg logit contributions | |
Fl | -0.026 |
Rudolph | -0.025 |
Fl | -0.025 |
Sn | -0.024 |
Nib | -0.024 |
Token | 't |
Token ID | 470 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
working | +0.005 |
ogs | +0.005 |
oom | +0.005 |
ay | +0.005 |
itting | +0.005 |
Neg logit contributions | |
Rudolph | -0.007 |
Nib | -0.007 |
Flor | -0.007 |
extingu | -0.007 |
Fl | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
joy | +0.038 |
friends | +0.037 |
working | +0.036 |
listener | +0.036 |
itting | +0.034 |
Neg logit contributions | |
Rudolph | -0.045 |
Fl | -0.045 |
Sn | -0.044 |
versa | -0.043 |
Fl | -0.043 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
listener | +0.031 |
itting | +0.030 |
working | +0.030 |
joy | +0.030 |
ogs | +0.029 |
Neg logit contributions | |
Rudolph | -0.038 |
Fl | -0.037 |
Sn | -0.036 |
Nib | -0.036 |
Fl | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
Rudolph | +0.027 |
Fl | +0.026 |
Nib | +0.026 |
Sn | +0.026 |
Fl | +0.026 |
Neg logit contributions | |
listener | -0.023 |
joy | -0.022 |
working | -0.022 |
itting | -0.022 |
ogs | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
joy | +0.039 |
working | +0.037 |
listener | +0.037 |
friends | +0.036 |
itting | +0.035 |
Neg logit contributions | |
Rudolph | -0.064 |
Fl | -0.062 |
Sn | -0.061 |
Fl | -0.061 |
Nib | -0.060 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
listener | +0.035 |
itting | +0.034 |
working | +0.034 |
ogs | +0.034 |
joy | +0.034 |
Neg logit contributions | |
Rudolph | -0.041 |
Fl | -0.040 |
Sn | -0.038 |
Nib | -0.038 |
Fl | -0.038 |
Token | ay |
Token ID | 323 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
listener | +0.022 |
joy | +0.021 |
working | +0.019 |
itting | +0.017 |
ogs | +0.016 |
Neg logit contributions | |
Rudolph | -0.160 |
Fl | -0.157 |
Sn | -0.155 |
Nib | -0.155 |
Fl | -0.155 |
Token | on |
Token ID | 261 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
listener | +0.172 |
joy | +0.163 |
itting | +0.155 |
ogs | +0.149 |
working | +0.148 |
Neg logit contributions | |
Fl | -0.214 |
Rudolph | -0.214 |
extingu | -0.208 |
Fl | -0.206 |
Frost | -0.205 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
listener | +0.055 |
joy | +0.055 |
itting | +0.053 |
working | +0.052 |
ogs | +0.052 |
Neg logit contributions | |
Rudolph | -0.060 |
Fl | -0.059 |
Nib | -0.058 |
Sn | -0.057 |
Fl | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
joy | +0.041 |
working | +0.041 |
listener | +0.040 |
friends | +0.039 |
itting | +0.038 |
Neg logit contributions | |
Rudolph | -0.072 |
Fl | -0.070 |
Sn | -0.069 |
Fl | -0.069 |
Nib | -0.068 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
listener | +0.040 |
itting | +0.039 |
ogs | +0.039 |
working | +0.038 |
joy | +0.038 |
Neg logit contributions | |
Rudolph | -0.045 |
Fl | -0.044 |
Sn | -0.043 |
Nib | -0.042 |
Fl | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
listener | +0.040 |
joy | +0.039 |
itting | +0.039 |
working | +0.038 |
ogs | +0.037 |
Neg logit contributions | |
Rudolph | -0.042 |
Fl | -0.042 |
Nib | -0.040 |
Sn | -0.040 |
Fl | -0.039 |
Token | yellow |
Token ID | 7872 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
Rudolph | +0.021 |
Nib | +0.020 |
Fl | +0.020 |
Sn | +0.020 |
Fl | +0.019 |
Neg logit contributions | |
listener | -0.015 |
working | -0.015 |
joy | -0.015 |
itting | -0.014 |
friends | -0.014 |
Token | flower |
Token ID | 15061 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ogs | +0.086 |
joy | +0.085 |
itting | +0.083 |
working | +0.082 |
listener | +0.082 |
Neg logit contributions | |
Fl | -0.072 |
Frost | -0.068 |
Rudolph | -0.067 |
Sn | -0.066 |
Nib | -0.066 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
joy | +0.028 |
ogs | +0.027 |
itting | +0.026 |
working | +0.026 |
listener | +0.025 |
Neg logit contributions | |
Fl | -0.022 |
Flor | -0.021 |
Fl | -0.021 |
Rudolph | -0.020 |
Nib | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Fl | +0.018 |
Rudolph | +0.017 |
Nib | +0.017 |
Flor | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
listener | -0.027 |
itting | -0.027 |
working | -0.026 |
joy | -0.026 |
ogs | -0.025 |
Token | dish |
Token ID | 9433 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Rudolph | +0.064 |
Fl | +0.062 |
Nib | +0.061 |
Sn | +0.061 |
Fl | +0.061 |
Neg logit contributions | |
listener | -0.048 |
joy | -0.046 |
working | -0.046 |
itting | -0.045 |
ogs | -0.044 |
Token | washer |
Token ID | 45146 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Nib | +0.088 |
Rudolph | +0.088 |
Fl | +0.087 |
Flor | +0.085 |
Sn | +0.082 |
Neg logit contributions | |
joy | -0.097 |
listener | -0.093 |
working | -0.092 |
runner | -0.090 |
itting | -0.089 |
Token | for |
Token ID | 329 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Rudolph | +0.221 |
Fl | +0.221 |
Nib | +0.218 |
Sn | +0.210 |
Flor | +0.209 |
Neg logit contributions | |
listener | -0.190 |
joy | -0.187 |
working | -0.186 |
itting | -0.181 |
ogs | -0.176 |
Token | help |
Token ID | 1037 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.017 |
Nib | +0.017 |
Sn | +0.017 |
Fl | +0.017 |
Neg logit contributions | |
listener | -0.016 |
joy | -0.016 |
working | -0.016 |
itting | -0.015 |
ogs | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
Rudolph | +0.020 |
Fl | +0.019 |
Nib | +0.019 |
Sn | +0.019 |
Fl | +0.019 |
Neg logit contributions | |
listener | -0.012 |
joy | -0.012 |
working | -0.012 |
itting | -0.012 |
ogs | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
listener | +0.002 |
working | +0.002 |
joy | +0.002 |
itting | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.002 |
Fl | -0.002 |
Nib | -0.002 |
Fl | -0.002 |
Sn | -0.002 |
Token | dish |
Token ID | 9433 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.007 |
Nib | +0.007 |
Fl | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
listener | -0.005 |
working | -0.005 |
joy | -0.005 |
itting | -0.005 |
friends | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
Rudolph | +0.027 |
Nib | +0.026 |
Fl | +0.026 |
Sn | +0.025 |
extingu | +0.025 |
Neg logit contributions | |
listener | -0.029 |
working | -0.029 |
itting | -0.029 |
joy | -0.028 |
ogs | -0.028 |
Token | prince |
Token ID | 19716 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.031 |
Nib | +0.030 |
Sn | +0.030 |
Sunny | +0.030 |
Neg logit contributions | |
itting | -0.030 |
ogs | -0.028 |
listener | -0.028 |
joy | -0.028 |
ugs | -0.026 |
Token | went |
Token ID | 1816 |
Feature activation | -1.43e-04 |
Pos logit contributions | |
Rudolph | +0.019 |
Fl | +0.018 |
Nib | +0.017 |
Frost | +0.017 |
Fl | +0.017 |
Neg logit contributions | |
itting | -0.023 |
joy | -0.023 |
listener | -0.022 |
ogs | -0.022 |
working | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
Rudolph | +0.000 |
Fl | +0.000 |
Fl | +0.000 |
Nib | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
listener | -0.000 |
joy | -0.000 |
working | -0.000 |
ogs | -0.000 |
itting | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
Rudolph | +0.033 |
Fl | +0.032 |
Nib | +0.030 |
Sn | +0.029 |
Frost | +0.029 |
Neg logit contributions | |
itting | -0.047 |
listener | -0.045 |
working | -0.044 |
joy | -0.044 |
ogs | -0.043 |
Token | battlefield |
Token ID | 13480 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Rudolph | +0.068 |
Fl | +0.068 |
Fl | +0.068 |
Sn | +0.068 |
Nib | +0.067 |
Neg logit contributions | |
listener | -0.047 |
working | -0.047 |
joy | -0.046 |
ogs | -0.043 |
itting | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Rudolph | +0.188 |
Fl | +0.184 |
Nib | +0.174 |
Sn | +0.174 |
Frost | +0.171 |
Neg logit contributions | |
listener | -0.212 |
itting | -0.210 |
joy | -0.208 |
working | -0.206 |
ogs | -0.201 |
Token | his |
Token ID | 465 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
Fl | +0.029 |
Rudolph | +0.028 |
Sunny | +0.025 |
Nib | +0.024 |
Frost | +0.024 |
Neg logit contributions | |
itting | -0.066 |
listener | -0.062 |
ogs | -0.060 |
rav | -0.060 |
ule | -0.058 |
Token | soldiers |
Token ID | 5795 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.002 |
Frost | +0.002 |
Sunny | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
itting | -0.001 |
listener | -0.001 |
ogs | -0.001 |
joy | -0.001 |
ogged | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
Rudolph | +0.096 |
Fl | +0.093 |
Nib | +0.089 |
Sn | +0.088 |
extingu | +0.087 |
Neg logit contributions | |
listener | -0.102 |
joy | -0.098 |
itting | -0.097 |
working | -0.097 |
ogs | -0.094 |
Token | He |
Token ID | 679 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
listener | +0.005 |
itting | +0.005 |
joy | +0.005 |
working | +0.005 |
ogs | +0.005 |
Neg logit contributions | |
Rudolph | -0.004 |
Fl | -0.004 |
Nib | -0.004 |
Sn | -0.004 |
Frost | -0.004 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
joy | +0.013 |
ogs | +0.013 |
listener | +0.013 |
itting | +0.012 |
working | +0.012 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.010 |
Sn | -0.010 |
Nib | -0.010 |
Fl | -0.010 |
Token | him |
Token ID | 683 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
Rudolph | +0.045 |
Fl | +0.044 |
Nib | +0.043 |
Sn | +0.043 |
Fl | +0.042 |
Neg logit contributions | |
listener | -0.047 |
joy | -0.046 |
itting | -0.046 |
working | -0.046 |
ogs | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
Rudolph | +0.102 |
Fl | +0.099 |
Sn | +0.098 |
Fl | +0.098 |
Nib | +0.097 |
Neg logit contributions | |
listener | -0.066 |
working | -0.064 |
joy | -0.064 |
ogs | -0.061 |
itting | -0.061 |
Token | help |
Token ID | 1037 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
Rudolph | +0.066 |
Fl | +0.064 |
Nib | +0.063 |
Fl | +0.063 |
Sn | +0.063 |
Neg logit contributions | |
listener | -0.054 |
working | -0.052 |
itting | -0.051 |
joy | -0.051 |
ogs | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
Rudolph | +0.070 |
Fl | +0.068 |
Nib | +0.067 |
Fl | +0.066 |
Sn | +0.066 |
Neg logit contributions | |
listener | -0.057 |
working | -0.056 |
joy | -0.055 |
itting | -0.055 |
ogs | -0.054 |
Token | drain |
Token ID | 14782 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Rudolph | +0.024 |
Fl | +0.024 |
Nib | +0.023 |
Sn | +0.023 |
Fl | +0.023 |
Neg logit contributions | |
listener | -0.024 |
joy | -0.024 |
working | -0.023 |
itting | -0.023 |
ogs | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Rudolph | +0.198 |
Fl | +0.195 |
Sn | +0.190 |
Nib | +0.189 |
Fl | +0.187 |
Neg logit contributions | |
listener | -0.204 |
joy | -0.203 |
itting | -0.196 |
working | -0.195 |
ogs | -0.188 |
Token | water |
Token ID | 1660 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.033 |
Sn | +0.032 |
Fl | +0.032 |
Nib | +0.032 |
Neg logit contributions | |
joy | -0.037 |
listener | -0.037 |
itting | -0.037 |
working | -0.036 |
ogs | -0.036 |
Token | from |
Token ID | 422 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Rudolph | +0.068 |
Fl | +0.067 |
Sn | +0.066 |
Nib | +0.065 |
Fl | +0.065 |
Neg logit contributions | |
listener | -0.062 |
joy | -0.062 |
itting | -0.059 |
working | -0.058 |
ogs | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Rudolph | +0.091 |
Fl | +0.088 |
Nib | +0.086 |
Sn | +0.085 |
Fl | +0.085 |
Neg logit contributions | |
working | -0.085 |
listener | -0.083 |
joy | -0.082 |
friends | -0.078 |
ogs | -0.078 |
Token | sink |
Token ID | 14595 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
Rudolph | +0.019 |
Fl | +0.017 |
Nib | +0.017 |
Fl | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
listener | -0.020 |
working | -0.019 |
joy | -0.019 |
itting | -0.018 |
friends | -0.018 |
Token | new |
Token ID | 649 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
Rudolph | +0.104 |
Fl | +0.101 |
Nib | +0.100 |
Sn | +0.099 |
Fl | +0.099 |
Neg logit contributions | |
listener | -0.074 |
joy | -0.072 |
working | -0.072 |
itting | -0.071 |
ogs | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
Fl | +0.011 |
Rudolph | +0.011 |
Sn | +0.010 |
Fl | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
joy | -0.011 |
itting | -0.011 |
listener | -0.011 |
working | -0.011 |
oom | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +9.12e-04 |
Pos logit contributions | |
listener | +0.049 |
joy | +0.049 |
working | +0.048 |
itting | +0.048 |
ogs | +0.047 |
Neg logit contributions | |
Rudolph | -0.037 |
Fl | -0.035 |
Fl | -0.035 |
Sn | -0.035 |
Nib | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
listener | +0.001 |
working | +0.001 |
joy | +0.001 |
itting | +0.001 |
ogs | +0.001 |
Neg logit contributions | |
Rudolph | -0.002 |
Fl | -0.001 |
Nib | -0.001 |
Sn | -0.001 |
Fl | -0.001 |
Token | called |
Token ID | 1444 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
Rudolph | +0.012 |
Fl | +0.011 |
Nib | +0.011 |
Fl | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
listener | -0.014 |
working | -0.013 |
joy | -0.013 |
itting | -0.013 |
friends | -0.013 |
Token | oxygen |
Token ID | 11863 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Rudolph | +0.051 |
Fl | +0.050 |
Nib | +0.048 |
Fl | +0.047 |
Tenn | +0.046 |
Neg logit contributions | |
joy | -0.072 |
working | -0.072 |
listener | -0.072 |
itting | -0.071 |
ogs | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-04 |
Pos logit contributions | |
Rudolph | +0.248 |
Fl | +0.244 |
Nib | +0.243 |
Fl | +0.241 |
Sn | +0.241 |
Neg logit contributions | |
listener | -0.147 |
working | -0.145 |
itting | -0.141 |
joy | -0.138 |
ogs | -0.136 |
Token | He |
Token ID | 679 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
Fl | +0.001 |
Rudolph | +0.001 |
Frost | +0.001 |
Sunny | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
listener | -0.001 |
working | -0.001 |
itting | -0.001 |
joy | -0.001 |
runner | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
Rudolph | +0.009 |
Fl | +0.009 |
Nib | +0.009 |
Sn | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
listener | -0.007 |
working | -0.007 |
joy | -0.007 |
itting | -0.007 |
ogs | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
Fl | +0.008 |
extingu | +0.007 |
Rudolph | +0.007 |
Nib | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
friends | -0.009 |
listener | -0.008 |
working | -0.008 |
joy | -0.008 |
itting | -0.008 |
Token | bit |
Token ID | 1643 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
listener | +0.007 |
working | +0.007 |
joy | +0.007 |
itting | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Nib | -0.009 |
Fl | -0.009 |
Rudolph | -0.009 |
Sn | -0.009 |
Fl | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
Fl | +0.047 |
Rudolph | +0.045 |
Sunny | +0.042 |
Sn | +0.042 |
Frost | +0.041 |
Neg logit contributions | |
listener | -0.074 |
itting | -0.073 |
working | -0.072 |
joy | -0.069 |
ogs | -0.069 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
listener | +0.007 |
itting | +0.006 |
working | +0.006 |
joy | +0.006 |
ogs | +0.006 |
Neg logit contributions | |
Rudolph | -0.008 |
Fl | -0.007 |
Nib | -0.007 |
Fl | -0.007 |
Sn | -0.007 |
Token | before |
Token ID | 878 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
listener | +0.027 |
working | +0.025 |
joy | +0.025 |
ogs | +0.024 |
itting | +0.024 |
Neg logit contributions | |
Rudolph | -0.023 |
Fl | -0.023 |
Sunny | -0.021 |
Sn | -0.021 |
Nib | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.033 |
Sn | +0.032 |
Nib | +0.031 |
Frost | +0.031 |
Neg logit contributions | |
listener | -0.041 |
itting | -0.039 |
working | -0.038 |
joy | -0.038 |
ogs | -0.038 |
Token | walked |
Token ID | 6807 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
Rudolph | +0.029 |
Fl | +0.028 |
Nib | +0.027 |
Flor | +0.027 |
Frost | +0.027 |
Neg logit contributions | |
joy | -0.035 |
listener | -0.033 |
itting | -0.032 |
ogs | -0.031 |
working | -0.031 |
Token | fore |
Token ID | 1674 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Rudolph | +0.006 |
Fl | +0.006 |
Nib | +0.006 |
Sn | +0.006 |
Fl | +0.006 |
Neg logit contributions | |
listener | -0.006 |
joy | -0.006 |
working | -0.006 |
itting | -0.006 |
ogs | -0.006 |
Token | shadow |
Token ID | 19106 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Fl | +0.171 |
Rudolph | +0.170 |
Nib | +0.163 |
Sn | +0.160 |
Fl | +0.159 |
Neg logit contributions | |
working | -0.228 |
listener | -0.227 |
itting | -0.225 |
ogs | -0.223 |
joy | -0.221 |
Token | ed |
Token ID | 276 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Rudolph | +0.053 |
Fl | +0.052 |
Sn | +0.051 |
Nib | +0.051 |
Fl | +0.050 |
Neg logit contributions | |
listener | -0.032 |
working | -0.031 |
joy | -0.030 |
itting | -0.030 |
ogs | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
Rudolph | +0.015 |
Fl | +0.015 |
Nib | +0.014 |
Sn | +0.014 |
Fl | +0.014 |
Neg logit contributions | |
listener | -0.017 |
working | -0.017 |
itting | -0.017 |
joy | -0.017 |
ogs | -0.016 |
Token | down |
Token ID | 866 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Rudolph | +0.004 |
Fl | +0.004 |
Nib | +0.004 |
Sn | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
listener | -0.003 |
joy | -0.003 |
itting | -0.003 |
working | -0.003 |
ogs | -0.003 |
Token | pour |
Token ID | 48681 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
listener | +0.100 |
itting | +0.097 |
working | +0.097 |
joy | +0.094 |
udding | +0.092 |
Neg logit contributions | |
Rudolph | -0.079 |
Fl | -0.079 |
Nib | -0.075 |
Sn | -0.074 |
from | -0.074 |
Token | her |
Token ID | 607 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
Rudolph | +0.058 |
Fl | +0.057 |
Nib | +0.056 |
Sn | +0.055 |
Fl | +0.055 |
Neg logit contributions | |
listener | -0.042 |
working | -0.041 |
itting | -0.040 |
joy | -0.040 |
ogs | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
Rudolph | +0.068 |
Fl | +0.066 |
Fl | +0.066 |
Sn | +0.065 |
Nib | +0.065 |
Neg logit contributions | |
listener | -0.059 |
joy | -0.058 |
working | -0.057 |
itting | -0.056 |
ogs | -0.055 |
Token | go |
Token ID | 467 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
Rudolph | +0.078 |
Fl | +0.076 |
Nib | +0.076 |
Fl | +0.075 |
Sn | +0.075 |
Neg logit contributions | |
listener | -0.051 |
working | -0.048 |
friends | -0.047 |
ogs | -0.047 |
itting | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Rudolph | +0.061 |
Fl | +0.059 |
Fl | +0.058 |
Nib | +0.058 |
Sn | +0.058 |
Neg logit contributions | |
listener | -0.047 |
joy | -0.046 |
working | -0.046 |
itting | -0.045 |
ogs | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
Rudolph | +0.065 |
Fl | +0.063 |
Fl | +0.063 |
Nib | +0.062 |
Sn | +0.062 |
Neg logit contributions | |
listener | -0.071 |
joy | -0.070 |
working | -0.069 |
ogs | -0.068 |
itting | -0.067 |
Token | basement |
Token ID | 17012 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Rudolph | +0.085 |
sc | +0.080 |
Das | +0.080 |
Nib | +0.079 |
Frost | +0.079 |
Neg logit contributions | |
listener | -0.051 |
friends | -0.049 |
working | -0.047 |
friend | -0.047 |
painter | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Rudolph | +0.199 |
Fl | +0.197 |
Sn | +0.191 |
Nib | +0.187 |
extingu | +0.183 |
Neg logit contributions | |
listener | -0.188 |
joy | -0.187 |
itting | -0.183 |
working | -0.182 |
ogs | -0.176 |
Token | get |
Token ID | 651 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
Rudolph | +0.039 |
Fl | +0.038 |
Nib | +0.037 |
Fl | +0.037 |
Sn | +0.037 |
Neg logit contributions | |
listener | -0.024 |
working | -0.023 |
ogs | -0.023 |
joy | -0.022 |
itting | -0.022 |
Token | some |
Token ID | 617 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
Rudolph | +0.052 |
Fl | +0.050 |
Fl | +0.049 |
Nib | +0.049 |
Sn | +0.049 |
Neg logit contributions | |
listener | -0.058 |
joy | -0.057 |
working | -0.057 |
itting | -0.056 |
ogs | -0.055 |
Token | laundry |
Token ID | 25724 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
Rudolph | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Sn | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
joy | -0.005 |
listener | -0.005 |
itting | -0.005 |
working | -0.005 |
ogs | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
Rudolph | +0.077 |
Fl | +0.073 |
Sn | +0.073 |
extingu | +0.071 |
Nib | +0.071 |
Neg logit contributions | |
listener | -0.068 |
joy | -0.067 |
itting | -0.066 |
working | -0.064 |
ogs | -0.063 |
Token | Joe |
Token ID | 5689 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
Fl | +0.025 |
Rudolph | +0.024 |
Nib | +0.024 |
Frost | +0.024 |
Sn | +0.023 |
Neg logit contributions | |
working | -0.023 |
listener | -0.023 |
itting | -0.023 |
joy | -0.022 |
runner | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
Rudolph | +0.071 |
Fl | +0.069 |
Nib | +0.068 |
Sn | +0.067 |
Fl | +0.067 |
Neg logit contributions | |
listener | -0.060 |
joy | -0.059 |
working | -0.059 |
itting | -0.058 |
ogs | -0.057 |
Token | come |
Token ID | 1282 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
Rudolph | +0.049 |
Fl | +0.048 |
Sn | +0.046 |
Nib | +0.046 |
Fl | +0.046 |
Neg logit contributions | |
joy | -0.041 |
listener | -0.040 |
itting | -0.039 |
working | -0.038 |
ogs | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
Rudolph | +0.050 |
Fl | +0.049 |
Fl | +0.048 |
Nib | +0.048 |
Sn | +0.047 |
Neg logit contributions | |
listener | -0.047 |
joy | -0.046 |
working | -0.045 |
itting | -0.045 |
ogs | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Rudolph | +0.056 |
Fl | +0.054 |
Nib | +0.052 |
Sn | +0.051 |
Frost | +0.051 |
Neg logit contributions | |
itting | -0.073 |
listener | -0.072 |
working | -0.070 |
joy | -0.069 |
ogs | -0.068 |
Token | port |
Token ID | 2493 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Rudolph | +0.105 |
ified | +0.105 |
Fl | +0.105 |
Nib | +0.105 |
versa | +0.104 |
Neg logit contributions | |
friends | -0.046 |
listener | -0.044 |
painter | -0.044 |
working | -0.043 |
joy | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
Rudolph | +0.183 |
Fl | +0.174 |
Nib | +0.168 |
Sn | +0.168 |
Frost | +0.165 |
Neg logit contributions | |
listener | -0.203 |
joy | -0.202 |
itting | -0.199 |
working | -0.197 |
ogs | -0.189 |
Token | discuss |
Token ID | 2112 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Rudolph | +0.049 |
Fl | +0.048 |
Nib | +0.047 |
Sn | +0.047 |
Fl | +0.046 |
Neg logit contributions | |
listener | -0.026 |
joy | -0.025 |
itting | -0.025 |
working | -0.025 |
ogs | -0.024 |
Token | something |
Token ID | 1223 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
Rudolph | +0.031 |
Fl | +0.030 |
Sn | +0.029 |
Nib | +0.029 |
Frost | +0.029 |
Neg logit contributions | |
listener | -0.037 |
working | -0.036 |
itting | -0.036 |
joy | -0.035 |
ogs | -0.034 |
Token | important |
Token ID | 1593 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
Rudolph | +0.069 |
Fl | +0.066 |
Fl | +0.066 |
Nib | +0.066 |
Sn | +0.066 |
Neg logit contributions | |
listener | -0.047 |
joy | -0.046 |
working | -0.046 |
itting | -0.045 |
ogs | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.018 |
Sn | +0.018 |
Nib | +0.018 |
Fl | +0.017 |
Neg logit contributions | |
listener | -0.013 |
joy | -0.012 |
working | -0.012 |
itting | -0.012 |
ogs | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
Fl | +0.000 |
Frost | +0.000 |
Rudolph | +0.000 |
extingu | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
itting | -0.000 |
ogs | -0.000 |
working | -0.000 |
joy | -0.000 |
listener | -0.000 |
Token | came |
Token ID | 1625 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
listener | +0.012 |
working | +0.012 |
ogs | +0.012 |
joy | +0.012 |
itting | +0.012 |
Neg logit contributions | |
Fl | -0.015 |
Rudolph | -0.015 |
Sn | -0.014 |
Fl | -0.014 |
Nib | -0.014 |
Token | down |
Token ID | 866 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
Rudolph | +0.050 |
Fl | +0.048 |
Nib | +0.047 |
Fl | +0.047 |
Sn | +0.047 |
Neg logit contributions | |
listener | -0.068 |
joy | -0.067 |
working | -0.066 |
itting | -0.065 |
ogs | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
listener | +0.007 |
joy | +0.007 |
working | +0.007 |
itting | +0.007 |
ogs | +0.007 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Nib | -0.006 |
Fl | -0.006 |
Sn | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Rudolph | +0.071 |
Fl | +0.069 |
Fl | +0.068 |
Nib | +0.068 |
Sn | +0.068 |
Neg logit contributions | |
joy | -0.051 |
listener | -0.051 |
working | -0.049 |
itting | -0.048 |
ogs | -0.047 |
Token | basement |
Token ID | 17012 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Rudolph | +0.060 |
Fl | +0.058 |
Nib | +0.057 |
Sn | +0.056 |
Fl | +0.056 |
Neg logit contributions | |
listener | -0.054 |
joy | -0.053 |
working | -0.053 |
itting | -0.052 |
ogs | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
Rudolph | +0.202 |
Fl | +0.202 |
Sn | +0.196 |
Nib | +0.191 |
Fl | +0.191 |
Neg logit contributions | |
listener | -0.175 |
working | -0.170 |
joy | -0.170 |
itting | -0.169 |
ogs | -0.165 |
Token | She |
Token ID | 1375 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.013 |
Fl | +0.013 |
Nib | +0.013 |
Sn | +0.013 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
working | -0.010 |
itting | -0.010 |
ogs | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Sn | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
listener | -0.002 |
working | -0.002 |
ogs | -0.002 |
itting | -0.002 |
joy | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
friends | +0.017 |
joy | +0.015 |
working | +0.015 |
ies | +0.014 |
listener | +0.014 |
Neg logit contributions | |
Fl | -0.024 |
mant | -0.023 |
Sn | -0.023 |
ified | -0.022 |
sc | -0.022 |
Token | box |
Token ID | 3091 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ogs | +0.009 |
itting | +0.009 |
ogged | +0.008 |
listener | +0.008 |
joy | +0.008 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Frost | -0.006 |
extingu | -0.006 |
Sn | -0.006 |
Token | : |
Token ID | 25 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
joy | +0.014 |
listener | +0.014 |
working | +0.014 |
itting | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.025 |
Sn | -0.024 |
Fl | -0.024 |
extingu | -0.024 |
Das | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Rudolph | +0.028 |
Fl | +0.027 |
Fl | +0.027 |
Sn | +0.027 |
Nib | +0.027 |
Neg logit contributions | |
joy | -0.023 |
listener | -0.022 |
working | -0.022 |
itting | -0.021 |
ogs | -0.021 |
Token | Give |
Token ID | 23318 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
Rudolph | +0.047 |
Fl | +0.045 |
Nib | +0.044 |
Sn | +0.043 |
Fl | +0.042 |
Neg logit contributions | |
listener | -0.075 |
joy | -0.073 |
working | -0.073 |
itting | -0.072 |
ogs | -0.071 |
Token | me |
Token ID | 502 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
Rudolph | +0.037 |
Sn | +0.036 |
Fl | +0.036 |
Nib | +0.035 |
Fl | +0.035 |
Neg logit contributions | |
listener | -0.052 |
joy | -0.051 |
working | -0.051 |
ogs | -0.050 |
itting | -0.049 |
Token | your |
Token ID | 534 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
listener | +0.017 |
joy | +0.017 |
working | +0.017 |
itting | +0.017 |
ogs | +0.017 |
Neg logit contributions | |
Rudolph | -0.013 |
Fl | -0.012 |
Sn | -0.012 |
Nib | -0.012 |
Fl | -0.012 |
Token | oxygen |
Token ID | 11863 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Rudolph | +0.063 |
Fl | +0.062 |
Nib | +0.062 |
Fl | +0.061 |
Sn | +0.061 |
Neg logit contributions | |
listener | -0.087 |
working | -0.086 |
joy | -0.085 |
itting | -0.083 |
friends | -0.083 |
Token | or |
Token ID | 393 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
Rudolph | +0.215 |
Fl | +0.207 |
Nib | +0.206 |
Fl | +0.205 |
Sn | +0.205 |
Neg logit contributions | |
listener | -0.163 |
joy | -0.158 |
working | -0.158 |
itting | -0.154 |
ogs | -0.152 |
Token | else |
Token ID | 2073 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
Rudolph | +0.059 |
Fl | +0.057 |
Fl | +0.057 |
Sn | +0.057 |
Nib | +0.056 |
Neg logit contributions | |
listener | -0.074 |
working | -0.072 |
joy | -0.072 |
itting | -0.070 |
ogs | -0.070 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
Fl | +0.097 |
Rudolph | +0.097 |
Sn | +0.092 |
Fl | +0.090 |
Nib | +0.089 |
Neg logit contributions | |
listener | -0.097 |
joy | -0.097 |
itting | -0.094 |
working | -0.092 |
ogs | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Rudolph | +0.004 |
Sn | +0.004 |
Fl | +0.004 |
Nib | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
ogs | -0.004 |
working | -0.004 |
itting | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Rudolph | +0.021 |
Nib | +0.020 |
Sn | +0.020 |
extingu | +0.020 |
Fl | +0.019 |
Neg logit contributions | |
listener | -0.018 |
ogs | -0.018 |
joy | -0.018 |
working | -0.017 |
itting | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | -6.52e-04 |
Pos logit contributions | |
joy | +0.007 |
listener | +0.007 |
itting | +0.007 |
working | +0.007 |
ogs | +0.007 |
Neg logit contributions | |
Fl | -0.005 |
Rudolph | -0.005 |
Fl | -0.005 |
Nib | -0.005 |
Sn | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
Rudolph | +0.001 |
extingu | +0.001 |
Nib | +0.001 |
Fl | +0.001 |
Das | +0.001 |
Neg logit contributions | |
listener | -0.001 |
working | -0.001 |
joy | -0.001 |
ogs | -0.001 |
itting | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Rudolph | +0.067 |
Fl | +0.067 |
Nib | +0.063 |
Sn | +0.063 |
Fl | +0.062 |
Neg logit contributions | |
joy | -0.058 |
listener | -0.057 |
itting | -0.057 |
ogs | -0.053 |
working | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
Fl | +0.032 |
Rudolph | +0.032 |
Fl | +0.032 |
Sn | +0.031 |
Nib | +0.031 |
Neg logit contributions | |
working | -0.017 |
listener | -0.017 |
ogs | -0.017 |
joy | -0.016 |
friends | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
Rudolph | +0.048 |
Fl | +0.047 |
Nib | +0.045 |
Sn | +0.045 |
Fl | +0.044 |
Neg logit contributions | |
listener | -0.060 |
itting | -0.059 |
joy | -0.059 |
working | -0.058 |
ogs | -0.057 |
Token | port |
Token ID | 2493 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Fl | +0.096 |
ified | +0.095 |
Fl | +0.093 |
Tenn | +0.092 |
Nib | +0.091 |
Neg logit contributions | |
friends | -0.043 |
friend | -0.041 |
working | -0.039 |
listener | -0.039 |
painter | -0.038 |
Token | with |
Token ID | 351 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
Rudolph | +0.181 |
Fl | +0.176 |
Sn | +0.169 |
Nib | +0.167 |
Fl | +0.164 |
Neg logit contributions | |
listener | -0.186 |
joy | -0.184 |
itting | -0.180 |
working | -0.178 |
ogs | -0.171 |
Token | her |
Token ID | 607 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
Fl | +0.065 |
Rudolph | +0.064 |
Nib | +0.062 |
Sn | +0.061 |
Flor | +0.059 |
Neg logit contributions | |
listener | -0.061 |
itting | -0.060 |
joy | -0.058 |
working | -0.058 |
ogs | -0.056 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
itting | +0.004 |
listener | +0.004 |
joy | +0.004 |
ogs | +0.004 |
working | +0.004 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.006 |
Sn | -0.006 |
Nib | -0.006 |
Frost | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Rudolph | +0.025 |
Fl | +0.024 |
Fl | +0.024 |
Nib | +0.024 |
Sn | +0.024 |
Neg logit contributions | |
listener | -0.013 |
working | -0.012 |
joy | -0.012 |
itting | -0.012 |
ogs | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
Rudolph | +0.022 |
Fl | +0.022 |
Sn | +0.021 |
Nib | +0.021 |
Fl | +0.021 |
Neg logit contributions | |
listener | -0.021 |
joy | -0.021 |
working | -0.020 |
itting | -0.020 |
ogs | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
listener | +0.000 |
joy | +0.000 |
working | +0.000 |
itting | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Nib | -0.000 |
Sn | -0.000 |
Fl | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
listener | +0.016 |
joy | +0.016 |
ogs | +0.016 |
itting | +0.016 |
working | +0.015 |
Neg logit contributions | |
Fl | -0.014 |
Rudolph | -0.014 |
Sn | -0.014 |
Nib | -0.013 |
Fl | -0.013 |
Token | went |
Token ID | 1816 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
Rudolph | +0.035 |
Fl | +0.034 |
Sn | +0.033 |
Nib | +0.033 |
Fl | +0.033 |
Neg logit contributions | |
listener | -0.025 |
joy | -0.024 |
working | -0.024 |
itting | -0.024 |
ogs | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.014 |
Fl | +0.014 |
Nib | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
listener | -0.009 |
working | -0.009 |
joy | -0.009 |
itting | -0.009 |
ogs | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
Rudolph | +0.040 |
Fl | +0.040 |
Nib | +0.039 |
Fl | +0.038 |
Sn | +0.038 |
Neg logit contributions | |
listener | -0.041 |
working | -0.041 |
joy | -0.041 |
ogs | -0.039 |
itting | -0.039 |
Token | cinema |
Token ID | 22041 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Nib | +0.073 |
ified | +0.073 |
Fl | +0.072 |
extingu | +0.071 |
Tenn | +0.070 |
Neg logit contributions | |
working | -0.047 |
friends | -0.045 |
listener | -0.044 |
painter | -0.044 |
friend | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
Rudolph | +0.185 |
Fl | +0.180 |
Sn | +0.173 |
Frost | +0.171 |
Fl | +0.169 |
Neg logit contributions | |
joy | -0.183 |
listener | -0.181 |
itting | -0.177 |
working | -0.176 |
ogs | -0.169 |
Token | watch |
Token ID | 2342 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
Fl | +0.041 |
Rudolph | +0.041 |
Nib | +0.040 |
Sn | +0.040 |
Fl | +0.040 |
Neg logit contributions | |
listener | -0.014 |
working | -0.014 |
joy | -0.013 |
ogs | -0.012 |
friends | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
listener | +0.017 |
joy | +0.017 |
working | +0.016 |
itting | +0.016 |
ogs | +0.016 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.011 |
Nib | -0.011 |
Fl | -0.011 |
Sn | -0.011 |
Token | funny |
Token ID | 8258 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
Rudolph | +0.041 |
Fl | +0.040 |
Nib | +0.039 |
Fl | +0.039 |
Sn | +0.039 |
Neg logit contributions | |
listener | -0.045 |
working | -0.044 |
joy | -0.044 |
itting | -0.043 |
ogs | -0.042 |
Token | movie |
Token ID | 3807 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
Rudolph | +0.010 |
Fl | +0.010 |
Sn | +0.009 |
Nib | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
listener | -0.017 |
joy | -0.016 |
itting | -0.016 |
working | -0.016 |
ogs | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
Fl | +0.042 |
Rudolph | +0.042 |
Sn | +0.041 |
Nib | +0.041 |
Fl | +0.040 |
Neg logit contributions | |
listener | -0.034 |
working | -0.033 |
itting | -0.033 |
joy | -0.032 |
ogs | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
Rudolph | +0.060 |
Fl | +0.058 |
Nib | +0.057 |
Sn | +0.057 |
Fl | +0.057 |
Neg logit contributions | |
listener | -0.051 |
joy | -0.050 |
working | -0.050 |
itting | -0.049 |
ogs | -0.048 |
Token | shut |
Token ID | 4423 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Rudolph | +0.065 |
Fl | +0.063 |
Fl | +0.063 |
Nib | +0.063 |
Sn | +0.062 |
Neg logit contributions | |
listener | -0.046 |
working | -0.045 |
joy | -0.044 |
itting | -0.043 |
ogs | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Rudolph | +0.114 |
Fl | +0.113 |
Nib | +0.111 |
extingu | +0.107 |
Das | +0.106 |
Neg logit contributions | |
joy | -0.091 |
listener | -0.088 |
working | -0.088 |
ogs | -0.086 |
friends | -0.084 |
Token | dish |
Token ID | 9433 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
Fl | +0.049 |
Sunny | +0.047 |
Nib | +0.046 |
Rudolph | +0.046 |
Flor | +0.046 |
Neg logit contributions | |
listener | -0.029 |
joy | -0.029 |
ay | -0.028 |
friends | -0.028 |
working | -0.028 |
Token | washer |
Token ID | 45146 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Rudolph | +0.080 |
Fl | +0.078 |
Fl | +0.077 |
Nib | +0.077 |
Sn | +0.076 |
Neg logit contributions | |
listener | -0.071 |
working | -0.070 |
itting | -0.068 |
ogs | -0.067 |
joy | -0.067 |
Token | off |
Token ID | 572 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
Rudolph | +0.218 |
Fl | +0.212 |
Nib | +0.210 |
Fl | +0.210 |
Sn | +0.207 |
Neg logit contributions | |
listener | -0.150 |
working | -0.147 |
joy | -0.145 |
itting | -0.143 |
ogs | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
Fl | +0.052 |
Rudolph | +0.051 |
Sn | +0.050 |
Fl | +0.048 |
Nib | +0.047 |
Neg logit contributions | |
listener | -0.057 |
itting | -0.057 |
joy | -0.056 |
working | -0.055 |
ogs | -0.053 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.13e-05 |
Pos logit contributions | |
listener | +0.002 |
joy | +0.002 |
working | +0.002 |
itting | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.002 |
Nib | -0.001 |
Fl | -0.001 |
Fl | -0.001 |
Sn | -0.001 |
Token | pressed |
Token ID | 12070 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
listener | +0.000 |
joy | +0.000 |
working | +0.000 |
itting | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Nib | -0.000 |
Sn | -0.000 |
Fl | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
Rudolph | +0.017 |
Fl | +0.017 |
Sn | +0.016 |
Nib | +0.016 |
Fl | +0.016 |
Neg logit contributions | |
listener | -0.025 |
itting | -0.025 |
joy | -0.025 |
working | -0.025 |
ogs | -0.024 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
joy | +0.015 |
listener | +0.015 |
itting | +0.015 |
working | +0.014 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.013 |
Fl | -0.013 |
Sn | -0.012 |
Frost | -0.012 |
Fl | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
Fl | +0.005 |
Rudolph | +0.005 |
Sn | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
listener | -0.008 |
working | -0.008 |
joy | -0.008 |
itting | -0.007 |
runner | -0.007 |
Token | went |
Token ID | 1816 |
Feature activation | -9.18e-03 |
Pos logit contributions | |
Rudolph | +0.046 |
Sn | +0.044 |
Fl | +0.044 |
Frost | +0.041 |
Das | +0.041 |
Neg logit contributions | |
joy | -0.052 |
listener | -0.051 |
itting | -0.050 |
working | -0.048 |
ogs | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
Rudolph | +0.017 |
Fl | +0.017 |
Fl | +0.017 |
Nib | +0.017 |
Sn | +0.016 |
Neg logit contributions | |
listener | -0.012 |
working | -0.011 |
joy | -0.011 |
ogs | -0.011 |
itting | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
Rudolph | +0.049 |
Fl | +0.047 |
Fl | +0.046 |
Nib | +0.046 |
Sn | +0.046 |
Neg logit contributions | |
listener | -0.058 |
joy | -0.057 |
working | -0.057 |
ogs | -0.055 |
itting | -0.055 |
Token | port |
Token ID | 2493 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Nib | +0.089 |
Fl | +0.088 |
Flor | +0.087 |
Rudolph | +0.087 |
ified | +0.087 |
Neg logit contributions | |
listener | -0.038 |
working | -0.037 |
friends | -0.037 |
joy | -0.037 |
ogs | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Rudolph | +0.178 |
Fl | +0.173 |
Sn | +0.168 |
Nib | +0.164 |
extingu | +0.163 |
Neg logit contributions | |
listener | -0.188 |
joy | -0.185 |
itting | -0.183 |
working | -0.181 |
ogs | -0.175 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Rudolph | +0.041 |
Fl | +0.040 |
Nib | +0.039 |
Sn | +0.039 |
Fl | +0.039 |
Neg logit contributions | |
listener | -0.026 |
joy | -0.026 |
working | -0.025 |
itting | -0.025 |
ogs | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
friends | +0.015 |
joy | +0.015 |
working | +0.015 |
listener | +0.015 |
itting | +0.014 |
Neg logit contributions | |
Fl | -0.017 |
Rudolph | -0.017 |
Sn | -0.017 |
Nib | -0.016 |
Fl | -0.016 |
Token | boats |
Token ID | 16659 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Rudolph | +0.019 |
Fl | +0.018 |
Sn | +0.017 |
Nib | +0.017 |
Das | +0.017 |
Neg logit contributions | |
itting | -0.020 |
listener | -0.020 |
working | -0.019 |
ogs | -0.019 |
joy | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
Rudolph | +0.051 |
Fl | +0.048 |
Sn | +0.048 |
Nib | +0.047 |
extingu | +0.046 |
Neg logit contributions | |
listener | -0.051 |
joy | -0.050 |
working | -0.048 |
itting | -0.047 |
ogs | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
listener | +0.023 |
itting | +0.022 |
joy | +0.022 |
working | +0.022 |
ogs | +0.021 |
Neg logit contributions | |
Fl | -0.024 |
Rudolph | -0.023 |
Sn | -0.022 |
Nib | -0.022 |
Fl | -0.022 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
Rudolph | +0.032 |
Fl | +0.031 |
Nib | +0.030 |
Sn | +0.030 |
Fl | +0.030 |
Neg logit contributions | |
listener | -0.027 |
joy | -0.026 |
working | -0.026 |
itting | -0.026 |
ogs | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
listener | +0.005 |
joy | +0.005 |
working | +0.005 |
itting | +0.005 |
ogs | +0.005 |
Neg logit contributions | |
Rudolph | -0.005 |
Fl | -0.005 |
Nib | -0.005 |
Sn | -0.005 |
Fl | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Rudolph | +0.035 |
Fl | +0.035 |
Sn | +0.034 |
Nib | +0.033 |
Fl | +0.033 |
Neg logit contributions | |
listener | -0.040 |
itting | -0.040 |
working | -0.040 |
joy | -0.039 |
ogs | -0.038 |
Token | camp |
Token ID | 1413 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
Rudolph | +0.052 |
Fl | +0.052 |
Fl | +0.050 |
Sn | +0.049 |
Nib | +0.049 |
Neg logit contributions | |
itting | -0.049 |
listener | -0.049 |
joy | -0.048 |
working | -0.048 |
ogs | -0.047 |
Token | fire |
Token ID | 6495 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Rudolph | +0.076 |
Fl | +0.072 |
Sn | +0.069 |
Fl | +0.069 |
Nib | +0.069 |
Neg logit contributions | |
listener | -0.142 |
joy | -0.140 |
itting | -0.139 |
working | -0.138 |
ogs | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-04 |
Pos logit contributions | |
Rudolph | +0.205 |
Fl | +0.200 |
Sn | +0.194 |
Nib | +0.192 |
Fl | +0.191 |
Neg logit contributions | |
listener | -0.162 |
itting | -0.158 |
joy | -0.157 |
working | -0.157 |
ogs | -0.151 |
Token | She |
Token ID | 1375 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
Rudolph | +0.000 |
Fl | +0.000 |
Nib | +0.000 |
Fl | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
listener | -0.000 |
joy | -0.000 |
working | -0.000 |
itting | -0.000 |
ogs | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
listener | +0.007 |
itting | +0.007 |
joy | +0.007 |
working | +0.007 |
ogs | +0.007 |
Neg logit contributions | |
Rudolph | -0.008 |
Fl | -0.008 |
Nib | -0.007 |
Sn | -0.007 |
Fl | -0.007 |
Token | hungry |
Token ID | 14720 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
listener | -0.006 |
joy | -0.006 |
working | -0.005 |
itting | -0.005 |
ogs | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
listener | +0.019 |
joy | +0.018 |
working | +0.018 |
itting | +0.018 |
ogs | +0.018 |
Neg logit contributions | |
Rudolph | -0.022 |
Fl | -0.021 |
Nib | -0.021 |
Sn | -0.021 |
Fl | -0.021 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
Fl | +0.047 |
Sn | +0.044 |
Rudolph | +0.043 |
Fl | +0.042 |
sc | +0.042 |
Neg logit contributions | |
joy | -0.062 |
ogs | -0.061 |
listener | -0.059 |
working | -0.059 |
friends | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
joy | +0.004 |
listener | +0.004 |
working | +0.004 |
itting | +0.004 |
ogs | +0.004 |
Neg logit contributions | |
Rudolph | -0.002 |
Fl | -0.002 |
Sn | -0.002 |
Fl | -0.002 |
Nib | -0.002 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
Rudolph | +0.102 |
Fl | +0.100 |
Fl | +0.099 |
Nib | +0.099 |
Sn | +0.098 |
Neg logit contributions | |
listener | -0.067 |
working | -0.064 |
joy | -0.063 |
itting | -0.062 |
ogs | -0.062 |
Token | our |
Token ID | 674 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Rudolph | +0.016 |
Fl | +0.016 |
Nib | +0.016 |
Fl | +0.016 |
Sn | +0.015 |
Neg logit contributions | |
listener | -0.017 |
joy | -0.017 |
working | -0.017 |
itting | -0.017 |
ogs | -0.016 |
Token | neighbour |
Token ID | 12250 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
Rudolph | +0.164 |
Fl | +0.161 |
Sn | +0.158 |
Nib | +0.158 |
Fl | +0.157 |
Neg logit contributions | |
listener | -0.070 |
joy | -0.069 |
working | -0.068 |
itting | -0.067 |
ogs | -0.064 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Rudolph | +0.105 |
Fl | +0.102 |
Sn | +0.099 |
Nib | +0.097 |
Fl | +0.095 |
Neg logit contributions | |
listener | -0.106 |
joy | -0.104 |
itting | -0.104 |
working | -0.103 |
ogs | -0.098 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
Rudolph | +0.190 |
Fl | +0.182 |
Sn | +0.179 |
Nib | +0.175 |
Fl | +0.174 |
Neg logit contributions | |
listener | -0.178 |
joy | -0.176 |
itting | -0.174 |
working | -0.172 |
ogs | -0.167 |
Token | |
Token ID | 220 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
Nib | +0.010 |
Fl | +0.010 |
Rudolph | +0.010 |
versa | +0.010 |
extingu | +0.010 |
Neg logit contributions | |
joy | -0.012 |
listener | -0.012 |
ogs | -0.011 |
friends | -0.011 |
itting | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
listener | +0.088 |
joy | +0.087 |
itting | +0.086 |
ogs | +0.086 |
working | +0.085 |
Neg logit contributions | |
Rudolph | -0.083 |
Fl | -0.079 |
Nib | -0.078 |
Fl | -0.078 |
Sn | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
extingu | +0.022 |
Nib | +0.021 |
ified | +0.021 |
versa | +0.021 |
Rudolph | +0.020 |
Neg logit contributions | |
friends | -0.013 |
ogs | -0.013 |
joy | -0.012 |
listener | -0.012 |
itting | -0.012 |
Token | So |
Token ID | 2396 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Nib | +0.027 |
extingu | +0.024 |
Flor | +0.024 |
Fl | +0.023 |
Rudolph | +0.023 |
Neg logit contributions | |
itting | -0.022 |
listener | -0.022 |
friends | -0.021 |
team | -0.021 |
oom | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
itting | +0.017 |
ops | +0.015 |
akes | +0.015 |
joy | +0.015 |
ogs | +0.015 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.006 |
Das | -0.006 |
Sunny | -0.006 |
Nib | -0.006 |
Token | family |
Token ID | 1641 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
itting | +0.035 |
working | +0.030 |
ogs | +0.030 |
anging | +0.030 |
joy | +0.030 |
Neg logit contributions | |
Rudolph | -0.045 |
Fl | -0.042 |
Frost | -0.042 |
Sunny | -0.041 |
Rudy | -0.040 |
Token | ran |
Token ID | 4966 |
Feature activation | -7.79e-03 |
Pos logit contributions | |
joy | +0.017 |
itting | +0.017 |
listener | +0.017 |
working | +0.017 |
ogs | +0.016 |
Neg logit contributions | |
Fl | -0.017 |
Rudolph | -0.017 |
Fl | -0.016 |
Sn | -0.016 |
Frost | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
Rudolph | +0.015 |
Fl | +0.015 |
Nib | +0.015 |
Das | +0.015 |
Sn | +0.014 |
Neg logit contributions | |
listener | -0.009 |
working | -0.009 |
joy | -0.009 |
friends | -0.009 |
ogs | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Fl | +0.040 |
Rudolph | +0.040 |
Frost | +0.038 |
Sn | +0.037 |
Nib | +0.037 |
Neg logit contributions | |
itting | -0.062 |
listener | -0.062 |
working | -0.061 |
joy | -0.060 |
ogs | -0.058 |
Token | basement |
Token ID | 17012 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Rudolph | +0.080 |
Nib | +0.078 |
Fl | +0.078 |
Fl | +0.077 |
Sn | +0.077 |
Neg logit contributions | |
listener | -0.055 |
working | -0.054 |
joy | -0.052 |
itting | -0.050 |
ogs | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
Rudolph | +0.192 |
Fl | +0.190 |
Sn | +0.183 |
Nib | +0.182 |
Fl | +0.179 |
Neg logit contributions | |
listener | -0.169 |
joy | -0.165 |
itting | -0.164 |
working | -0.164 |
ogs | -0.159 |
Token | where |
Token ID | 810 |
Feature activation | -9.64e-04 |
Pos logit contributions | |
listener | +0.011 |
joy | +0.011 |
working | +0.011 |
itting | +0.010 |
ogs | +0.010 |
Neg logit contributions | |
Rudolph | -0.009 |
Fl | -0.008 |
Nib | -0.008 |
Fl | -0.008 |
Sn | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +7.64e-03 |
Pos logit contributions | |
Fl | +0.001 |
Rudolph | +0.001 |
Frost | +0.001 |
Sunny | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
joy | -0.002 |
itting | -0.002 |
listener | -0.002 |
working | -0.002 |
ogs | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
listener | +0.011 |
joy | +0.011 |
itting | +0.010 |
ogs | +0.010 |
working | +0.010 |
Neg logit contributions | |
Rudolph | -0.014 |
Fl | -0.014 |
Nib | -0.013 |
Sn | -0.013 |
Frost | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
listener | +0.028 |
itting | +0.027 |
working | +0.027 |
joy | +0.027 |
ogs | +0.026 |
Neg logit contributions | |
Rudolph | -0.024 |
Fl | -0.023 |
Nib | -0.022 |
Sn | -0.022 |
Frost | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Rudolph | +0.020 |
Nib | +0.019 |
Fl | +0.019 |
Sn | +0.019 |
extingu | +0.018 |
Neg logit contributions | |
listener | -0.019 |
joy | -0.019 |
itting | -0.019 |
ogs | -0.019 |
working | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Rudolph | +0.028 |
Nib | +0.027 |
extingu | +0.027 |
Flor | +0.027 |
Fl | +0.027 |
Neg logit contributions | |
itting | -0.026 |
listener | -0.026 |
working | -0.026 |
ogs | -0.025 |
runner | -0.024 |
Token | soldier |
Token ID | 10686 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Rudolph | +0.021 |
Fl | +0.021 |
Nib | +0.021 |
Sn | +0.020 |
Fl | +0.020 |
Neg logit contributions | |
listener | -0.021 |
working | -0.021 |
joy | -0.021 |
itting | -0.020 |
ogs | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
Rudolph | +0.079 |
Fl | +0.076 |
Nib | +0.074 |
Sn | +0.073 |
Fl | +0.073 |
Neg logit contributions | |
listener | -0.068 |
joy | -0.068 |
itting | -0.068 |
working | -0.066 |
ogs | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
Fl | +0.005 |
Rudolph | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
listener | -0.003 |
working | -0.003 |
joy | -0.003 |
ogs | -0.003 |
itting | -0.003 |
Token | war |
Token ID | 1175 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Rudolph | +0.042 |
Fl | +0.041 |
Fl | +0.040 |
Nib | +0.040 |
Sn | +0.040 |
Neg logit contributions | |
listener | -0.048 |
joy | -0.047 |
working | -0.047 |
itting | -0.046 |
ogs | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Rudolph | +0.195 |
Fl | +0.189 |
Nib | +0.186 |
Sn | +0.186 |
Fl | +0.185 |
Neg logit contributions | |
listener | -0.169 |
joy | -0.166 |
working | -0.165 |
itting | -0.162 |
ogs | -0.159 |
Token | fought |
Token ID | 8350 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Rudolph | +0.033 |
Fl | +0.032 |
Fl | +0.032 |
Sn | +0.032 |
Nib | +0.032 |
Neg logit contributions | |
listener | -0.032 |
working | -0.031 |
joy | -0.031 |
itting | -0.030 |
ogs | -0.030 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
Rudolph | +0.025 |
Fl | +0.024 |
Sn | +0.023 |
Nib | +0.023 |
Fl | +0.023 |
Neg logit contributions | |
listener | -0.036 |
joy | -0.036 |
itting | -0.036 |
working | -0.035 |
ogs | -0.034 |
Token | ly |
Token ID | 306 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Rudolph | +0.002 |
Fl | +0.002 |
Sn | +0.002 |
Nib | +0.002 |
Fl | +0.002 |
Neg logit contributions | |
itting | -0.002 |
listener | -0.002 |
joy | -0.002 |
working | -0.002 |
ogs | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
Rudolph | +0.017 |
Fl | +0.017 |
Sn | +0.016 |
extingu | +0.016 |
Frost | +0.015 |
Neg logit contributions | |
itting | -0.018 |
listener | -0.018 |
joy | -0.018 |
working | -0.017 |
ogs | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
itting | +0.014 |
listener | +0.013 |
working | +0.013 |
joy | +0.013 |
oom | +0.012 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.012 |
Nib | -0.011 |
Sunny | -0.011 |
Rudy | -0.011 |
Token | dad |
Token ID | 9955 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
itting | +0.040 |
working | +0.038 |
listener | +0.037 |
ogs | +0.037 |
akes | +0.035 |
Neg logit contributions | |
Rudolph | -0.051 |
Fl | -0.047 |
Rudy | -0.045 |
Frost | -0.045 |
Sn | -0.045 |
Token | went |
Token ID | 1816 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
joy | +0.008 |
listener | +0.008 |
itting | +0.008 |
ogs | +0.007 |
working | +0.007 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.006 |
Sn | -0.006 |
extingu | -0.006 |
Frost | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
Fl | +0.040 |
Rudolph | +0.039 |
Fl | +0.039 |
Nib | +0.039 |
Sn | +0.038 |
Neg logit contributions | |
listener | -0.023 |
joy | -0.023 |
ogs | -0.023 |
working | -0.022 |
friends | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Fl | +0.057 |
Rudolph | +0.056 |
Nib | +0.054 |
Sn | +0.054 |
Fl | +0.054 |
Neg logit contributions | |
joy | -0.057 |
listener | -0.056 |
working | -0.055 |
ogs | -0.054 |
friends | -0.052 |
Token | port |
Token ID | 2493 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Fl | +0.096 |
Fl | +0.093 |
Nib | +0.091 |
ified | +0.091 |
Sn | +0.091 |
Neg logit contributions | |
working | -0.053 |
listener | -0.051 |
friends | -0.050 |
friend | -0.047 |
painter | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
Rudolph | +0.173 |
Fl | +0.165 |
Nib | +0.158 |
Sn | +0.158 |
extingu | +0.158 |
Neg logit contributions | |
listener | -0.188 |
itting | -0.184 |
joy | -0.184 |
working | -0.182 |
ogs | -0.173 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
Fl | +0.045 |
ified | +0.042 |
Rudolph | +0.042 |
Fl | +0.042 |
Sn | +0.042 |
Neg logit contributions | |
listener | -0.018 |
working | -0.018 |
friends | -0.018 |
joy | -0.017 |
ogs | -0.017 |
Token | up |
Token ID | 510 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
listener | +0.024 |
joy | +0.023 |
itting | +0.023 |
working | +0.023 |
ogs | +0.022 |
Neg logit contributions | |
Rudolph | -0.013 |
Fl | -0.012 |
Nib | -0.012 |
Sn | -0.012 |
Fl | -0.012 |
Token | Uncle |
Token ID | 23169 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
Rudolph | +0.039 |
Fl | +0.038 |
Nib | +0.037 |
Sn | +0.036 |
Frost | +0.035 |
Neg logit contributions | |
listener | -0.048 |
itting | -0.047 |
working | -0.046 |
joy | -0.046 |
ogs | -0.044 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
Rudolph | +0.043 |
Fl | +0.042 |
Nib | +0.041 |
Sn | +0.041 |
Fl | +0.041 |
Neg logit contributions | |
listener | -0.044 |
joy | -0.044 |
working | -0.043 |
itting | -0.043 |
ogs | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
Rudolph | +0.028 |
Sn | +0.026 |
Fl | +0.026 |
Nib | +0.026 |
Fl | +0.026 |
Neg logit contributions | |
listener | -0.038 |
joy | -0.038 |
working | -0.038 |
itting | -0.037 |
ogs | -0.036 |
Token | very |
Token ID | 845 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
Rudolph | +0.045 |
Fl | +0.045 |
Fl | +0.043 |
Sn | +0.043 |
Frost | +0.042 |
Neg logit contributions | |
ogs | -0.044 |
itting | -0.043 |
joy | -0.042 |
working | -0.042 |
ogged | -0.042 |
Token | furry |
Token ID | 40857 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ogs | +0.004 |
joy | +0.004 |
itting | +0.004 |
ogged | +0.003 |
ops | +0.003 |
Neg logit contributions | |
Fl | -0.003 |
Rudolph | -0.003 |
Nib | -0.003 |
Frost | -0.003 |
Flor | -0.003 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
itting | +0.036 |
joy | +0.036 |
working | +0.036 |
ogs | +0.035 |
listener | +0.035 |
Neg logit contributions | |
Fl | -0.041 |
Rudolph | -0.041 |
Nib | -0.039 |
Sn | -0.039 |
Fl | -0.038 |
Token | called |
Token ID | 1444 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
Rudolph | +0.006 |
Fl | +0.006 |
Nib | +0.006 |
Sn | +0.006 |
Fl | +0.006 |
Neg logit contributions | |
listener | -0.006 |
working | -0.006 |
joy | -0.005 |
itting | -0.005 |
ogs | -0.005 |
Token | Midnight |
Token ID | 27960 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Rudolph | +0.047 |
extingu | +0.044 |
Fl | +0.043 |
sc | +0.042 |
mant | +0.042 |
Neg logit contributions | |
working | -0.070 |
joy | -0.069 |
listener | -0.069 |
ogs | -0.068 |
itting | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Rudolph | +0.243 |
Fl | +0.235 |
Nib | +0.234 |
Sn | +0.231 |
Fl | +0.231 |
Neg logit contributions | |
listener | -0.111 |
working | -0.107 |
joy | -0.104 |
itting | -0.103 |
friends | -0.100 |
Token | Midnight |
Token ID | 27960 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
extingu | +0.025 |
fire | +0.022 |
works | +0.022 |
ured | +0.022 |
mant | +0.021 |
Neg logit contributions | |
joy | -0.028 |
working | -0.027 |
listener | -0.026 |
friends | -0.026 |
runner | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
extingu | +0.176 |
Rudolph | +0.175 |
Sn | +0.170 |
Nib | +0.170 |
mant | +0.167 |
Neg logit contributions | |
listener | -0.065 |
working | -0.065 |
friends | -0.060 |
joy | -0.057 |
itting | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
listener | +0.007 |
joy | +0.007 |
working | +0.007 |
itting | +0.007 |
ogs | +0.007 |
Neg logit contributions | |
Rudolph | -0.005 |
Fl | -0.005 |
Nib | -0.005 |
Sn | -0.005 |
Fl | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
listener | +0.009 |
joy | +0.009 |
ogs | +0.009 |
itting | +0.009 |
working | +0.009 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.011 |
Sn | -0.010 |
Nib | -0.010 |
Fl | -0.010 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Rudolph | +0.029 |
Fl | +0.028 |
Sn | +0.027 |
Nib | +0.027 |
Fl | +0.026 |
Neg logit contributions | |
listener | -0.026 |
joy | -0.025 |
itting | -0.025 |
ogs | -0.024 |
working | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
working | +0.039 |
joy | +0.038 |
listener | +0.038 |
friends | +0.037 |
ogs | +0.034 |
Neg logit contributions | |
Fl | -0.082 |
Rudolph | -0.081 |
Sn | -0.079 |
Nib | -0.079 |
extingu | -0.078 |
Token | show |
Token ID | 905 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
listener | +0.012 |
joy | +0.012 |
working | +0.011 |
itting | +0.011 |
ogs | +0.011 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.011 |
Nib | -0.010 |
Sn | -0.010 |
Fl | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | +4.77e-03 |
Pos logit contributions | |
extingu | +0.047 |
Fl | +0.047 |
fire | +0.046 |
sc | +0.044 |
Das | +0.043 |
Neg logit contributions | |
friends | -0.043 |
listener | -0.040 |
ogs | -0.039 |
working | -0.039 |
joy | -0.038 |
Token | friend |
Token ID | 1545 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
itting | +0.006 |
listener | +0.006 |
working | +0.005 |
joy | +0.005 |
ogs | +0.005 |
Neg logit contributions | |
Fl | -0.010 |
Rudolph | -0.009 |
Sn | -0.009 |
Nib | -0.009 |
Frost | -0.009 |
Token | Midnight |
Token ID | 27960 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Rudolph | +0.007 |
Fl | +0.007 |
Nib | +0.007 |
Sn | +0.007 |
Fl | +0.007 |
Neg logit contributions | |
listener | -0.007 |
joy | -0.007 |
working | -0.007 |
itting | -0.006 |
ogs | -0.006 |
Token | something |
Token ID | 1223 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
Rudolph | +0.195 |
Fl | +0.193 |
Fl | +0.187 |
Sn | +0.187 |
Nib | +0.186 |
Neg logit contributions | |
listener | -0.160 |
joy | -0.158 |
working | -0.155 |
itting | -0.152 |
ogs | -0.151 |
Token | special |
Token ID | 2041 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
Rudolph | +0.060 |
Nib | +0.058 |
Fl | +0.058 |
Sn | +0.057 |
Fl | +0.056 |
Neg logit contributions | |
listener | -0.039 |
working | -0.039 |
itting | -0.038 |
joy | -0.038 |
friends | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
Rudolph | +0.017 |
Fl | +0.016 |
Nib | +0.016 |
Fl | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
listener | -0.011 |
joy | -0.010 |
working | -0.010 |
itting | -0.010 |
ogs | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +3.34e-04 |
Pos logit contributions | |
extingu | +0.009 |
Frost | +0.008 |
Fl | +0.008 |
Nib | +0.008 |
Rudolph | +0.008 |
Neg logit contributions | |
listener | -0.005 |
joy | -0.005 |
working | -0.005 |
ogs | -0.005 |
friends | -0.005 |
Token | took |
Token ID | 1718 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
listener | +0.001 |
joy | +0.000 |
working | +0.000 |
itting | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Sn | -0.001 |
Nib | -0.001 |
Fl | -0.001 |
Token | mouse |
Token ID | 10211 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
itting | +0.012 |
ogs | +0.012 |
listener | +0.012 |
joy | +0.012 |
ogged | +0.012 |
Neg logit contributions | |
Fl | -0.008 |
Rudolph | -0.008 |
Nib | -0.007 |
Fl | -0.007 |
Sn | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
Fl | +0.040 |
Rudolph | +0.038 |
Nib | +0.038 |
Frost | +0.037 |
Fl | +0.037 |
Neg logit contributions | |
joy | -0.050 |
listener | -0.050 |
itting | -0.049 |
runner | -0.047 |
working | -0.047 |
Token | very |
Token ID | 845 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.008 |
Nib | +0.008 |
Sn | +0.008 |
Fl | +0.008 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
working | -0.010 |
itting | -0.010 |
ogs | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Fl | +0.016 |
Rudolph | +0.016 |
Nib | +0.016 |
Frost | +0.015 |
Fl | +0.015 |
Neg logit contributions | |
joy | -0.012 |
ogs | -0.012 |
itting | -0.012 |
listener | -0.012 |
working | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
working | +0.037 |
listener | +0.037 |
itting | +0.037 |
ogs | +0.036 |
oom | +0.036 |
Neg logit contributions | |
Fl | -0.032 |
Rudolph | -0.030 |
from | -0.029 |
Sn | -0.029 |
Frost | -0.028 |
Token | |
Token ID | 220 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
listener | +0.013 |
working | +0.013 |
joy | +0.013 |
itting | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.009 |
Fl | -0.008 |
Nib | -0.008 |
Sn | -0.008 |
Fl | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
listener | +0.130 |
joy | +0.127 |
working | +0.127 |
itting | +0.125 |
ogs | +0.122 |
Neg logit contributions | |
Rudolph | -0.096 |
Fl | -0.094 |
Nib | -0.091 |
Sn | -0.091 |
Fl | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
Rudolph | +0.005 |
extingu | +0.005 |
Nib | +0.005 |
Fl | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
listener | -0.005 |
joy | -0.005 |
ogs | -0.005 |
itting | -0.005 |
working | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
Rudolph | +0.009 |
Fl | +0.009 |
Nib | +0.008 |
Sn | +0.008 |
Fl | +0.008 |
Neg logit contributions | |
listener | -0.014 |
joy | -0.013 |
working | -0.013 |
itting | -0.013 |
ogs | -0.013 |
Token | witch |
Token ID | 16365 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Sn | +0.003 |
Fl | +0.003 |
Neg logit contributions | |
listener | -0.004 |
joy | -0.004 |
working | -0.004 |
itting | -0.004 |
ogs | -0.004 |
Token | continued |
Token ID | 3767 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
Rudolph | +0.026 |
Fl | +0.025 |
Nib | +0.024 |
Fl | +0.024 |
Sn | +0.024 |
Neg logit contributions | |
listener | -0.028 |
joy | -0.027 |
itting | -0.027 |
working | -0.027 |
ogs | -0.027 |
Token | little |
Token ID | 1310 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
itting | +0.013 |
ogs | +0.012 |
working | +0.012 |
ogged | +0.012 |
joy | +0.012 |
Neg logit contributions | |
Rudolph | -0.013 |
Fl | -0.012 |
Flor | -0.012 |
Fl | -0.012 |
Sunny | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
Fl | +0.015 |
Flor | +0.015 |
Sunny | +0.014 |
Rudolph | +0.014 |
Nib | +0.013 |
Neg logit contributions | |
itting | -0.014 |
ogs | -0.013 |
ogged | -0.013 |
udding | -0.013 |
working | -0.012 |
Token | stopped |
Token ID | 5025 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
Fl | +0.010 |
Rudolph | +0.010 |
Sn | +0.010 |
Fl | +0.010 |
Flor | +0.009 |
Neg logit contributions | |
working | -0.014 |
itting | -0.014 |
listener | -0.013 |
joy | -0.013 |
ogs | -0.013 |
Token | weeping |
Token ID | 45705 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
Fl | +0.007 |
Rudolph | +0.007 |
Nib | +0.007 |
Sn | +0.007 |
Flor | +0.006 |
Neg logit contributions | |
listener | -0.008 |
working | -0.008 |
ogs | -0.007 |
itting | -0.007 |
oom | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.03e-03 |
Pos logit contributions | |
Rudolph | +0.040 |
Fl | +0.040 |
Sn | +0.038 |
Nib | +0.038 |
Fl | +0.037 |
Neg logit contributions | |
listener | -0.035 |
itting | -0.034 |
working | -0.034 |
joy | -0.033 |
ogs | -0.032 |
Token | |
Token ID | 220 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
listener | +0.014 |
working | +0.014 |
joy | +0.014 |
itting | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.011 |
Sn | -0.011 |
Nib | -0.011 |
Fl | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e-04 |
Pos logit contributions | |
listener | +0.138 |
working | +0.136 |
joy | +0.134 |
itting | +0.131 |
ogs | +0.128 |
Neg logit contributions | |
Rudolph | -0.096 |
Fl | -0.095 |
Sn | -0.091 |
Nib | -0.091 |
Fl | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
listener | +0.001 |
joy | +0.001 |
ogs | +0.001 |
itting | +0.001 |
working | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Nib | -0.000 |
Fl | -0.000 |
extingu | -0.000 |
Sn | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -8.66e-05 |
Pos logit contributions | |
Rudolph | +0.004 |
Fl | +0.004 |
Nib | +0.004 |
Sn | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
listener | -0.007 |
joy | -0.007 |
working | -0.007 |
itting | -0.007 |
ogs | -0.007 |
Token | grass |
Token ID | 8701 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Rudolph | +0.000 |
Fl | +0.000 |
Fl | +0.000 |
Nib | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
itting | -0.000 |
listener | -0.000 |
working | -0.000 |
ogs | -0.000 |
joy | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
listener | +0.049 |
working | +0.048 |
joy | +0.048 |
ogs | +0.047 |
itting | +0.046 |
Neg logit contributions | |
Fl | -0.039 |
Rudolph | -0.038 |
Fl | -0.037 |
Nib | -0.037 |
Sn | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Fl | +0.027 |
Rudolph | +0.027 |
Sn | +0.026 |
Fl | +0.025 |
Nib | +0.025 |
Neg logit contributions | |
joy | -0.026 |
listener | -0.025 |
itting | -0.025 |
working | -0.024 |
ogs | -0.024 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
listener | +0.045 |
working | +0.044 |
joy | +0.044 |
itting | +0.043 |
ogs | +0.042 |
Neg logit contributions | |
Rudolph | -0.058 |
Fl | -0.056 |
Sn | -0.055 |
Fl | -0.055 |
Nib | -0.055 |
Token | bad |
Token ID | 2089 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
Rudolph | +0.007 |
Fl | +0.007 |
Fl | +0.007 |
Sn | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
listener | -0.006 |
joy | -0.006 |
working | -0.006 |
ogs | -0.006 |
itting | -0.006 |
Token | things |
Token ID | 1243 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
Rudolph | +0.095 |
Fl | +0.093 |
Nib | +0.088 |
Sunny | +0.086 |
Sn | +0.086 |
Neg logit contributions | |
itting | -0.084 |
listener | -0.074 |
joy | -0.071 |
working | -0.070 |
ite | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
listener | +0.033 |
working | +0.032 |
joy | +0.032 |
itting | +0.032 |
ogs | +0.031 |
Neg logit contributions | |
Rudolph | -0.038 |
Fl | -0.037 |
Nib | -0.037 |
Fl | -0.037 |
Sn | -0.036 |
Token | as |
Token ID | 355 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
listener | +0.035 |
joy | +0.035 |
working | +0.035 |
itting | +0.034 |
ogs | +0.034 |
Neg logit contributions | |
Rudolph | -0.027 |
Fl | -0.026 |
Sn | -0.025 |
Nib | -0.025 |
Fl | -0.025 |
Token | long |
Token ID | 890 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
itting | +0.123 |
joy | +0.121 |
listener | +0.119 |
ogged | +0.117 |
ogs | +0.117 |
Neg logit contributions | |
Fl | -0.110 |
Rudolph | -0.108 |
Nib | -0.100 |
Sn | -0.099 |
Frost | -0.099 |
Token | as |
Token ID | 355 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
listener | +0.111 |
itting | +0.111 |
joy | +0.108 |
working | +0.103 |
ogs | +0.102 |
Neg logit contributions | |
Rudolph | -0.091 |
Fl | -0.089 |
Sn | -0.084 |
Nib | -0.084 |
Fl | -0.081 |
Token | you |
Token ID | 345 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
itting | +0.151 |
joy | +0.150 |
listener | +0.149 |
ogs | +0.143 |
working | +0.141 |
Neg logit contributions | |
Fl | -0.117 |
Rudolph | -0.116 |
Nib | -0.107 |
Sn | -0.105 |
Frost | -0.104 |
Token | don |
Token ID | 836 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
joy | +0.076 |
listener | +0.075 |
itting | +0.072 |
ogs | +0.070 |
working | +0.066 |
Neg logit contributions | |
Fl | -0.097 |
Nib | -0.096 |
Rudolph | -0.096 |
Frost | -0.092 |
Sn | -0.091 |
Token | 't |
Token ID | 470 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
listener | +0.009 |
working | +0.009 |
joy | +0.009 |
itting | +0.008 |
ogs | +0.008 |
Neg logit contributions | |
Rudolph | -0.007 |
Fl | -0.006 |
Nib | -0.006 |
Fl | -0.006 |
Sn | -0.006 |
Token | man |
Token ID | 582 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
ogs | +0.052 |
ogged | +0.050 |
itting | +0.049 |
oom | +0.047 |
listener | +0.047 |
Neg logit contributions | |
Rudolph | -0.049 |
extingu | -0.048 |
Fl | -0.047 |
Nib | -0.046 |
Fl | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
joy | +0.014 |
ogs | +0.014 |
listener | +0.014 |
itting | +0.014 |
working | +0.014 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.012 |
Nib | -0.011 |
Fl | -0.011 |
Sn | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
listener | +0.002 |
joy | +0.002 |
working | +0.002 |
itting | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.002 |
Fl | -0.002 |
Fl | -0.002 |
Nib | -0.002 |
Sn | -0.002 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
listener | +0.007 |
ogs | +0.007 |
joy | +0.007 |
itting | +0.007 |
working | +0.007 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Frost | -0.006 |
Nib | -0.006 |
Sn | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
listener | +0.024 |
itting | +0.023 |
joy | +0.023 |
working | +0.023 |
ogs | +0.022 |
Neg logit contributions | |
Rudolph | -0.024 |
Fl | -0.023 |
Sn | -0.022 |
Nib | -0.022 |
Frost | -0.021 |
Token | |
Token ID | 220 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
listener | +0.015 |
joy | +0.014 |
working | +0.014 |
itting | +0.014 |
ogs | +0.014 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.012 |
Nib | -0.012 |
Sn | -0.012 |
Fl | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
listener | +0.138 |
working | +0.135 |
joy | +0.134 |
itting | +0.131 |
ogs | +0.127 |
Neg logit contributions | |
Rudolph | -0.091 |
Fl | -0.090 |
Nib | -0.086 |
Sn | -0.085 |
Fl | -0.084 |
Token | John |
Token ID | 7554 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
listener | +0.002 |
joy | +0.002 |
itting | +0.002 |
working | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.002 |
Fl | -0.002 |
Nib | -0.002 |
Sn | -0.002 |
Fl | -0.002 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
listener | +0.027 |
joy | +0.027 |
itting | +0.027 |
working | +0.027 |
ogs | +0.026 |
Neg logit contributions | |
Rudolph | -0.028 |
Fl | -0.027 |
Nib | -0.027 |
Sn | -0.026 |
Fl | -0.026 |
Token | away |
Token ID | 1497 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
listener | +0.029 |
joy | +0.029 |
working | +0.029 |
ogs | +0.028 |
itting | +0.028 |
Neg logit contributions | |
Rudolph | -0.021 |
Fl | -0.020 |
Fl | -0.020 |
Sn | -0.020 |
Nib | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
Rudolph | +0.055 |
Fl | +0.053 |
Fl | +0.052 |
Nib | +0.052 |
Sn | +0.052 |
Neg logit contributions | |
listener | -0.054 |
joy | -0.053 |
working | -0.052 |
itting | -0.051 |
ogs | -0.050 |
Token | sad |
Token ID | 6507 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
Rudolph | +0.012 |
Fl | +0.012 |
Sn | +0.011 |
Nib | +0.011 |
Fl | +0.011 |
Neg logit contributions | |
listener | -0.009 |
joy | -0.009 |
working | -0.008 |
itting | -0.008 |
ogs | -0.008 |
Token | because |
Token ID | 780 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Fl | +0.036 |
Rudolph | +0.035 |
Sn | +0.034 |
Nib | +0.033 |
from | +0.032 |
Neg logit contributions | |
listener | -0.042 |
working | -0.041 |
itting | -0.040 |
joy | -0.040 |
ogs | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
itting | +0.037 |
listener | +0.036 |
joy | +0.035 |
working | +0.035 |
oom | +0.034 |
Neg logit contributions | |
Fl | -0.055 |
Rudolph | -0.053 |
Sn | -0.052 |
Frost | -0.051 |
Nib | -0.050 |
Token | couldn |
Token ID | 3521 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
ogs | +0.052 |
joy | +0.051 |
itting | +0.051 |
listener | +0.050 |
working | +0.047 |
Neg logit contributions | |
Rudolph | -0.045 |
Fl | -0.044 |
Sn | -0.042 |
Fl | -0.042 |
Frost | -0.040 |
Token | 't |
Token ID | 470 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
listener | +0.016 |
joy | +0.016 |
working | +0.016 |
itting | +0.016 |
ogs | +0.016 |
Neg logit contributions | |
Rudolph | -0.012 |
Fl | -0.011 |
Nib | -0.011 |
Sn | -0.011 |
Fl | -0.011 |
Token | play |
Token ID | 711 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
joy | +0.015 |
itting | +0.014 |
listener | +0.014 |
ogs | +0.014 |
working | +0.013 |
Neg logit contributions | |
Rudolph | -0.017 |
Fl | -0.017 |
Sn | -0.016 |
Fl | -0.016 |
Nib | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
listener | +0.143 |
itting | +0.140 |
joy | +0.140 |
working | +0.139 |
ogs | +0.136 |
Neg logit contributions | |
Rudolph | -0.096 |
Fl | -0.094 |
Sn | -0.090 |
Fl | -0.089 |
Nib | -0.088 |
Token | guitar |
Token ID | 10047 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
itting | +0.041 |
listener | +0.040 |
joy | +0.039 |
ogs | +0.038 |
ogged | +0.037 |
Neg logit contributions | |
Rudolph | -0.035 |
Fl | -0.032 |
Sn | -0.031 |
Sunny | -0.030 |
Rudy | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
Fl | +0.060 |
Rudolph | +0.058 |
Sn | +0.055 |
Nib | +0.054 |
Fl | +0.053 |
Neg logit contributions | |
joy | -0.077 |
listener | -0.077 |
itting | -0.077 |
working | -0.073 |
ule | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +8.68e-03 |
Pos logit contributions | |
Rudolph | +0.031 |
Fl | +0.030 |
Nib | +0.030 |
Fl | +0.029 |
Sn | +0.029 |
Neg logit contributions | |
listener | -0.035 |
joy | -0.034 |
working | -0.034 |
itting | -0.033 |
ogs | -0.033 |
Token | forest |
Token ID | 8222 |
Feature activation | -4.80e-03 |
Pos logit contributions | |
listener | +0.011 |
joy | +0.011 |
working | +0.011 |
itting | +0.011 |
ogs | +0.010 |
Neg logit contributions | |
Rudolph | -0.016 |
Fl | -0.016 |
Nib | -0.016 |
Sn | -0.016 |
Fl | -0.015 |
Token | � |
Token ID | 95 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.017 |
Sn | +0.017 |
Nib | +0.017 |
Fl | +0.016 |
Neg logit contributions | |
listener | -0.019 |
working | -0.019 |
joy | -0.019 |
itting | -0.019 |
ogs | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Rudolph | +0.047 |
Fl | +0.045 |
Nib | +0.044 |
Sn | +0.044 |
Fl | +0.044 |
Neg logit contributions | |
listener | -0.062 |
joy | -0.061 |
working | -0.060 |
itting | -0.060 |
ogs | -0.059 |
Token | � |
Token ID | 129 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
Fl | +0.015 |
Fl | +0.014 |
Frost | +0.014 |
Sn | +0.014 |
Rudolph | +0.014 |
Neg logit contributions | |
listener | -0.023 |
working | -0.021 |
iness | -0.020 |
itting | -0.020 |
runner | -0.019 |
Token | � |
Token ID | 241 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Rudolph | +0.015 |
Fl | +0.014 |
Nib | +0.014 |
Sn | +0.014 |
Fl | +0.014 |
Neg logit contributions | |
listener | -0.014 |
working | -0.013 |
joy | -0.013 |
itting | -0.013 |
ogs | -0.013 |
Token | Hey |
Token ID | 10814 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ogs | +0.064 |
listener | +0.064 |
itting | +0.063 |
working | +0.062 |
ies | +0.062 |
Neg logit contributions | |
Fl | -0.048 |
Sn | -0.047 |
Fl | -0.047 |
Rudolph | -0.046 |
Das | -0.044 |
Token | ! |
Token ID | 0 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
Fl | +0.059 |
Rudolph | +0.059 |
Sn | +0.057 |
Fl | +0.056 |
Nib | +0.055 |
Neg logit contributions | |
listener | -0.052 |
itting | -0.050 |
working | -0.050 |
joy | -0.049 |
ogs | -0.049 |
Token | I |
Token ID | 314 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
joy | +0.010 |
listener | +0.010 |
itting | +0.009 |
ogs | +0.009 |
working | +0.009 |
Neg logit contributions | |
Rudolph | -0.008 |
Fl | -0.007 |
Nib | -0.007 |
Fl | -0.007 |
extingu | -0.007 |
Token | can |
Token ID | 460 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
joy | +0.027 |
listener | +0.026 |
ogs | +0.026 |
working | +0.026 |
itting | +0.026 |
Neg logit contributions | |
Fl | -0.032 |
Nib | -0.032 |
Rudolph | -0.032 |
Sn | -0.031 |
Fl | -0.031 |
Token | help |
Token ID | 1037 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.033 |
Sn | +0.032 |
Frost | +0.031 |
Nib | +0.031 |
Neg logit contributions | |
joy | -0.048 |
listener | -0.046 |
itting | -0.044 |
ogs | -0.042 |
working | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
Rudolph | +0.011 |
Fl | +0.011 |
Sn | +0.011 |
Nib | +0.011 |
Fl | +0.011 |
Neg logit contributions | |
listener | -0.014 |
joy | -0.013 |
itting | -0.013 |
working | -0.013 |
ogs | -0.013 |
Token | â |
Token ID | 22940 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
joy | +0.006 |
listener | +0.006 |
itting | +0.006 |
ogs | +0.006 |
working | +0.006 |
Neg logit contributions | |
Rudolph | -0.005 |
extingu | -0.005 |
Fl | -0.005 |
Nib | -0.005 |
versa | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
joy | +0.027 |
listener | +0.026 |
itting | +0.026 |
reader | +0.025 |
ogged | +0.024 |
Neg logit contributions | |
Fl | -0.017 |
Frost | -0.014 |
Fl | -0.014 |
Nib | -0.014 |
Sn | -0.013 |
Token | ow |
Token ID | 12334 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Rudolph | +0.022 |
Nib | +0.020 |
Fl | +0.020 |
Sn | +0.020 |
Fl | +0.020 |
Neg logit contributions | |
listener | -0.024 |
joy | -0.023 |
working | -0.023 |
itting | -0.023 |
ogs | -0.022 |
Token | ! |
Token ID | 0 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
joy | +0.058 |
listener | +0.056 |
itting | +0.053 |
reader | +0.052 |
ogged | +0.050 |
Neg logit contributions | |
Fl | -0.041 |
Fl | -0.038 |
Frost | -0.037 |
Rudolph | -0.036 |
Sunny | -0.035 |
Token | That |
Token ID | 1320 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
Rudolph | +0.002 |
versa | +0.002 |
Nib | +0.002 |
Das | +0.002 |
Fl | +0.002 |
Neg logit contributions | |
itting | -0.002 |
listener | -0.002 |
joy | -0.002 |
working | -0.002 |
ogs | -0.002 |
Token | hurts |
Token ID | 20406 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
listener | +0.011 |
working | +0.011 |
joy | +0.011 |
itting | +0.010 |
ogs | +0.010 |
Neg logit contributions | |
Rudolph | -0.009 |
Fl | -0.008 |
Nib | -0.008 |
Sn | -0.008 |
Fl | -0.008 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
Rudolph | +0.073 |
Nib | +0.071 |
Sn | +0.068 |
Das | +0.068 |
Flor | +0.068 |
Neg logit contributions | |
listener | -0.047 |
working | -0.046 |
ogs | -0.046 |
itting | -0.046 |
friends | -0.045 |
Token | Ben |
Token ID | 3932 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
listener | +0.006 |
joy | +0.006 |
working | +0.006 |
ogs | +0.006 |
itting | +0.006 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Sn | -0.006 |
Fl | -0.006 |
Nib | -0.006 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.37e-04 |
Pos logit contributions | |
Rudolph | +0.010 |
Fl | +0.010 |
Sn | +0.009 |
Nib | +0.009 |
Das | +0.009 |
Neg logit contributions | |
listener | -0.008 |
friends | -0.008 |
ogs | -0.007 |
joy | -0.007 |
working | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
listener | +0.000 |
joy | +0.000 |
working | +0.000 |
itting | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Nib | -0.000 |
Fl | -0.000 |
Das | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-03 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.008 |
versa | +0.008 |
Nib | +0.008 |
extingu | +0.008 |
Neg logit contributions | |
joy | -0.007 |
listener | -0.006 |
friends | -0.006 |
ogs | -0.006 |
itting | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
Rudolph | +0.010 |
extingu | +0.010 |
Sn | +0.010 |
Nib | +0.010 |
versa | +0.010 |
Neg logit contributions | |
ogs | -0.008 |
joy | -0.008 |
friends | -0.008 |
listener | -0.008 |
itting | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
listener | +0.050 |
joy | +0.049 |
working | +0.049 |
itting | +0.048 |
ogs | +0.047 |
Neg logit contributions | |
Rudolph | -0.047 |
Fl | -0.045 |
Fl | -0.044 |
Nib | -0.044 |
Sn | -0.044 |
Token | coffee |
Token ID | 6891 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
Fl | +0.025 |
Rudolph | +0.025 |
Sn | +0.024 |
Nib | +0.022 |
Rudy | +0.022 |
Neg logit contributions | |
itting | -0.051 |
listener | -0.050 |
joy | -0.050 |
working | -0.050 |
ogs | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Rudolph | +0.125 |
Fl | +0.123 |
Sn | +0.120 |
Fl | +0.118 |
Nib | +0.117 |
Neg logit contributions | |
listener | -0.103 |
joy | -0.103 |
itting | -0.100 |
working | -0.100 |
ogs | -0.097 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
versa | +0.017 |
Nib | +0.017 |
Das | +0.017 |
extingu | +0.017 |
Neg logit contributions | |
listener | -0.012 |
itting | -0.012 |
working | -0.012 |
joy | -0.012 |
ogs | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
Rudolph | +0.039 |
Fl | +0.038 |
Nib | +0.037 |
Fl | +0.037 |
Sn | +0.037 |
Neg logit contributions | |
listener | -0.034 |
working | -0.033 |
joy | -0.033 |
itting | -0.032 |
ogs | -0.032 |
Token | ran |
Token ID | 4966 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
working | +0.002 |
listener | +0.002 |
itting | +0.002 |
friends | +0.002 |
ogs | +0.002 |
Neg logit contributions | |
Rudolph | -0.002 |
Nib | -0.002 |
Sn | -0.002 |
Das | -0.002 |
Fl | -0.002 |
Token | away |
Token ID | 1497 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
listener | +0.016 |
working | +0.015 |
joy | +0.015 |
itting | +0.015 |
ogs | +0.015 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.010 |
Nib | -0.010 |
Fl | -0.010 |
Sn | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
Rudolph | +0.071 |
Fl | +0.070 |
Sn | +0.068 |
Nib | +0.067 |
Fl | +0.067 |
Neg logit contributions | |
listener | -0.073 |
joy | -0.073 |
itting | -0.072 |
working | -0.071 |
ogs | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.013 |
Fl | +0.013 |
Nib | +0.013 |
Sn | +0.013 |
Neg logit contributions | |
listener | -0.015 |
joy | -0.015 |
working | -0.015 |
itting | -0.015 |
ogs | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
Rudolph | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Sn | +0.005 |
Fl | +0.005 |
Neg logit contributions | |
listener | -0.006 |
joy | -0.006 |
working | -0.006 |
itting | -0.006 |
ogs | -0.006 |
Token | Mom |
Token ID | 29252 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
Rudolph | +0.012 |
Fl | +0.011 |
Nib | +0.011 |
Sn | +0.011 |
Fl | +0.011 |
Neg logit contributions | |
listener | -0.015 |
joy | -0.015 |
working | -0.015 |
itting | -0.015 |
ogs | -0.014 |
Token | something |
Token ID | 1223 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
listener | +0.032 |
itting | +0.031 |
ogs | +0.031 |
working | +0.031 |
joy | +0.031 |
Neg logit contributions | |
Rudolph | -0.021 |
Fl | -0.021 |
Sn | -0.020 |
Nib | -0.020 |
Fl | -0.019 |
Token | terrible |
Token ID | 7818 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
Rudolph | +0.044 |
Sn | +0.044 |
Fl | +0.043 |
Fl | +0.043 |
Nib | +0.042 |
Neg logit contributions | |
listener | -0.033 |
working | -0.033 |
joy | -0.032 |
itting | -0.032 |
friends | -0.031 |
Token | happened |
Token ID | 3022 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.033 |
Nib | +0.032 |
Sn | +0.032 |
Frost | +0.032 |
Neg logit contributions | |
listener | -0.015 |
joy | -0.015 |
itting | -0.014 |
ogs | -0.014 |
working | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
Rudolph | +0.057 |
Fl | +0.056 |
Sn | +0.054 |
Nib | +0.053 |
Fl | +0.053 |
Neg logit contributions | |
listener | -0.050 |
working | -0.047 |
ogs | -0.046 |
itting | -0.045 |
joy | -0.045 |
Token | The |
Token ID | 383 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
joy | +0.006 |
listener | +0.006 |
working | +0.006 |
itting | +0.006 |
ogs | +0.006 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Nib | -0.005 |
Sn | -0.005 |
Fl | -0.005 |
Token | thin |
Token ID | 7888 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
itting | +0.012 |
ogs | +0.012 |
joy | +0.012 |
ogged | +0.012 |
listener | +0.011 |
Neg logit contributions | |
Rudolph | -0.011 |
Sn | -0.010 |
Das | -0.010 |
extingu | -0.010 |
Fl | -0.010 |
Token | motor |
Token ID | 5584 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
joy | +0.050 |
itting | +0.049 |
udding | +0.048 |
ogs | +0.048 |
rav | +0.048 |
Neg logit contributions | |
Rudolph | -0.033 |
extingu | -0.031 |
Das | -0.031 |
Sn | -0.029 |
Fl | -0.028 |
Token | began |
Token ID | 2540 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Sn | +0.003 |
Frost | +0.003 |
Fl | +0.003 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
ogs | -0.004 |
working | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
listener | +0.025 |
itting | +0.024 |
working | +0.024 |
ogs | +0.024 |
joy | +0.023 |
Neg logit contributions | |
Fl | -0.028 |
Rudolph | -0.027 |
Sn | -0.027 |
Nib | -0.026 |
extingu | -0.026 |
Token | break |
Token ID | 2270 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
working | +0.013 |
listener | +0.013 |
joy | +0.013 |
itting | +0.013 |
ogs | +0.013 |
Neg logit contributions | |
Rudolph | -0.013 |
Fl | -0.013 |
Fl | -0.013 |
Nib | -0.013 |
Sn | -0.012 |
Token | down |
Token ID | 866 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Rudolph | +0.092 |
Fl | +0.088 |
Nib | +0.087 |
Fl | +0.087 |
Sn | +0.087 |
Neg logit contributions | |
listener | -0.069 |
joy | -0.069 |
working | -0.068 |
itting | -0.066 |
ogs | -0.065 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
joy | +0.012 |
listener | +0.012 |
itting | +0.012 |
working | +0.012 |
ogs | +0.012 |
Neg logit contributions | |
Rudolph | -0.011 |
Fl | -0.011 |
Sn | -0.010 |
Nib | -0.010 |
Fl | -0.010 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
listener | +0.062 |
joy | +0.061 |
working | +0.060 |
itting | +0.059 |
ogs | +0.057 |
Neg logit contributions | |
Rudolph | -0.085 |
Fl | -0.083 |
Fl | -0.082 |
Sn | -0.082 |
Nib | -0.081 |
Token | like |
Token ID | 588 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
listener | +0.025 |
joy | +0.025 |
working | +0.024 |
itting | +0.024 |
ogs | +0.024 |
Neg logit contributions | |
Rudolph | -0.023 |
Fl | -0.022 |
Nib | -0.022 |
Sn | -0.022 |
Fl | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
listener | +0.048 |
joy | +0.048 |
working | +0.047 |
itting | +0.047 |
ogs | +0.046 |
Neg logit contributions | |
Rudolph | -0.041 |
Fl | -0.039 |
Fl | -0.039 |
Nib | -0.038 |
Sn | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
itting | +0.018 |
listener | +0.018 |
joy | +0.017 |
working | +0.017 |
ogs | +0.017 |
Neg logit contributions | |
Fl | -0.018 |
Rudolph | -0.017 |
Sn | -0.017 |
Nib | -0.016 |
Fl | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
listener | +0.085 |
working | +0.085 |
itting | +0.083 |
joy | +0.082 |
ogs | +0.082 |
Neg logit contributions | |
Rudolph | -0.034 |
Fl | -0.033 |
Sn | -0.031 |
Nib | -0.031 |
Fl | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
itting | +0.040 |
listener | +0.039 |
joy | +0.038 |
working | +0.037 |
ogs | +0.037 |
Neg logit contributions | |
Fl | -0.037 |
Rudolph | -0.035 |
Nib | -0.035 |
Sn | -0.034 |
Rudy | -0.033 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
joy | +0.039 |
itting | +0.038 |
listener | +0.038 |
ogs | +0.037 |
working | +0.037 |
Neg logit contributions | |
Rudolph | -0.037 |
Fl | -0.035 |
Sn | -0.034 |
Fl | -0.034 |
Nib | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
Rudolph | +0.011 |
Fl | +0.011 |
Sn | +0.010 |
Nib | +0.010 |
Fl | +0.010 |
Neg logit contributions | |
itting | -0.011 |
listener | -0.011 |
working | -0.011 |
joy | -0.011 |
ogs | -0.010 |
Token | if |
Token ID | 611 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Fl | +0.031 |
Rudolph | +0.031 |
Nib | +0.030 |
Sn | +0.029 |
Flor | +0.029 |
Neg logit contributions | |
joy | -0.030 |
working | -0.030 |
itting | -0.030 |
listener | -0.030 |
ogs | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Rudolph | +0.076 |
Fl | +0.075 |
Nib | +0.074 |
Sn | +0.072 |
Flor | +0.070 |
Neg logit contributions | |
itting | -0.060 |
listener | -0.059 |
joy | -0.058 |
ogs | -0.058 |
working | -0.056 |
Token | car |
Token ID | 1097 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
Rudolph | +0.019 |
Fl | +0.019 |
Sn | +0.019 |
Nib | +0.018 |
extingu | +0.017 |
Neg logit contributions | |
joy | -0.023 |
listener | -0.023 |
itting | -0.023 |
ogs | -0.022 |
working | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
Rudolph | +0.010 |
Fl | +0.010 |
Sn | +0.010 |
Nib | +0.009 |
extingu | +0.009 |
Neg logit contributions | |
listener | -0.011 |
joy | -0.011 |
itting | -0.011 |
ogs | -0.010 |
working | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
listener | +0.009 |
itting | +0.008 |
working | +0.008 |
joy | +0.008 |
ogs | +0.008 |
Neg logit contributions | |
Fl | -0.005 |
Rudolph | -0.005 |
Sn | -0.005 |
Nib | -0.005 |
Frost | -0.005 |
Token | played |
Token ID | 2826 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
joy | +0.003 |
itting | +0.003 |
listener | +0.003 |
working | +0.003 |
ogs | +0.003 |
Neg logit contributions | |
Rudolph | -0.003 |
Fl | -0.003 |
Sn | -0.003 |
Fl | -0.003 |
Nib | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
listener | +0.074 |
joy | +0.073 |
working | +0.072 |
itting | +0.072 |
ogs | +0.070 |
Neg logit contributions | |
Rudolph | -0.051 |
Fl | -0.050 |
Nib | -0.048 |
Sn | -0.048 |
Fl | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
Rudolph | +0.021 |
Fl | +0.020 |
Sn | +0.019 |
Frost | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
itting | -0.030 |
listener | -0.028 |
ogs | -0.028 |
working | -0.027 |
joy | -0.027 |
Token | until |
Token ID | 1566 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Fl | +0.004 |
Rudolph | +0.004 |
Sn | +0.004 |
Fl | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
working | -0.004 |
ogs | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
itting | +0.041 |
listener | +0.040 |
ogs | +0.039 |
joy | +0.038 |
working | +0.037 |
Neg logit contributions | |
Rudolph | -0.034 |
Fl | -0.033 |
Sn | -0.031 |
Nib | -0.031 |
Frost | -0.030 |
Token | fell |
Token ID | 3214 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
itting | +0.017 |
joy | +0.017 |
working | +0.017 |
listener | +0.017 |
ogs | +0.017 |
Neg logit contributions | |
Fl | -0.016 |
Rudolph | -0.015 |
Nib | -0.014 |
Sn | -0.014 |
Fl | -0.014 |
Token | asleep |
Token ID | 16039 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
Rudolph | +0.039 |
Fl | +0.038 |
Sn | +0.037 |
Nib | +0.035 |
Fl | +0.035 |
Neg logit contributions | |
listener | -0.060 |
joy | -0.058 |
itting | -0.058 |
working | -0.058 |
ogs | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
Rudolph | +0.095 |
Fl | +0.093 |
Sn | +0.091 |
Nib | +0.089 |
Fl | +0.087 |
Neg logit contributions | |
listener | -0.082 |
itting | -0.082 |
ogs | -0.080 |
joy | -0.079 |
working | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
Rudolph | +0.051 |
Nib | +0.049 |
Fl | +0.048 |
Fl | +0.048 |
Sn | +0.048 |
Neg logit contributions | |
listener | -0.032 |
working | -0.032 |
joy | -0.031 |
ogs | -0.031 |
itting | -0.031 |
Token | little |
Token ID | 1310 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Rudolph | +0.005 |
Fl | +0.005 |
Nib | +0.005 |
Fl | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
listener | -0.005 |
joy | -0.005 |
working | -0.005 |
itting | -0.005 |
ogs | -0.005 |
Token | one |
Token ID | 530 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Fl | +0.035 |
Rudolph | +0.033 |
Sn | +0.033 |
Flor | +0.032 |
Fl | +0.032 |
Neg logit contributions | |
itting | -0.027 |
working | -0.027 |
listener | -0.026 |
ogs | -0.026 |
ogged | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
joy | +0.063 |
listener | +0.062 |
working | +0.060 |
itting | +0.060 |
ogs | +0.059 |
Neg logit contributions | |
Rudolph | -0.074 |
Fl | -0.073 |
Fl | -0.071 |
Sn | -0.071 |
Nib | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | +2.30e-04 |
Pos logit contributions | |
Rudolph | +0.013 |
extingu | +0.012 |
versa | +0.012 |
Tenn | +0.012 |
Nib | +0.011 |
Neg logit contributions | |
listener | -0.010 |
itting | -0.010 |
ay | -0.010 |
joy | -0.010 |
ite | -0.010 |
Token | forest |
Token ID | 8222 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
joy | +0.000 |
listener | +0.000 |
itting | +0.000 |
working | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Fl | -0.000 |
Nib | -0.000 |
Flor | -0.000 |
Token | can |
Token ID | 460 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Fl | +0.007 |
Rudolph | +0.007 |
Nib | +0.007 |
Fl | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
joy | -0.011 |
listener | -0.011 |
working | -0.010 |
itting | -0.010 |
ogs | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
Rudolph | +0.031 |
Fl | +0.030 |
Nib | +0.029 |
Sn | +0.029 |
Fl | +0.029 |
Neg logit contributions | |
listener | -0.039 |
joy | -0.038 |
working | -0.038 |
itting | -0.037 |
ogs | -0.037 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
listener | +0.032 |
working | +0.031 |
joy | +0.031 |
friends | +0.031 |
itting | +0.030 |
Neg logit contributions | |
Rudolph | -0.037 |
Sn | -0.035 |
extingu | -0.035 |
Nib | -0.035 |
Fl | -0.035 |
Token | ." |
Token ID | 526 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
Rudolph | +0.045 |
Nib | +0.044 |
Fl | +0.043 |
Fl | +0.043 |
Sn | +0.043 |
Neg logit contributions | |
working | -0.036 |
listener | -0.035 |
ogs | -0.034 |
joy | -0.033 |
friends | -0.032 |
Token | It |
Token ID | 632 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
Rudolph | +0.009 |
extingu | +0.009 |
Fl | +0.008 |
Sn | +0.008 |
Das | +0.008 |
Neg logit contributions | |
joy | -0.008 |
listener | -0.008 |
ogs | -0.008 |
itting | -0.007 |
friends | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.018 |
Sn | +0.017 |
Frost | +0.017 |
Nib | +0.016 |
Neg logit contributions | |
itting | -0.025 |
working | -0.025 |
listener | -0.025 |
ogs | -0.024 |
joy | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
Fl | +0.014 |
Rudolph | +0.013 |
Sn | +0.012 |
Frost | +0.012 |
Fl | +0.012 |
Neg logit contributions | |
joy | -0.023 |
listener | -0.023 |
itting | -0.023 |
ogged | -0.022 |
working | -0.022 |
Token | nothing |
Token ID | 2147 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Rudolph | +0.009 |
Fl | +0.008 |
extingu | +0.008 |
Sn | +0.008 |
sc | +0.008 |
Neg logit contributions | |
friends | -0.008 |
listener | -0.008 |
working | -0.008 |
itting | -0.008 |
joy | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
Rudolph | +0.020 |
Fl | +0.019 |
Fl | +0.019 |
Sn | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
listener | -0.023 |
joy | -0.023 |
itting | -0.022 |
working | -0.022 |
ogs | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
joy | +0.102 |
listener | +0.098 |
itting | +0.095 |
ogs | +0.092 |
working | +0.092 |
Neg logit contributions | |
Rudolph | -0.097 |
Fl | -0.095 |
Nib | -0.092 |
Sn | -0.090 |
Fl | -0.090 |
Token | scared |
Token ID | 12008 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
listener | +0.063 |
joy | +0.062 |
itting | +0.061 |
working | +0.061 |
ogs | +0.060 |
Neg logit contributions | |
Rudolph | -0.054 |
Fl | -0.052 |
Nib | -0.051 |
Sn | -0.050 |
Fl | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
Rudolph | +0.043 |
Fl | +0.043 |
Sn | +0.041 |
Fl | +0.040 |
Nib | +0.040 |
Neg logit contributions | |
joy | -0.040 |
listener | -0.039 |
itting | -0.038 |
working | -0.038 |
ogs | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
Rudolph | +0.007 |
Fl | +0.007 |
Sn | +0.007 |
Nib | +0.007 |
Fl | +0.007 |
Neg logit contributions | |
listener | -0.008 |
itting | -0.008 |
joy | -0.008 |
working | -0.007 |
ogs | -0.007 |
Token | That |
Token ID | 1320 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Rudolph | +0.012 |
Nib | +0.011 |
extingu | +0.011 |
Fl | +0.011 |
versa | +0.011 |
Neg logit contributions | |
listener | -0.011 |
itting | -0.011 |
joy | -0.011 |
working | -0.011 |
ogs | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
joy | +0.027 |
listener | +0.026 |
itting | +0.026 |
working | +0.025 |
ogs | +0.025 |
Neg logit contributions | |
Rudolph | -0.015 |
Fl | -0.014 |
Sn | -0.013 |
Fl | -0.013 |
Nib | -0.013 |
Token | just |
Token ID | 655 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Rudolph | +0.017 |
sc | +0.017 |
Fl | +0.016 |
extingu | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
friends | -0.015 |
listener | -0.014 |
itting | -0.013 |
working | -0.013 |
friend | -0.013 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
listener | +0.001 |
working | +0.001 |
joy | +0.001 |
itting | +0.001 |
ogs | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Fl | -0.001 |
Sn | -0.001 |
Nib | -0.001 |
Token | heavy |
Token ID | 4334 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Rudolph | +0.030 |
Fl | +0.030 |
extingu | +0.029 |
Sn | +0.029 |
Fl | +0.029 |
Neg logit contributions | |
joy | -0.020 |
listener | -0.019 |
friends | -0.019 |
working | -0.019 |
itting | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
Rudolph | +0.045 |
Fl | +0.044 |
Fl | +0.044 |
Nib | +0.043 |
Sn | +0.043 |
Neg logit contributions | |
listener | -0.027 |
joy | -0.027 |
working | -0.026 |
itting | -0.025 |
ogs | -0.025 |
Token | The |
Token ID | 383 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
listener | +0.006 |
joy | +0.005 |
working | +0.005 |
itting | +0.005 |
ogs | +0.005 |
Neg logit contributions | |
Rudolph | -0.005 |
Fl | -0.005 |
Nib | -0.005 |
Sn | -0.004 |
Fl | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
itting | +0.010 |
udding | +0.010 |
joy | +0.009 |
ogs | +0.009 |
ugs | +0.009 |
Neg logit contributions | |
Rudolph | -0.005 |
Das | -0.005 |
Fl | -0.005 |
Fl | -0.005 |
Mr | -0.004 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
itting | +0.012 |
atic | +0.011 |
ops | +0.011 |
rav | +0.011 |
ogs | +0.011 |
Neg logit contributions | |
extingu | -0.008 |
Rudolph | -0.008 |
Fl | -0.008 |
from | -0.007 |
Nib | -0.007 |
Token | tried |
Token ID | 3088 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
Fl | +0.003 |
Rudolph | +0.003 |
Fl | +0.003 |
Sn | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
joy | -0.004 |
listener | -0.004 |
itting | -0.004 |
working | -0.004 |
ogs | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.014 |
Fl | +0.013 |
Nib | +0.013 |
Sn | +0.013 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
working | -0.009 |
itting | -0.009 |
ogs | -0.009 |
Token | take |
Token ID | 1011 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
Rudolph | +0.003 |
Nib | +0.003 |
Sn | +0.003 |
Fl | +0.003 |
Fl | +0.003 |
Neg logit contributions | |
listener | -0.002 |
working | -0.002 |
friends | -0.002 |
ogs | -0.002 |
runner | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
listener | +0.007 |
joy | +0.007 |
working | +0.007 |
itting | +0.007 |
ogs | +0.007 |
Neg logit contributions | |
Rudolph | -0.006 |
Fl | -0.006 |
Nib | -0.006 |
Sn | -0.006 |
Fl | -0.006 |
Token | off |
Token ID | 572 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Rudolph | +0.045 |
Fl | +0.043 |
Fl | +0.042 |
Sn | +0.042 |
Nib | +0.042 |
Neg logit contributions | |
listener | -0.044 |
joy | -0.043 |
working | -0.043 |
itting | -0.042 |
ogs | -0.042 |
Token | him |
Token ID | 683 |
Feature activation | -3.69e-04 |
Pos logit contributions | |
listener | +0.060 |
itting | +0.059 |
working | +0.058 |
joy | +0.057 |
ogs | +0.056 |
Neg logit contributions | |
Rudolph | -0.055 |
Fl | -0.054 |
Nib | -0.052 |
Sn | -0.052 |
Fl | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-04 |
Pos logit contributions | |
Fl | +0.001 |
Rudolph | +0.001 |
Sn | +0.001 |
Nib | +0.001 |
Frost | +0.001 |
Neg logit contributions | |
listener | -0.001 |
itting | -0.001 |
joy | -0.001 |
working | -0.001 |
ogs | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
joy | +0.000 |
listener | +0.000 |
itting | +0.000 |
working | +0.000 |
ogs | +0.000 |
Neg logit contributions | |
Rudolph | -0.000 |
Fl | -0.000 |
Fl | -0.000 |
Sn | -0.000 |
Nib | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
Rudolph | +0.006 |
Sn | +0.005 |
Nib | +0.005 |
Fl | +0.005 |
extingu | +0.005 |
Neg logit contributions | |
listener | -0.006 |
ogs | -0.005 |
joy | -0.005 |
itting | -0.005 |
working | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
Rudolph | +0.015 |
Fl | +0.014 |
Nib | +0.014 |
Sn | +0.014 |
Fl | +0.014 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
working | -0.010 |
itting | -0.010 |
ogs | -0.009 |
Token | Look |
Token ID | 8567 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
Rudolph | +0.003 |
Fl | +0.003 |
Nib | +0.003 |
Sn | +0.003 |
Das | +0.003 |
Neg logit contributions | |
listener | -0.003 |
joy | -0.003 |
itting | -0.003 |
working | -0.003 |
ogs | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
Fl | +0.012 |
Rudolph | +0.012 |
Nib | +0.012 |
Sn | +0.011 |
Frost | +0.011 |
Neg logit contributions | |
listener | -0.011 |
working | -0.011 |
joy | -0.011 |
itting | -0.011 |
ogs | -0.010 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
Rudolph | +0.036 |
Fl | +0.035 |
Fl | +0.035 |
Sn | +0.034 |
Nib | +0.034 |
Neg logit contributions | |
listener | -0.033 |
joy | -0.033 |
working | -0.032 |
itting | -0.031 |
ogs | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
Fl | +0.052 |
Rudolph | +0.051 |
Nib | +0.050 |
Sn | +0.049 |
Fl | +0.048 |
Neg logit contributions | |
listener | -0.055 |
itting | -0.054 |
joy | -0.053 |
working | -0.053 |
ogs | -0.052 |
Token | I |
Token ID | 314 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
Rudolph | +0.013 |
Fl | +0.013 |
Sn | +0.013 |
Nib | +0.013 |
Fl | +0.013 |
Neg logit contributions | |
listener | -0.017 |
joy | -0.016 |
working | -0.016 |
itting | -0.016 |
ogs | -0.016 |
Token | 'm |
Token ID | 1101 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
joy | +0.013 |
working | +0.013 |
ogs | +0.013 |
listener | +0.013 |
ule | +0.013 |
Neg logit contributions | |
� | -0.011 |
Fl | -0.011 |
Fl | -0.010 |
Sn | -0.010 |
Nib | -0.010 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Rudolph | +0.090 |
Fl | +0.089 |
Sn | +0.085 |
Nib | +0.083 |
Fl | +0.083 |
Neg logit contributions | |
listener | -0.094 |
working | -0.093 |
itting | -0.092 |
joy | -0.092 |
ogs | -0.088 |
Token | But |
Token ID | 887 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.014 |
Sn | +0.013 |
Nib | +0.013 |
Fl | +0.013 |
Neg logit contributions | |
listener | -0.018 |
joy | -0.018 |
working | -0.018 |
itting | -0.017 |
ogs | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Rudolph | +0.021 |
Fl | +0.020 |
Nib | +0.020 |
Sn | +0.020 |
Fl | +0.020 |
Neg logit contributions | |
listener | -0.026 |
joy | -0.026 |
working | -0.026 |
itting | -0.026 |
ogs | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -8.05e-03 |
Pos logit contributions | |
Rudolph | +0.019 |
Nib | +0.018 |
Sn | +0.018 |
Fl | +0.017 |
Fl | +0.017 |
Neg logit contributions | |
listener | -0.017 |
working | -0.016 |
joy | -0.016 |
itting | -0.016 |
ogs | -0.015 |
Token | too |
Token ID | 1165 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
Rudolph | +0.014 |
extingu | +0.013 |
Flor | +0.013 |
Nib | +0.013 |
Fl | +0.013 |
Neg logit contributions | |
listener | -0.011 |
working | -0.011 |
joy | -0.011 |
friends | -0.011 |
itting | -0.010 |
Token | late |
Token ID | 2739 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
joy | +0.055 |
listener | +0.055 |
itting | +0.053 |
ogs | +0.053 |
working | +0.053 |
Neg logit contributions | |
Rudolph | -0.035 |
Fl | -0.034 |
Fl | -0.033 |
Sn | -0.032 |
Nib | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-04 |
Pos logit contributions | |
Rudolph | +0.166 |
Fl | +0.162 |
Nib | +0.159 |
Sn | +0.159 |
Fl | +0.158 |
Neg logit contributions | |
listener | -0.110 |
joy | -0.108 |
working | -0.106 |
itting | -0.105 |
ogs | -0.102 |
Token | |
Token ID | 220 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
joy | +0.002 |
listener | +0.001 |
itting | +0.001 |
working | +0.001 |
ogs | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Nib | -0.001 |
extingu | -0.001 |
Fl | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
listener | +0.131 |
working | +0.128 |
joy | +0.126 |
itting | +0.124 |
ogs | +0.120 |
Neg logit contributions | |
Rudolph | -0.084 |
Fl | -0.084 |
Sn | -0.080 |
Nib | -0.079 |
Fl | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
extingu | +0.013 |
Rudolph | +0.012 |
Nib | +0.012 |
Flor | +0.012 |
Sn | +0.012 |
Neg logit contributions | |
joy | -0.009 |
ogs | -0.009 |
itting | -0.009 |
listener | -0.008 |
working | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
Rudolph | +0.016 |
Nib | +0.015 |
Fl | +0.015 |
extingu | +0.015 |
Flor | +0.014 |
Neg logit contributions | |
itting | -0.020 |
listener | -0.019 |
working | -0.019 |
joy | -0.019 |
ogs | -0.019 |
Token | They |
Token ID | 2990 |
Feature activation | +3.55e-04 |
Pos logit contributions | |
extingu | +0.010 |
Rudolph | +0.010 |
Fl | +0.010 |
Nib | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
itting | -0.010 |
listener | -0.009 |
working | -0.009 |
ogs | -0.009 |
friends | -0.009 |
Token | go |
Token ID | 467 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
joy | +0.001 |
itting | +0.001 |
listener | +0.001 |
ugs | +0.001 |
working | +0.001 |
Neg logit contributions | |
Rudolph | -0.001 |
Fl | -0.001 |
Nib | -0.001 |
Flor | -0.001 |
Sn | -0.001 |
Token | back |
Token ID | 736 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
Rudolph | +0.007 |
Fl | +0.006 |
Sn | +0.006 |
Nib | +0.006 |
Frost | +0.006 |
Neg logit contributions | |
itting | -0.008 |
working | -0.008 |
listener | -0.008 |
joy | -0.007 |
iness | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
itting | +0.007 |
listener | +0.007 |
working | +0.007 |
joy | +0.006 |
iness | +0.006 |
Neg logit contributions | |
Fl | -0.006 |
Rudolph | -0.006 |
Sn | -0.005 |
Frost | -0.005 |
from | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
Fl | +0.032 |
Rudolph | +0.032 |
Sn | +0.030 |
Frost | +0.030 |
Nib | +0.029 |
Neg logit contributions | |
itting | -0.049 |
listener | -0.048 |
working | -0.047 |
ogs | -0.046 |
joy | -0.046 |
Token | bathroom |
Token ID | 12436 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
Rudolph | +0.062 |
Fl | +0.060 |
Sn | +0.059 |
Nib | +0.058 |
Fl | +0.058 |
Neg logit contributions | |
listener | -0.042 |
joy | -0.041 |
itting | -0.041 |
working | -0.041 |
ogs | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Rudolph | +0.127 |
Fl | +0.124 |
Sn | +0.118 |
Nib | +0.116 |
Frost | +0.116 |
Neg logit contributions | |
itting | -0.152 |
listener | -0.150 |
working | -0.147 |
ogs | -0.145 |
joy | -0.142 |
Token | wash |
Token ID | 13502 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Rudolph | +0.035 |
Fl | +0.034 |
Nib | +0.033 |
Sn | +0.033 |
Fl | +0.033 |
Neg logit contributions | |
listener | -0.024 |
joy | -0.024 |
itting | -0.024 |
working | -0.023 |
ogs | -0.023 |
Token | their |
Token ID | 511 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Rudolph | +0.070 |
Fl | +0.067 |
Nib | +0.066 |
Fl | +0.066 |
Sn | +0.065 |
Neg logit contributions | |
listener | -0.095 |
joy | -0.094 |
working | -0.093 |
itting | -0.092 |
ogs | -0.092 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
Fl | +0.035 |
Rudolph | +0.035 |
Sn | +0.033 |
Frost | +0.033 |
Nib | +0.033 |
Neg logit contributions | |
listener | -0.025 |
itting | -0.025 |
working | -0.025 |
joy | -0.024 |
ogs | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
listener | +0.032 |
joy | +0.031 |
working | +0.031 |
itting | +0.031 |
ogs | +0.030 |
Neg logit contributions | |
Rudolph | -0.049 |
Fl | -0.047 |
Nib | -0.047 |
Fl | -0.046 |
Sn | -0.046 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Rudolph | +0.021 |
Fl | +0.020 |
Nib | +0.020 |
Fl | +0.020 |
Sn | +0.020 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
friends | -0.010 |
itting | -0.009 |
working | -0.009 |
Token | Sara |
Token ID | 24799 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
friends | +0.013 |
joy | +0.013 |
ogs | +0.012 |
listener | +0.011 |
ies | +0.011 |
Neg logit contributions | |
mant | -0.024 |
sc | -0.024 |
Fl | -0.024 |
Rudolph | -0.023 |
versa | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
Rudolph | +0.013 |
Fl | +0.012 |
Nib | +0.012 |
Fl | +0.012 |
Sn | +0.012 |
Neg logit contributions | |
listener | -0.012 |
joy | -0.012 |
working | -0.012 |
itting | -0.012 |
ogs | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Rudolph | +0.009 |
Fl | +0.009 |
Nib | +0.009 |
Sn | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
listener | -0.007 |
working | -0.007 |
itting | -0.007 |
joy | -0.007 |
ogs | -0.006 |
Token | doctor |
Token ID | 6253 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
itting | +0.023 |
listener | +0.022 |
working | +0.022 |
ogs | +0.022 |
joy | +0.021 |
Neg logit contributions | |
Fl | -0.020 |
Rudolph | -0.019 |
Sn | -0.019 |
extingu | -0.019 |
Nib | -0.018 |
Token | kit |
Token ID | 6220 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
Rudolph | +0.128 |
Fl | +0.125 |
Nib | +0.122 |
Sn | +0.122 |
Fl | +0.121 |
Neg logit contributions | |
listener | -0.108 |
joy | -0.106 |
working | -0.104 |
itting | -0.103 |
ogs | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Rudolph | +0.098 |
Fl | +0.098 |
Sn | +0.096 |
Nib | +0.092 |
extingu | +0.091 |
Neg logit contributions | |
listener | -0.109 |
working | -0.107 |
joy | -0.105 |
itting | -0.103 |
ogs | -0.101 |
Token | They |
Token ID | 1119 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Rudolph | +0.022 |
versa | +0.021 |
mant | +0.021 |
ified | +0.020 |
Fl | +0.020 |
Neg logit contributions | |
joy | -0.015 |
listener | -0.014 |
working | -0.013 |
ogs | -0.013 |
friends | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Rudolph | +0.023 |
Fl | +0.022 |
Nib | +0.022 |
Fl | +0.022 |
Sn | +0.022 |
Neg logit contributions | |
listener | -0.015 |
joy | -0.015 |
working | -0.014 |
itting | -0.014 |
ogs | -0.014 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Rudolph | +0.026 |
Fl | +0.025 |
sc | +0.025 |
Nib | +0.025 |
Flor | +0.024 |
Neg logit contributions | |
friends | -0.022 |
listener | -0.020 |
joy | -0.020 |
working | -0.019 |
itting | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
Fl | +0.019 |
Rudolph | +0.019 |
Nib | +0.018 |
Sn | +0.018 |
Frost | +0.018 |
Neg logit contributions | |
working | -0.020 |
listener | -0.020 |
itting | -0.019 |
joy | -0.019 |
ogs | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Rudolph | +0.073 |
Fl | +0.073 |
Nib | +0.071 |
Sn | +0.071 |
Frost | +0.069 |
Neg logit contributions | |
itting | -0.034 |
working | -0.033 |
listener | -0.033 |
joy | -0.033 |
ogs | -0.032 |
Token | for |
Token ID | 329 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Rudolph | +0.046 |
Fl | +0.045 |
Nib | +0.044 |
Sn | +0.043 |
Fl | +0.042 |
Neg logit contributions | |
listener | -0.043 |
joy | -0.042 |
working | -0.042 |
itting | -0.041 |
ogs | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Rudolph | +0.055 |
Fl | +0.053 |
Nib | +0.052 |
Sn | +0.052 |
Fl | +0.052 |
Neg logit contributions | |
listener | -0.055 |
joy | -0.053 |
itting | -0.053 |
working | -0.053 |
ogs | -0.052 |
Token | money |
Token ID | 1637 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
Rudolph | +0.038 |
Fl | +0.037 |
Sn | +0.037 |
Nib | +0.036 |
Fl | +0.036 |
Neg logit contributions | |
listener | -0.028 |
itting | -0.028 |
joy | -0.028 |
working | -0.028 |
ogs | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
Rudolph | +0.067 |
Fl | +0.065 |
Nib | +0.064 |
Sn | +0.063 |
Das | +0.060 |
Neg logit contributions | |
listener | -0.068 |
joy | -0.067 |
itting | -0.065 |
working | -0.064 |
ogs | -0.064 |
Token | store |
Token ID | 3650 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
Rudolph | +0.008 |
Fl | +0.008 |
Sn | +0.007 |
Nib | +0.007 |
Fl | +0.007 |
Neg logit contributions | |
listener | -0.010 |
joy | -0.010 |
itting | -0.010 |
working | -0.010 |
ogs | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
Rudolph | +0.095 |
Fl | +0.092 |
Nib | +0.091 |
Sn | +0.090 |
Das | +0.085 |
Neg logit contributions | |
listener | -0.123 |
itting | -0.123 |
working | -0.119 |
joy | -0.118 |
ogs | -0.114 |
Token | She |
Token ID | 1375 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
Fl | +0.007 |
Rudolph | +0.007 |
Sn | +0.007 |
Nib | +0.006 |
Fl | +0.006 |
Neg logit contributions | |
listener | -0.009 |
joy | -0.009 |
working | -0.009 |
itting | -0.008 |
ogs | -0.008 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
Rudolph | +0.006 |
Fl | +0.006 |
Sn | +0.006 |
Nib | +0.006 |
Fl | +0.006 |
Neg logit contributions | |
joy | -0.006 |
listener | -0.006 |
working | -0.006 |
itting | -0.006 |
ogs | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Rudolph | +0.044 |
Fl | +0.043 |
Nib | +0.042 |
Sn | +0.041 |
Fl | +0.040 |
Neg logit contributions | |
listener | -0.050 |
itting | -0.050 |
joy | -0.048 |
working | -0.048 |
ogs | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
Rudolph | +0.014 |
Fl | +0.013 |
Sn | +0.013 |
Nib | +0.013 |
Fl | +0.012 |
Neg logit contributions | |
listener | -0.025 |
itting | -0.025 |
working | -0.024 |
joy | -0.024 |
ogs | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
Rudolph | +0.046 |
Fl | +0.045 |
Nib | +0.044 |
Fl | +0.044 |
Sn | +0.044 |
Neg logit contributions | |
joy | -0.043 |
listener | -0.042 |
working | -0.041 |
itting | -0.041 |
ogs | -0.039 |
Token | I |
Token ID | 40 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
Rudolph | +0.050 |
Fl | +0.049 |
Fl | +0.048 |
Sn | +0.048 |
Nib | +0.048 |
Neg logit contributions | |
listener | -0.056 |
joy | -0.055 |
working | -0.054 |
itting | -0.054 |
ogs | -0.053 |
Token | know |
Token ID | 760 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
joy | +0.005 |
ogs | +0.005 |
listener | +0.005 |
itting | +0.005 |
working | +0.004 |
Neg logit contributions | |
Fl | -0.006 |
Rudolph | -0.006 |
Nib | -0.006 |
Frost | -0.006 |
Fl | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Fl | +0.025 |
Rudolph | +0.024 |
Frost | +0.023 |
Nib | +0.022 |
Sn | +0.022 |
Neg logit contributions | |
listener | -0.032 |
working | -0.031 |
itting | -0.030 |
joy | -0.030 |
ogs | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
Fl | +0.012 |
Rudolph | +0.012 |
Fl | +0.011 |
Sn | +0.011 |
Frost | +0.011 |
Neg logit contributions | |
joy | -0.023 |
listener | -0.023 |
itting | -0.022 |
ogs | -0.022 |
working | -0.021 |
Token | bad |
Token ID | 2089 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
Rudolph | +0.050 |
Fl | +0.050 |
Sn | +0.049 |
Nib | +0.048 |
extingu | +0.048 |
Neg logit contributions | |
listener | -0.052 |
working | -0.051 |
friends | -0.050 |
joy | -0.049 |
itting | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Fl | +0.121 |
Rudolph | +0.115 |
Sunny | +0.108 |
Frost | +0.106 |
from | +0.106 |
Neg logit contributions | |
joy | -0.144 |
itting | -0.143 |
listener | -0.133 |
ogged | -0.129 |
udding | -0.129 |
Token | but |
Token ID | 475 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Rudolph | +0.018 |
Fl | +0.017 |
Fl | +0.017 |
Nib | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
listener | -0.021 |
joy | -0.021 |
working | -0.020 |
itting | -0.020 |
ogs | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
Rudolph | +0.017 |
Fl | +0.016 |
Sn | +0.016 |
Fl | +0.016 |
Nib | +0.016 |
Neg logit contributions | |
listener | -0.016 |
working | -0.015 |
joy | -0.015 |
itting | -0.015 |
friends | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
listener | +0.003 |
working | +0.003 |
itting | +0.003 |
joy | +0.003 |
ogs | +0.003 |
Neg logit contributions | |
Rudolph | -0.003 |
Sn | -0.002 |
Nib | -0.002 |
Fl | -0.002 |
Fl | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
Rudolph | +0.034 |
Fl | +0.032 |
extingu | +0.032 |
Sn | +0.032 |
Nib | +0.032 |
Neg logit contributions | |
friends | -0.031 |
working | -0.031 |
listener | -0.030 |
itting | -0.029 |
joy | -0.028 |