Token | butterfly |
Token ID | 35113 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.010 |
Fox | +0.010 |
We | +0.009 |
Neg logit contributions | |
oll | -0.022 |
ier | -0.022 |
aney | -0.021 |
contain | -0.020 |
ax | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Fox | +0.018 |
oc | +0.015 |
Are | +0.015 |
We | +0.015 |
things | +0.014 |
Neg logit contributions | |
oll | -0.032 |
ier | -0.031 |
aney | -0.030 |
ax | -0.029 |
ige | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
aney | +0.017 |
oll | +0.016 |
ver | +0.016 |
ipp | +0.016 |
ax | +0.016 |
Neg logit contributions | |
AAAA | -0.011 |
situations | -0.011 |
Raw | -0.011 |
cave | -0.010 |
Are | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.016 |
ier | -0.016 |
aney | -0.015 |
contain | -0.015 |
ver | -0.015 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Are | +0.009 |
AAAA | +0.009 |
Fox | +0.009 |
Raw | +0.009 |
We | +0.008 |
Neg logit contributions | |
aney | -0.010 |
ier | -0.010 |
oll | -0.010 |
contain | -0.010 |
ver | -0.009 |
Token | ited |
Token ID | 863 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
oll | +0.029 |
ier | +0.029 |
aney | +0.024 |
contain | +0.021 |
ax | +0.017 |
Neg logit contributions | |
AAAA | -0.145 |
Raw | -0.143 |
Are | -0.143 |
Fox | -0.140 |
We | -0.138 |
Token | ly |
Token ID | 306 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
oll | +0.360 |
ier | +0.354 |
aney | +0.334 |
contain | +0.319 |
ver | +0.304 |
Neg logit contributions | |
AAAA | -0.382 |
Are | -0.372 |
Raw | -0.372 |
Fox | -0.361 |
We | -0.354 |
Token | , |
Token ID | 11 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
Raw | +0.089 |
AAAA | +0.088 |
Are | +0.086 |
Look | +0.082 |
Come | +0.081 |
Neg logit contributions | |
oll | -0.084 |
ier | -0.083 |
aney | -0.076 |
contain | -0.074 |
ver | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ier | +0.005 |
contain | +0.004 |
oll | +0.004 |
ver | +0.004 |
aney | +0.004 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Come | -0.005 |
Ar | -0.005 |
Are | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
AAAA | +0.012 |
Raw | +0.012 |
Are | +0.011 |
Fox | +0.011 |
We | +0.011 |
Neg logit contributions | |
oll | -0.021 |
ier | -0.021 |
aney | -0.020 |
contain | -0.019 |
ax | -0.019 |
Token | bird |
Token ID | 6512 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
ier | +0.001 |
oll | +0.001 |
aney | +0.001 |
contain | +0.001 |
ige | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Peter | -0.001 |
Come | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
oll | +0.197 |
aney | +0.189 |
ier | +0.184 |
ige | +0.177 |
fourteen | +0.171 |
Neg logit contributions | |
Fox | -0.098 |
We | -0.097 |
things | -0.096 |
cave | -0.095 |
Are | -0.092 |
Token | his |
Token ID | 465 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
AAAA | +0.030 |
Raw | +0.029 |
Are | +0.029 |
Fox | +0.027 |
We | +0.027 |
Neg logit contributions | |
oll | -0.054 |
ier | -0.053 |
aney | -0.051 |
contain | -0.049 |
ver | -0.048 |
Token | raft |
Token ID | 31812 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
oll | +0.032 |
ier | +0.030 |
aney | +0.029 |
contain | +0.029 |
ige | +0.028 |
Neg logit contributions | |
Raw | -0.024 |
Are | -0.024 |
AAAA | -0.023 |
Come | -0.022 |
Fox | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
oll | +0.068 |
aney | +0.067 |
ier | +0.064 |
ige | +0.060 |
contain | +0.058 |
Neg logit contributions | |
Fox | -0.033 |
cave | -0.032 |
We | -0.031 |
oc | -0.030 |
things | -0.030 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
oll | +0.013 |
aney | +0.013 |
ier | +0.013 |
contain | +0.012 |
ax | +0.012 |
Neg logit contributions | |
AAAA | -0.009 |
Raw | -0.008 |
Fox | -0.008 |
situations | -0.008 |
Peter | -0.008 |
Token | ited |
Token ID | 863 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
oll | +0.024 |
ier | +0.023 |
aces | +0.021 |
aney | +0.020 |
ver | +0.018 |
Neg logit contributions | |
AAAA | -0.060 |
Raw | -0.060 |
oc | -0.058 |
Look | -0.057 |
Are | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
oll | +0.290 |
ier | +0.286 |
aney | +0.265 |
contain | +0.249 |
ax | +0.234 |
Neg logit contributions | |
AAAA | -0.452 |
Raw | -0.444 |
Are | -0.442 |
Fox | -0.428 |
We | -0.420 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.010 |
aney | +0.010 |
contain | +0.010 |
ax | +0.009 |
Neg logit contributions | |
AAAA | -0.007 |
Raw | -0.007 |
Are | -0.007 |
Fox | -0.006 |
Come | -0.006 |
Token | jumped |
Token ID | 11687 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
oll | +0.014 |
ier | +0.014 |
aney | +0.013 |
contain | +0.013 |
ver | +0.012 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Are | -0.011 |
Fox | -0.010 |
We | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
oll | +0.057 |
ier | +0.056 |
aney | +0.055 |
contain | +0.052 |
ver | +0.051 |
Neg logit contributions | |
AAAA | -0.032 |
Raw | -0.031 |
Are | -0.031 |
Fox | -0.030 |
We | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
AAAA | +0.035 |
Raw | +0.034 |
Are | +0.034 |
Fox | +0.032 |
We | +0.032 |
Neg logit contributions | |
oll | -0.049 |
ier | -0.048 |
aney | -0.046 |
contain | -0.045 |
ax | -0.043 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
oll | +0.000 |
ier | +0.000 |
aney | +0.000 |
contain | +0.000 |
ax | +0.000 |
Neg logit contributions | |
AAAA | -0.000 |
Raw | -0.000 |
Are | -0.000 |
Fox | -0.000 |
We | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Fox | +0.013 |
We | +0.013 |
Are | +0.013 |
Come | +0.013 |
Peter | +0.012 |
Neg logit contributions | |
ier | -0.025 |
oll | -0.024 |
aney | -0.023 |
obb | -0.023 |
contain | -0.022 |
Token | dad |
Token ID | 9955 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
oll | +0.004 |
ier | +0.003 |
aney | +0.003 |
contain | +0.003 |
ax | +0.003 |
Neg logit contributions | |
AAAA | -0.003 |
Raw | -0.003 |
Are | -0.003 |
Fox | -0.003 |
We | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
oll | +0.069 |
ier | +0.069 |
aney | +0.065 |
obb | +0.064 |
vious | +0.062 |
Neg logit contributions | |
We | -0.036 |
Fox | -0.035 |
Are | -0.034 |
Come | -0.033 |
things | -0.033 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
oll | +0.020 |
ier | +0.020 |
aney | +0.019 |
contain | +0.019 |
ver | +0.018 |
Neg logit contributions | |
AAAA | -0.006 |
Are | -0.006 |
Raw | -0.006 |
Fox | -0.005 |
We | -0.005 |
Token | ited |
Token ID | 863 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
oll | +0.031 |
aces | +0.029 |
ier | +0.028 |
ver | +0.025 |
aney | +0.024 |
Neg logit contributions | |
AAAA | -0.052 |
Look | -0.051 |
Raw | -0.050 |
oc | -0.049 |
things | -0.049 |
Token | ly |
Token ID | 306 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
oll | +0.400 |
ier | +0.385 |
aney | +0.367 |
contain | +0.358 |
ver | +0.352 |
Neg logit contributions | |
Are | -0.329 |
AAAA | -0.329 |
We | -0.321 |
Fox | -0.321 |
Raw | -0.314 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
AAAA | +0.069 |
Are | +0.068 |
Fox | +0.067 |
Raw | +0.064 |
We | +0.064 |
Neg logit contributions | |
oll | -0.102 |
ier | -0.101 |
aney | -0.096 |
contain | -0.093 |
ver | -0.089 |
Token | she |
Token ID | 673 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
oll | +0.011 |
ier | +0.010 |
aney | +0.010 |
contain | +0.009 |
ver | +0.009 |
Neg logit contributions | |
Are | -0.008 |
AAAA | -0.007 |
We | -0.007 |
Raw | -0.007 |
Fox | -0.007 |
Token | jumped |
Token ID | 11687 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.009 |
aney | +0.009 |
contain | +0.009 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.008 |
Raw | -0.007 |
Are | -0.007 |
Fox | -0.007 |
We | -0.007 |
Token | into |
Token ID | 656 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
oll | +0.055 |
ier | +0.054 |
aney | +0.052 |
contain | +0.050 |
ver | +0.048 |
Neg logit contributions | |
AAAA | -0.034 |
Raw | -0.033 |
Are | -0.033 |
Fox | -0.032 |
We | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
cave | +0.042 |
We | +0.040 |
woods | +0.039 |
places | +0.037 |
hole | +0.037 |
Neg logit contributions | |
oll | -0.058 |
ige | -0.056 |
ier | -0.053 |
aney | -0.053 |
ver | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
oll | +0.096 |
ier | +0.095 |
aney | +0.090 |
contain | +0.087 |
ver | +0.085 |
Neg logit contributions | |
AAAA | -0.048 |
Raw | -0.046 |
Are | -0.046 |
Fox | -0.045 |
Look | -0.042 |
Token | mountain |
Token ID | 8598 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
AAAA | +0.013 |
Are | +0.012 |
Raw | +0.012 |
Fox | +0.011 |
Come | +0.011 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
aney | -0.023 |
contain | -0.023 |
ax | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
oll | +0.004 |
ier | +0.004 |
aney | +0.004 |
ige | +0.004 |
contain | +0.003 |
Neg logit contributions | |
cave | -0.002 |
We | -0.002 |
Are | -0.002 |
Fox | -0.002 |
AAAA | -0.002 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
oll | +0.016 |
aney | +0.015 |
ax | +0.013 |
ver | +0.013 |
ier | +0.013 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.013 |
Ar | -0.012 |
cave | -0.012 |
Peter | -0.012 |
Token | ited |
Token ID | 863 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
oll | +0.026 |
ier | +0.025 |
aces | +0.023 |
aney | +0.021 |
ver | +0.018 |
Neg logit contributions | |
AAAA | -0.061 |
Raw | -0.060 |
Look | -0.058 |
oc | -0.057 |
Ar | -0.057 |
Token | ly |
Token ID | 306 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oll | +0.362 |
ier | +0.355 |
aney | +0.335 |
contain | +0.322 |
ver | +0.308 |
Neg logit contributions | |
AAAA | -0.378 |
Are | -0.370 |
Raw | -0.368 |
Fox | -0.358 |
We | -0.351 |
Token | , |
Token ID | 11 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
Raw | +0.088 |
AAAA | +0.087 |
Are | +0.084 |
Look | +0.081 |
We | +0.080 |
Neg logit contributions | |
oll | -0.085 |
ier | -0.084 |
aney | -0.077 |
contain | -0.074 |
ax | -0.072 |
Token | she |
Token ID | 673 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
oll | +0.006 |
ier | +0.006 |
aney | +0.005 |
contain | +0.005 |
ver | +0.005 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.006 |
Fox | -0.006 |
Come | -0.006 |
Token | rushed |
Token ID | 13999 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
oll | +0.015 |
ier | +0.014 |
aney | +0.014 |
contain | +0.013 |
ax | +0.013 |
Neg logit contributions | |
AAAA | -0.014 |
Are | -0.014 |
Raw | -0.013 |
We | -0.013 |
Fox | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
AAAA | +0.031 |
Raw | +0.030 |
Are | +0.030 |
Sorry | +0.028 |
Fox | +0.028 |
Neg logit contributions | |
ier | -0.029 |
oll | -0.029 |
aney | -0.027 |
contain | -0.027 |
ax | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
AAAA | +0.001 |
Raw | +0.001 |
Are | +0.001 |
Fox | +0.001 |
We | +0.001 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
contain | -0.003 |
ver | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
We | +0.021 |
Are | +0.020 |
Fox | +0.020 |
things | +0.020 |
AAAA | +0.019 |
Neg logit contributions | |
oll | -0.039 |
ier | -0.037 |
aney | -0.037 |
ige | -0.035 |
contain | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
oll | +0.015 |
aney | +0.015 |
ax | +0.015 |
ill | +0.014 |
ver | +0.014 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.012 |
Ar | -0.011 |
situations | -0.011 |
Ro | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
AAAA | +0.007 |
Are | +0.007 |
Raw | +0.007 |
Sorry | +0.007 |
situations | +0.007 |
Neg logit contributions | |
oll | -0.013 |
aney | -0.013 |
he | -0.013 |
ier | -0.012 |
ax | -0.012 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
AAAA | +0.008 |
Fox | +0.008 |
Are | +0.007 |
Raw | +0.007 |
We | +0.007 |
Neg logit contributions | |
oll | -0.012 |
ier | -0.012 |
aney | -0.012 |
contain | -0.011 |
ax | -0.011 |
Token | ited |
Token ID | 863 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
oll | +0.023 |
ier | +0.021 |
aney | +0.017 |
contain | +0.013 |
ver | +0.010 |
Neg logit contributions | |
AAAA | -0.148 |
Raw | -0.146 |
Are | -0.146 |
Fox | -0.143 |
We | -0.141 |
Token | ly |
Token ID | 306 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ier | +0.361 |
oll | +0.357 |
aney | +0.338 |
contain | +0.319 |
ax | +0.316 |
Neg logit contributions | |
AAAA | -0.381 |
Raw | -0.379 |
Are | -0.370 |
Fox | -0.349 |
Look | -0.343 |
Token | , |
Token ID | 11 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
Raw | +0.098 |
AAAA | +0.093 |
Are | +0.092 |
Look | +0.091 |
Ar | +0.088 |
Neg logit contributions | |
oll | -0.076 |
ier | -0.073 |
aney | -0.064 |
ax | -0.064 |
contain | -0.062 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ier | +0.006 |
oll | +0.006 |
contain | +0.006 |
ax | +0.005 |
ver | +0.005 |
Neg logit contributions | |
Raw | -0.006 |
AAAA | -0.006 |
Are | -0.006 |
Ar | -0.005 |
Come | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.014 |
Are | +0.014 |
Fox | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.018 |
ier | -0.018 |
aney | -0.017 |
contain | -0.016 |
ax | -0.016 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ier | +0.000 |
oll | +0.000 |
ill | +0.000 |
contain | +0.000 |
ax | +0.000 |
Neg logit contributions | |
AAAA | -0.000 |
Raw | -0.000 |
Are | -0.000 |
Ar | -0.000 |
We | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.013 |
Are | +0.013 |
Sorry | +0.013 |
Look | +0.013 |
Neg logit contributions | |
ier | -0.043 |
oll | -0.041 |
aney | -0.039 |
contain | -0.039 |
aces | -0.038 |
Token | unknown |
Token ID | 6439 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Fox | -0.001 |
We | -0.001 |
Token | things |
Token ID | 1243 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ier | +0.105 |
oll | +0.102 |
aney | +0.097 |
contain | +0.097 |
ver | +0.092 |
Neg logit contributions | |
AAAA | -0.033 |
Raw | -0.030 |
Are | -0.029 |
Look | -0.025 |
Fox | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
things | +0.061 |
Are | +0.060 |
Fox | +0.059 |
cave | +0.056 |
We | +0.056 |
Neg logit contributions | |
oll | -0.125 |
aney | -0.124 |
ige | -0.119 |
ier | -0.114 |
ipp | -0.111 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.016 |
aney | +0.016 |
contain | +0.015 |
ver | +0.015 |
Neg logit contributions | |
AAAA | -0.008 |
Raw | -0.008 |
Are | -0.007 |
Peter | -0.007 |
Look | -0.007 |
Token | ited |
Token ID | 863 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
oll | +0.026 |
ier | +0.024 |
aces | +0.022 |
aney | +0.022 |
contain | +0.018 |
Neg logit contributions | |
AAAA | -0.057 |
Raw | -0.055 |
oc | -0.054 |
Ar | -0.053 |
Look | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ier | +0.289 |
oll | +0.289 |
aney | +0.263 |
contain | +0.248 |
ax | +0.240 |
Neg logit contributions | |
AAAA | -0.451 |
Raw | -0.445 |
Are | -0.438 |
Fox | -0.420 |
We | -0.414 |
Token | he |
Token ID | 339 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ier | +0.007 |
oll | +0.007 |
contain | +0.006 |
ver | +0.006 |
ax | +0.006 |
Neg logit contributions | |
AAAA | -0.007 |
Raw | -0.007 |
Come | -0.006 |
Are | -0.006 |
Look | -0.006 |
Token | kept |
Token ID | 4030 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
oll | +0.013 |
ier | +0.013 |
aney | +0.012 |
contain | +0.012 |
ver | +0.011 |
Neg logit contributions | |
AAAA | -0.012 |
Are | -0.011 |
Raw | -0.011 |
We | -0.011 |
Fox | -0.011 |
Token | exploring |
Token ID | 13504 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Raw | +0.030 |
AAAA | +0.029 |
Are | +0.029 |
Sorry | +0.027 |
We | +0.027 |
Neg logit contributions | |
oll | -0.037 |
ier | -0.037 |
contain | -0.035 |
ax | -0.034 |
aney | -0.033 |
Token | until |
Token ID | 1566 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
AAAA | +0.083 |
Raw | +0.081 |
Are | +0.081 |
Fox | +0.078 |
We | +0.076 |
Neg logit contributions | |
oll | -0.108 |
ier | -0.106 |
aney | -0.102 |
contain | -0.097 |
ax | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
AAAA | +0.063 |
Are | +0.062 |
Raw | +0.061 |
Fox | +0.058 |
We | +0.058 |
Neg logit contributions | |
oll | -0.083 |
ier | -0.082 |
aney | -0.076 |
contain | -0.074 |
ver | -0.071 |
Token | magical |
Token ID | 10883 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Come | +0.006 |
Raw | +0.006 |
We | +0.006 |
Are | +0.006 |
Neg logit contributions | |
ier | -0.007 |
oll | -0.007 |
aney | -0.006 |
contain | -0.006 |
salon | -0.006 |
Token | box |
Token ID | 3091 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ier | +0.029 |
oll | +0.029 |
aney | +0.027 |
contain | +0.027 |
ige | +0.025 |
Neg logit contributions | |
AAAA | -0.016 |
Raw | -0.016 |
Are | -0.015 |
Come | -0.015 |
We | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
cave | +0.011 |
We | +0.010 |
Are | +0.009 |
Fox | +0.009 |
hole | +0.009 |
Neg logit contributions | |
aney | -0.020 |
oll | -0.019 |
ier | -0.019 |
ige | -0.018 |
fourteen | -0.018 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
oll | +0.014 |
ver | +0.013 |
aces | +0.012 |
ents | +0.012 |
about | +0.012 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Sorry | -0.011 |
Look | -0.011 |
keeping | -0.010 |
Token | ited |
Token ID | 863 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
oll | +0.025 |
ier | +0.024 |
aney | +0.023 |
aces | +0.020 |
contain | +0.018 |
Neg logit contributions | |
AAAA | -0.067 |
Raw | -0.066 |
Are | -0.064 |
oc | -0.062 |
Look | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ier | +0.308 |
oll | +0.307 |
aney | +0.281 |
contain | +0.265 |
ax | +0.263 |
Neg logit contributions | |
AAAA | -0.433 |
Raw | -0.429 |
Are | -0.419 |
Look | -0.397 |
Fox | -0.396 |
Token | he |
Token ID | 339 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ver | +0.003 |
oll | +0.003 |
ier | +0.003 |
like | +0.003 |
pper | +0.003 |
Neg logit contributions | |
ASH | -0.002 |
keeping | -0.002 |
Raw | -0.002 |
Come | -0.002 |
situations | -0.002 |
Token | opened |
Token ID | 4721 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
oll | +0.014 |
ier | +0.013 |
aney | +0.013 |
contain | +0.012 |
ents | +0.012 |
Neg logit contributions | |
situations | -0.018 |
Raw | -0.018 |
AAAA | -0.017 |
Are | -0.017 |
We | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
oll | +0.011 |
ier | +0.011 |
aney | +0.010 |
contain | +0.010 |
ax | +0.010 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
Fox | -0.004 |
We | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.026 |
Are | +0.026 |
Fox | +0.025 |
We | +0.024 |
Neg logit contributions | |
oll | -0.033 |
ier | -0.032 |
aney | -0.031 |
contain | -0.030 |
ver | -0.028 |
Token | by |
Token ID | 416 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.027 |
Are | +0.026 |
Fox | +0.026 |
oc | +0.025 |
Neg logit contributions | |
ier | -0.027 |
contain | -0.025 |
aney | -0.024 |
oll | -0.024 |
ax | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.011 |
Fox | +0.010 |
We | +0.010 |
Neg logit contributions | |
oll | -0.011 |
ier | -0.011 |
aney | -0.011 |
contain | -0.010 |
ver | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
aney | +0.011 |
oll | +0.011 |
he | +0.010 |
about | +0.009 |
ax | +0.009 |
Neg logit contributions | |
AAAA | -0.011 |
situations | -0.011 |
Ar | -0.011 |
Raw | -0.010 |
cave | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.009 |
Are | +0.008 |
Fox | +0.008 |
situations | +0.008 |
Neg logit contributions | |
aney | -0.016 |
oll | -0.016 |
he | -0.016 |
ier | -0.016 |
ver | -0.015 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
AAAA | +0.010 |
Fox | +0.010 |
Raw | +0.009 |
Are | +0.009 |
We | +0.009 |
Neg logit contributions | |
oll | -0.014 |
ier | -0.014 |
aney | -0.014 |
contain | -0.013 |
he | -0.013 |
Token | ited |
Token ID | 863 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
ier | +0.020 |
oll | +0.019 |
aney | +0.015 |
contain | +0.013 |
ax | +0.010 |
Neg logit contributions | |
AAAA | -0.150 |
Raw | -0.149 |
Fox | -0.148 |
Are | -0.147 |
We | -0.144 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
oll | +0.303 |
ier | +0.302 |
aney | +0.283 |
contain | +0.261 |
ax | +0.259 |
Neg logit contributions | |
AAAA | -0.435 |
Raw | -0.434 |
Are | -0.424 |
Fox | -0.403 |
Ar | -0.400 |
Token | she |
Token ID | 673 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
oll | +0.009 |
ier | +0.008 |
aney | +0.008 |
contain | +0.008 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.006 |
Come | -0.005 |
Fox | -0.005 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
oll | +0.012 |
ier | +0.012 |
aney | +0.011 |
contain | +0.011 |
ver | +0.010 |
Neg logit contributions | |
Are | -0.012 |
situations | -0.012 |
AAAA | -0.012 |
Raw | -0.012 |
Fox | -0.012 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
AAAA | +0.024 |
Raw | +0.023 |
Are | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
ier | -0.025 |
oll | -0.025 |
contain | -0.024 |
aney | -0.023 |
ax | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ier | +0.074 |
oll | +0.074 |
contain | +0.073 |
aney | +0.072 |
ill | +0.066 |
Neg logit contributions | |
AAAA | -0.073 |
Raw | -0.070 |
Are | -0.069 |
Fox | -0.066 |
Sorry | -0.063 |
Token | found |
Token ID | 1043 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
oll | +0.019 |
ier | +0.019 |
aney | +0.018 |
contain | +0.017 |
ax | +0.016 |
Neg logit contributions | |
AAAA | -0.014 |
Raw | -0.014 |
Are | -0.014 |
Fox | -0.013 |
We | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
AAAA | +0.035 |
Raw | +0.034 |
Are | +0.034 |
Fox | +0.032 |
We | +0.031 |
Neg logit contributions | |
oll | -0.063 |
ier | -0.062 |
aney | -0.060 |
contain | -0.058 |
ver | -0.056 |
Token | coin |
Token ID | 10752 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
AAAA | +0.004 |
Come | +0.004 |
Raw | +0.004 |
We | +0.004 |
Are | +0.004 |
Neg logit contributions | |
oll | -0.005 |
ier | -0.004 |
aney | -0.004 |
contain | -0.004 |
salon | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
aney | +0.029 |
oll | +0.027 |
contain | +0.026 |
ier | +0.026 |
ige | +0.026 |
Neg logit contributions | |
cave | -0.013 |
things | -0.012 |
Fox | -0.011 |
hole | -0.011 |
We | -0.011 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
oll | +0.019 |
aney | +0.017 |
contain | +0.017 |
ver | +0.017 |
ax | +0.016 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Ar | -0.011 |
Peter | -0.011 |
situations | -0.011 |
Token | ited |
Token ID | 863 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
oll | +0.026 |
ier | +0.024 |
aney | +0.023 |
aces | +0.022 |
contain | +0.018 |
Neg logit contributions | |
AAAA | -0.062 |
Raw | -0.061 |
Are | -0.059 |
Look | -0.059 |
oc | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
oll | +0.354 |
ier | +0.352 |
aney | +0.328 |
contain | +0.312 |
ax | +0.306 |
Neg logit contributions | |
AAAA | -0.387 |
Raw | -0.381 |
Are | -0.373 |
Fox | -0.355 |
We | -0.349 |
Token | he |
Token ID | 339 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ver | +0.004 |
oll | +0.004 |
ier | +0.004 |
contain | +0.004 |
ax | +0.003 |
Neg logit contributions | |
Raw | -0.007 |
AAAA | -0.007 |
situations | -0.007 |
Come | -0.006 |
ASH | -0.006 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
oll | +0.015 |
ier | +0.014 |
aney | +0.014 |
contain | +0.013 |
ax | +0.013 |
Neg logit contributions | |
AAAA | -0.017 |
Are | -0.017 |
Raw | -0.017 |
situations | -0.017 |
We | -0.016 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
AAAA | +0.049 |
Raw | +0.048 |
Ar | +0.045 |
Are | +0.045 |
Look | +0.045 |
Neg logit contributions | |
oll | -0.038 |
ier | -0.038 |
ver | -0.033 |
aney | -0.033 |
contain | -0.033 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
oll | +0.092 |
ier | +0.090 |
contain | +0.083 |
aney | +0.081 |
ver | +0.079 |
Neg logit contributions | |
AAAA | -0.088 |
Raw | -0.087 |
Are | -0.086 |
Look | -0.084 |
Come | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Are | +0.022 |
things | +0.022 |
We | +0.021 |
Fox | +0.021 |
AAAA | +0.021 |
Neg logit contributions | |
oll | -0.043 |
aney | -0.042 |
ier | -0.042 |
contain | -0.039 |
ige | -0.039 |
Token | |
Token ID | 220 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
oll | +0.016 |
aney | +0.015 |
ier | +0.015 |
contain | +0.014 |
ax | +0.014 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.010 |
Are | -0.009 |
Fox | -0.009 |
Ar | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ier | +0.059 |
oll | +0.058 |
contain | +0.055 |
aney | +0.055 |
ige | +0.053 |
Neg logit contributions | |
AAAA | -0.012 |
Are | -0.012 |
Raw | -0.011 |
We | -0.010 |
Fox | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
AAAA | +0.013 |
Raw | +0.012 |
Fox | +0.011 |
Are | +0.011 |
Sorry | +0.011 |
Neg logit contributions | |
aney | -0.026 |
oll | -0.026 |
ier | -0.025 |
ver | -0.024 |
he | -0.024 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Fox | +0.013 |
Raw | +0.013 |
Are | +0.013 |
We | +0.012 |
Neg logit contributions | |
oll | -0.021 |
aney | -0.020 |
ier | -0.020 |
contain | -0.019 |
ax | -0.018 |
Token | ited |
Token ID | 863 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
oll | +0.026 |
ier | +0.025 |
aney | +0.020 |
contain | +0.016 |
ver | +0.013 |
Neg logit contributions | |
AAAA | -0.149 |
Raw | -0.147 |
Are | -0.147 |
Fox | -0.143 |
We | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
oll | +0.309 |
ier | +0.305 |
aney | +0.285 |
contain | +0.268 |
ax | +0.254 |
Neg logit contributions | |
AAAA | -0.429 |
Raw | -0.422 |
Are | -0.419 |
Fox | -0.404 |
We | -0.397 |
Token | try |
Token ID | 1949 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.017 |
aney | +0.016 |
contain | +0.015 |
ver | +0.015 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.011 |
Are | -0.011 |
Fox | -0.011 |
We | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
AAAA | +0.036 |
Are | +0.036 |
Raw | +0.036 |
Sorry | +0.033 |
We | +0.033 |
Neg logit contributions | |
oll | -0.044 |
ier | -0.044 |
aney | -0.041 |
contain | -0.040 |
ax | -0.039 |
Token | berries |
Token ID | 36322 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
AAAA | +0.015 |
Are | +0.014 |
Raw | +0.014 |
We | +0.013 |
Fox | +0.013 |
Neg logit contributions | |
oll | -0.025 |
ier | -0.025 |
aney | -0.024 |
contain | -0.023 |
ax | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
Fox | +0.025 |
things | +0.024 |
We | +0.021 |
Are | +0.021 |
cave | +0.021 |
Neg logit contributions | |
oll | -0.058 |
aney | -0.055 |
ige | -0.053 |
ier | -0.053 |
salon | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ier | +0.092 |
oll | +0.092 |
aney | +0.088 |
contain | +0.084 |
ax | +0.080 |
Neg logit contributions | |
AAAA | -0.080 |
Raw | -0.078 |
Are | -0.077 |
Fox | -0.073 |
We | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
AAAA | +0.038 |
Are | +0.037 |
Raw | +0.036 |
Sorry | +0.035 |
We | +0.035 |
Neg logit contributions | |
ier | -0.042 |
aney | -0.042 |
oll | -0.042 |
contain | -0.041 |
ill | -0.041 |
Token | water |
Token ID | 1660 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
AAAA | +0.012 |
Are | +0.011 |
Raw | +0.011 |
Come | +0.011 |
Fox | +0.011 |
Neg logit contributions | |
ier | -0.021 |
oll | -0.021 |
aney | -0.020 |
contain | -0.020 |
ax | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
cave | +0.009 |
Fox | +0.009 |
We | +0.009 |
Are | +0.009 |
things | +0.008 |
Neg logit contributions | |
oll | -0.018 |
aney | -0.017 |
ier | -0.016 |
ver | -0.016 |
contain | -0.016 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
oll | +0.020 |
ax | +0.017 |
aney | +0.017 |
ier | +0.017 |
ige | +0.017 |
Neg logit contributions | |
AAAA | -0.016 |
Raw | -0.016 |
cave | -0.016 |
Ar | -0.016 |
situations | -0.015 |
Token | ited |
Token ID | 863 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
oll | +0.025 |
ier | +0.023 |
aney | +0.021 |
aces | +0.019 |
contain | +0.018 |
Neg logit contributions | |
AAAA | -0.066 |
Raw | -0.065 |
Are | -0.063 |
Look | -0.063 |
oc | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
oll | +0.289 |
ier | +0.284 |
aney | +0.264 |
contain | +0.249 |
ver | +0.232 |
Neg logit contributions | |
AAAA | -0.448 |
Raw | -0.439 |
Are | -0.438 |
Fox | -0.424 |
We | -0.417 |
Token | Tina |
Token ID | 35903 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
oll | +0.007 |
ier | +0.007 |
contain | +0.006 |
ver | +0.006 |
ax | +0.006 |
Neg logit contributions | |
Raw | -0.005 |
AAAA | -0.004 |
Are | -0.004 |
Come | -0.004 |
cave | -0.004 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
oll | +0.009 |
ier | +0.009 |
aney | +0.009 |
contain | +0.008 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.007 |
Are | -0.006 |
Raw | -0.006 |
Fox | -0.006 |
We | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
AAAA | +0.020 |
Raw | +0.020 |
Are | +0.020 |
Fox | +0.019 |
We | +0.018 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
aney | -0.022 |
contain | -0.022 |
ax | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
contain | +0.016 |
oll | +0.016 |
aney | +0.015 |
ier | +0.015 |
ax | +0.015 |
Neg logit contributions | |
AAAA | -0.015 |
Raw | -0.014 |
Are | -0.014 |
We | -0.013 |
Fox | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
We | +0.040 |
things | +0.039 |
Fox | +0.037 |
places | +0.036 |
Help | +0.035 |
Neg logit contributions | |
oll | -0.089 |
aney | -0.084 |
ige | -0.081 |
ited | -0.078 |
contain | -0.076 |
Token | |
Token ID | 220 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
aney | +0.027 |
oll | +0.025 |
contain | +0.025 |
ver | +0.025 |
ier | +0.025 |
Neg logit contributions | |
Raw | -0.019 |
AAAA | -0.019 |
Ro | -0.017 |
Fox | -0.016 |
cave | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
oll | +0.060 |
ier | +0.060 |
aney | +0.058 |
ver | +0.056 |
contain | +0.055 |
Neg logit contributions | |
AAAA | -0.023 |
Raw | -0.023 |
Are | -0.021 |
Fox | -0.020 |
Look | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.004 |
Are | +0.004 |
Fox | +0.004 |
situations | +0.004 |
Neg logit contributions | |
aney | -0.009 |
oll | -0.009 |
ier | -0.009 |
ver | -0.008 |
he | -0.008 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Fox | +0.005 |
Are | +0.005 |
Come | +0.004 |
Neg logit contributions | |
aney | -0.008 |
ier | -0.008 |
oll | -0.008 |
contain | -0.007 |
ver | -0.007 |
Token | ited |
Token ID | 863 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
oll | +0.032 |
ier | +0.028 |
aney | +0.023 |
contain | +0.020 |
ver | +0.017 |
Neg logit contributions | |
AAAA | -0.145 |
Are | -0.143 |
Raw | -0.142 |
Look | -0.137 |
We | -0.137 |
Token | for |
Token ID | 329 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
oll | +0.371 |
ier | +0.364 |
aney | +0.345 |
contain | +0.331 |
ver | +0.316 |
Neg logit contributions | |
AAAA | -0.364 |
Are | -0.356 |
Raw | -0.354 |
Fox | -0.344 |
We | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
AAAA | +0.002 |
Are | +0.002 |
Raw | +0.002 |
Fox | +0.002 |
We | +0.002 |
Neg logit contributions | |
oll | -0.004 |
ier | -0.004 |
aney | -0.004 |
contain | -0.004 |
ver | -0.004 |
Token | surprise |
Token ID | 5975 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
AAAA | +0.019 |
Raw | +0.018 |
Are | +0.018 |
Fox | +0.018 |
We | +0.017 |
Neg logit contributions | |
oll | -0.026 |
ier | -0.026 |
aney | -0.025 |
contain | -0.024 |
ax | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
oll | +0.014 |
ier | +0.013 |
aney | +0.013 |
ige | +0.012 |
contain | +0.012 |
Neg logit contributions | |
Are | -0.008 |
Fox | -0.008 |
We | -0.008 |
AAAA | -0.008 |
things | -0.007 |
Token | John |
Token ID | 1757 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ier | +0.010 |
oll | +0.009 |
aney | +0.009 |
contain | +0.009 |
ver | +0.009 |
Neg logit contributions | |
AAAA | -0.007 |
Raw | -0.007 |
Are | -0.007 |
Come | -0.007 |
Fox | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
AAAA | +0.043 |
Raw | +0.042 |
Are | +0.042 |
Fox | +0.038 |
We | +0.038 |
Neg logit contributions | |
oll | -0.073 |
ier | -0.072 |
aney | -0.069 |
contain | -0.067 |
ax | -0.064 |
Token | k |
Token ID | 479 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
AAAA | +0.016 |
Are | +0.015 |
Raw | +0.015 |
things | +0.015 |
Fox | +0.015 |
Neg logit contributions | |
oll | -0.029 |
ier | -0.028 |
aney | -0.027 |
ax | -0.026 |
ill | -0.025 |
Token | ite |
Token ID | 578 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
AAAA | +0.028 |
Raw | +0.027 |
Are | +0.027 |
Fox | +0.026 |
We | +0.026 |
Neg logit contributions | |
oll | -0.016 |
ier | -0.015 |
aney | -0.014 |
contain | -0.013 |
ver | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
oll | +0.086 |
aney | +0.083 |
ier | +0.081 |
ax | +0.077 |
contain | +0.075 |
Neg logit contributions | |
Fox | -0.042 |
We | -0.042 |
cave | -0.041 |
things | -0.040 |
Are | -0.039 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
oll | +0.018 |
aney | +0.017 |
ier | +0.017 |
contain | +0.017 |
ver | +0.016 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.011 |
Peter | -0.010 |
Are | -0.010 |
Ar | -0.010 |
Token | ited |
Token ID | 863 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
oll | +0.025 |
ier | +0.023 |
aney | +0.021 |
aces | +0.020 |
ver | +0.017 |
Neg logit contributions | |
AAAA | -0.063 |
Raw | -0.061 |
Are | -0.059 |
Look | -0.059 |
oc | -0.059 |
Token | ly |
Token ID | 306 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
oll | +0.359 |
ier | +0.358 |
aney | +0.336 |
contain | +0.319 |
ax | +0.308 |
Neg logit contributions | |
AAAA | -0.377 |
Raw | -0.371 |
Are | -0.366 |
Fox | -0.349 |
We | -0.342 |
Token | , |
Token ID | 11 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
Raw | +0.096 |
AAAA | +0.092 |
Are | +0.091 |
Look | +0.089 |
Ar | +0.086 |
Neg logit contributions | |
ier | -0.082 |
oll | -0.081 |
aney | -0.072 |
contain | -0.070 |
ax | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ier | +0.005 |
ver | +0.005 |
contain | +0.005 |
oll | +0.004 |
ax | +0.004 |
Neg logit contributions | |
Raw | -0.007 |
AAAA | -0.006 |
Ar | -0.006 |
Come | -0.006 |
situations | -0.006 |
Token | child |
Token ID | 1200 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.010 |
Are | +0.010 |
Fox | +0.009 |
We | +0.009 |
Neg logit contributions | |
oll | -0.032 |
ier | -0.031 |
aney | -0.030 |
contain | -0.029 |
ax | -0.028 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
AAAA | +0.022 |
Fox | +0.021 |
Are | +0.021 |
Raw | +0.021 |
We | +0.020 |
Neg logit contributions | |
oll | -0.046 |
ier | -0.044 |
aney | -0.043 |
contain | -0.040 |
ige | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
things | +0.038 |
Fox | +0.032 |
We | +0.031 |
packages | +0.028 |
cave | +0.028 |
Neg logit contributions | |
oll | -0.083 |
aney | -0.081 |
vious | -0.078 |
ige | -0.076 |
ited | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
AAAA | +0.033 |
Are | +0.032 |
Raw | +0.032 |
Fox | +0.031 |
We | +0.030 |
Neg logit contributions | |
oll | -0.053 |
ier | -0.052 |
aney | -0.048 |
contain | -0.047 |
ver | -0.045 |
Token | freezer |
Token ID | 30967 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
AAAA | +0.023 |
Raw | +0.022 |
Peter | +0.021 |
Ar | +0.020 |
Are | +0.020 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.018 |
aney | -0.018 |
contain | -0.016 |
ige | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
oll | +0.024 |
aney | +0.023 |
contain | +0.022 |
ier | +0.022 |
ige | +0.022 |
Neg logit contributions | |
things | -0.011 |
cave | -0.010 |
We | -0.010 |
Fox | -0.010 |
Are | -0.009 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
aney | +0.014 |
oll | +0.014 |
ier | +0.013 |
ill | +0.013 |
contain | +0.013 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.013 |
Ar | -0.013 |
Fox | -0.012 |
cave | -0.012 |
Token | ited |
Token ID | 863 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
oll | +0.024 |
ier | +0.023 |
aney | +0.020 |
aces | +0.020 |
contain | +0.018 |
Neg logit contributions | |
AAAA | -0.058 |
Raw | -0.055 |
Look | -0.054 |
Are | -0.054 |
oc | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
oll | +0.313 |
ier | +0.304 |
aney | +0.285 |
contain | +0.273 |
ver | +0.261 |
Neg logit contributions | |
AAAA | -0.421 |
Are | -0.414 |
Raw | -0.409 |
Fox | -0.403 |
We | -0.398 |
Token | she |
Token ID | 673 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ier | +0.008 |
oll | +0.008 |
aney | +0.008 |
contain | +0.008 |
ver | +0.008 |
Neg logit contributions | |
Raw | -0.007 |
AAAA | -0.007 |
Ar | -0.007 |
Fox | -0.007 |
Are | -0.007 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
oll | +0.011 |
ier | +0.010 |
aney | +0.010 |
contain | +0.009 |
ax | +0.009 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
Are | -0.009 |
Fox | -0.009 |
We | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
oll | +0.003 |
ier | +0.003 |
aney | +0.002 |
contain | +0.002 |
ver | +0.002 |
Neg logit contributions | |
Fox | -0.001 |
AAAA | -0.001 |
things | -0.001 |
Look | -0.001 |
Are | -0.001 |
Token | freezer |
Token ID | 30967 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
AAAA | +0.019 |
Are | +0.018 |
Raw | +0.018 |
Fox | +0.017 |
We | +0.017 |
Neg logit contributions | |
oll | -0.029 |
ier | -0.029 |
aney | -0.027 |
contain | -0.026 |
ver | -0.025 |
Token | piece |
Token ID | 3704 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
AAAA | +0.012 |
Are | +0.012 |
Raw | +0.012 |
Fox | +0.011 |
We | +0.011 |
Neg logit contributions | |
oll | -0.016 |
ier | -0.016 |
aney | -0.015 |
contain | -0.014 |
ver | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
aney | +0.070 |
ige | +0.068 |
oll | +0.066 |
ier | +0.066 |
ver | +0.065 |
Neg logit contributions | |
cave | -0.074 |
We | -0.071 |
Are | -0.069 |
Fox | -0.068 |
Water | -0.068 |
Token | gum |
Token ID | 27142 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
oll | +0.079 |
ier | +0.077 |
aney | +0.074 |
contain | +0.072 |
ige | +0.069 |
Neg logit contributions | |
AAAA | -0.059 |
Raw | -0.057 |
Are | -0.056 |
Fox | -0.054 |
We | -0.053 |
Token | ! |
Token ID | 0 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
aney | +0.134 |
oll | +0.129 |
ier | +0.127 |
contain | +0.126 |
ver | +0.121 |
Neg logit contributions | |
Fox | -0.070 |
Are | -0.069 |
AAAA | -0.069 |
cave | -0.068 |
Raw | -0.068 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Raw | +0.033 |
AAAA | +0.033 |
Fox | +0.032 |
Ar | +0.031 |
situations | +0.031 |
Neg logit contributions | |
aney | -0.040 |
oll | -0.038 |
ver | -0.035 |
ill | -0.035 |
ax | -0.034 |
Token | ited |
Token ID | 863 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
oll | +0.029 |
ier | +0.027 |
aces | +0.025 |
aney | +0.023 |
iness | +0.020 |
Neg logit contributions | |
AAAA | -0.057 |
Raw | -0.054 |
Look | -0.054 |
oc | -0.053 |
Ar | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
oll | +0.399 |
ier | +0.394 |
aney | +0.374 |
contain | +0.359 |
ver | +0.343 |
Neg logit contributions | |
AAAA | -0.337 |
Raw | -0.329 |
Are | -0.327 |
Fox | -0.313 |
We | -0.306 |
Token | she |
Token ID | 673 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
oll | +0.006 |
ier | +0.006 |
aney | +0.006 |
contain | +0.005 |
ver | +0.005 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.005 |
Fox | -0.005 |
Ar | -0.005 |
Token | climbed |
Token ID | 19952 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
oll | +0.011 |
ier | +0.010 |
aney | +0.010 |
contain | +0.009 |
ax | +0.009 |
Neg logit contributions | |
AAAA | -0.011 |
Are | -0.011 |
Raw | -0.011 |
situations | -0.011 |
We | -0.011 |
Token | over |
Token ID | 625 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ier | +0.164 |
oll | +0.164 |
aney | +0.153 |
contain | +0.149 |
ax | +0.146 |
Neg logit contributions | |
AAAA | -0.114 |
Raw | -0.112 |
Are | -0.112 |
Fox | -0.103 |
We | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
oll | +0.072 |
ier | +0.071 |
aney | +0.069 |
contain | +0.066 |
ver | +0.064 |
Neg logit contributions | |
AAAA | -0.047 |
Are | -0.046 |
Raw | -0.046 |
Fox | -0.042 |
We | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
things | +0.015 |
We | +0.014 |
Raw | +0.014 |
Are | +0.014 |
places | +0.014 |
Neg logit contributions | |
oll | -0.028 |
aney | -0.026 |
ier | -0.025 |
contain | -0.024 |
ige | -0.024 |
Token | |
Token ID | 220 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.017 |
aney | +0.017 |
ax | +0.016 |
contain | +0.016 |
Neg logit contributions | |
Raw | -0.009 |
AAAA | -0.009 |
Are | -0.008 |
cave | -0.008 |
Peter | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
oll | +0.069 |
ier | +0.069 |
aney | +0.066 |
contain | +0.065 |
ige | +0.062 |
Neg logit contributions | |
AAAA | -0.016 |
Are | -0.015 |
Raw | -0.014 |
We | -0.013 |
Fox | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
AAAA | +0.004 |
Raw | +0.004 |
Are | +0.004 |
Fox | +0.004 |
We | +0.003 |
Neg logit contributions | |
oll | -0.012 |
ier | -0.012 |
aney | -0.012 |
contain | -0.011 |
ver | -0.011 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.009 |
aney | -0.009 |
contain | -0.008 |
ax | -0.008 |
Token | ited |
Token ID | 863 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
oll | +0.038 |
ier | +0.038 |
aney | +0.033 |
contain | +0.029 |
ax | +0.025 |
Neg logit contributions | |
AAAA | -0.137 |
Raw | -0.136 |
Are | -0.135 |
Fox | -0.132 |
We | -0.130 |
Token | ly |
Token ID | 306 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
oll | +0.305 |
ier | +0.301 |
aney | +0.280 |
contain | +0.265 |
ax | +0.250 |
Neg logit contributions | |
AAAA | -0.431 |
Raw | -0.424 |
Are | -0.421 |
Fox | -0.407 |
We | -0.399 |
Token | , |
Token ID | 11 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
AAAA | +0.081 |
Raw | +0.080 |
Are | +0.078 |
Fox | +0.075 |
We | +0.073 |
Neg logit contributions | |
oll | -0.090 |
ier | -0.088 |
aney | -0.083 |
contain | -0.080 |
ax | -0.077 |
Token | Ark |
Token ID | 9128 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ier | +0.008 |
oll | +0.008 |
aney | +0.007 |
contain | +0.007 |
ax | +0.007 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
Come | -0.005 |
Fox | -0.005 |
Token | ie |
Token ID | 494 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
AAAA | +0.028 |
Fox | +0.027 |
Are | +0.027 |
Raw | +0.027 |
Peter | +0.026 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.022 |
aney | -0.022 |
contain | -0.021 |
ver | -0.020 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.011 |
Fox | +0.010 |
We | +0.010 |
Neg logit contributions | |
oll | -0.015 |
ier | -0.015 |
aney | -0.015 |
contain | -0.014 |
ige | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
We | +0.049 |
Are | +0.046 |
things | +0.046 |
Fox | +0.046 |
cave | +0.044 |
Neg logit contributions | |
oll | -0.090 |
ier | -0.087 |
aney | -0.086 |
ige | -0.081 |
ax | -0.080 |
Token | |
Token ID | 220 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
aney | +0.019 |
oll | +0.018 |
contain | +0.017 |
ier | +0.016 |
ver | +0.016 |
Neg logit contributions | |
AAAA | -0.015 |
Raw | -0.015 |
Fox | -0.013 |
situations | -0.013 |
oc | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
oll | +0.070 |
ier | +0.070 |
aney | +0.067 |
contain | +0.066 |
ax | +0.063 |
Neg logit contributions | |
AAAA | -0.017 |
Are | -0.016 |
Raw | -0.016 |
Fox | -0.014 |
We | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.004 |
Are | +0.004 |
Fox | +0.004 |
situations | +0.004 |
Neg logit contributions | |
aney | -0.011 |
oll | -0.011 |
ier | -0.010 |
contain | -0.010 |
ver | -0.010 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.006 |
Fox | +0.006 |
Are | +0.006 |
Come | +0.006 |
Neg logit contributions | |
aney | -0.008 |
oll | -0.008 |
ier | -0.008 |
contain | -0.008 |
ver | -0.007 |
Token | ited |
Token ID | 863 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
oll | +0.023 |
ier | +0.023 |
aney | +0.018 |
contain | +0.015 |
ax | +0.011 |
Neg logit contributions | |
AAAA | -0.148 |
Raw | -0.146 |
Are | -0.145 |
Fox | -0.143 |
We | -0.141 |
Token | ly |
Token ID | 306 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oll | +0.311 |
ier | +0.306 |
aney | +0.286 |
contain | +0.270 |
ax | +0.254 |
Neg logit contributions | |
AAAA | -0.425 |
Raw | -0.417 |
Are | -0.416 |
Fox | -0.402 |
We | -0.395 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Raw | +0.088 |
AAAA | +0.086 |
Are | +0.083 |
Look | +0.080 |
Ar | +0.078 |
Neg logit contributions | |
oll | -0.085 |
ier | -0.084 |
aney | -0.078 |
contain | -0.075 |
ax | -0.073 |
Token | Annie |
Token ID | 25860 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
oll | +0.009 |
ier | +0.009 |
aney | +0.009 |
contain | +0.008 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.006 |
Fox | -0.005 |
Come | -0.005 |
Token | went |
Token ID | 1816 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
AAAA | +0.136 |
Raw | +0.130 |
Are | +0.129 |
Fox | +0.125 |
We | +0.121 |
Neg logit contributions | |
oll | -0.205 |
ier | -0.203 |
aney | -0.193 |
contain | -0.187 |
ax | -0.178 |
Token | out |
Token ID | 503 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
AAAA | +0.029 |
Raw | +0.028 |
Are | +0.028 |
Fox | +0.026 |
We | +0.026 |
Neg logit contributions | |
ier | -0.034 |
oll | -0.034 |
aney | -0.031 |
contain | -0.031 |
ax | -0.029 |
Token | field |
Token ID | 2214 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
AAAA | +0.018 |
Are | +0.018 |
Raw | +0.018 |
Come | +0.017 |
Sorry | +0.016 |
Neg logit contributions | |
ier | -0.020 |
oll | -0.019 |
aney | -0.018 |
he | -0.017 |
contain | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
oll | +0.044 |
ier | +0.041 |
aney | +0.039 |
ige | +0.039 |
ax | +0.038 |
Neg logit contributions | |
We | -0.021 |
cave | -0.021 |
Fox | -0.020 |
things | -0.020 |
Come | -0.019 |
Token | corn |
Token ID | 11676 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
oll | +0.059 |
ier | +0.056 |
aney | +0.053 |
contain | +0.052 |
ige | +0.051 |
Neg logit contributions | |
Are | -0.078 |
AAAA | -0.076 |
Raw | -0.076 |
We | -0.075 |
Sorry | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Fox | +0.042 |
AAAA | +0.041 |
Are | +0.041 |
Raw | +0.041 |
We | +0.040 |
Neg logit contributions | |
oll | -0.058 |
ier | -0.057 |
aney | -0.055 |
contain | -0.052 |
ige | -0.050 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
aney | +0.018 |
oll | +0.017 |
contain | +0.017 |
ill | +0.016 |
ax | +0.016 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.010 |
Peter | -0.009 |
Ar | -0.009 |
Fox | -0.009 |
Token | ited |
Token ID | 863 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
oll | +0.027 |
ier | +0.025 |
aces | +0.023 |
aney | +0.022 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.066 |
Raw | -0.064 |
Look | -0.062 |
Ar | -0.061 |
oc | -0.061 |
Token | ly |
Token ID | 306 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
oll | +0.355 |
ier | +0.350 |
aney | +0.330 |
contain | +0.315 |
ver | +0.299 |
Neg logit contributions | |
AAAA | -0.380 |
Raw | -0.371 |
Are | -0.371 |
Fox | -0.358 |
We | -0.350 |
Token | , |
Token ID | 11 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
Raw | +0.086 |
AAAA | +0.084 |
Are | +0.083 |
Look | +0.078 |
We | +0.077 |
Neg logit contributions | |
oll | -0.087 |
ier | -0.086 |
aney | -0.080 |
contain | -0.077 |
ax | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ier | +0.006 |
aney | +0.006 |
oll | +0.006 |
contain | +0.006 |
ver | +0.006 |
Neg logit contributions | |
Raw | -0.007 |
AAAA | -0.007 |
Ar | -0.006 |
Are | -0.006 |
cave | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
AAAA | +0.011 |
Fox | +0.011 |
Are | +0.011 |
things | +0.011 |
Raw | +0.011 |
Neg logit contributions | |
oll | -0.030 |
ier | -0.030 |
aney | -0.028 |
contain | -0.028 |
ax | -0.027 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.000 |
Raw | -0.000 |
Are | -0.000 |
Fox | -0.000 |
We | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ier | +0.077 |
oll | +0.075 |
aney | +0.068 |
contain | +0.067 |
ver | +0.064 |
Neg logit contributions | |
AAAA | -0.091 |
Raw | -0.090 |
Are | -0.089 |
Come | -0.082 |
Fox | -0.082 |
Token | |
Token ID | 220 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
oll | +0.014 |
ver | +0.013 |
ax | +0.013 |
aney | +0.013 |
ill | +0.013 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
Are | -0.009 |
Fox | -0.009 |
situations | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
oll | +0.064 |
ier | +0.064 |
aney | +0.062 |
contain | +0.060 |
ver | +0.058 |
Neg logit contributions | |
AAAA | -0.018 |
Raw | -0.017 |
Are | -0.017 |
Fox | -0.016 |
We | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
AAAA | +0.007 |
Raw | +0.007 |
Are | +0.006 |
situations | +0.006 |
Fox | +0.006 |
Neg logit contributions | |
oll | -0.012 |
aney | -0.012 |
ver | -0.012 |
ier | -0.012 |
ax | -0.012 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Fox | +0.008 |
AAAA | +0.008 |
Are | +0.008 |
Raw | +0.007 |
We | +0.007 |
Neg logit contributions | |
oll | -0.010 |
ier | -0.010 |
aney | -0.009 |
contain | -0.009 |
ver | -0.009 |
Token | ited |
Token ID | 863 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
oll | +0.025 |
ier | +0.024 |
aney | +0.020 |
contain | +0.016 |
ax | +0.013 |
Neg logit contributions | |
AAAA | -0.147 |
Raw | -0.145 |
Are | -0.144 |
Fox | -0.142 |
We | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
ier | +0.343 |
oll | +0.343 |
aney | +0.317 |
contain | +0.300 |
ax | +0.297 |
Neg logit contributions | |
AAAA | -0.395 |
Raw | -0.391 |
Are | -0.383 |
Fox | -0.361 |
Look | -0.358 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
ier | +0.007 |
oll | +0.007 |
contain | +0.007 |
ver | +0.007 |
ax | +0.006 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.006 |
Come | -0.006 |
situations | -0.005 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
oll | +0.032 |
ier | +0.031 |
aney | +0.030 |
contain | +0.029 |
ver | +0.028 |
Neg logit contributions | |
AAAA | -0.021 |
Raw | -0.020 |
Are | -0.020 |
Fox | -0.020 |
We | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
AAAA | +0.089 |
Raw | +0.089 |
Are | +0.084 |
Fox | +0.081 |
Look | +0.078 |
Neg logit contributions | |
ier | -0.094 |
oll | -0.091 |
contain | -0.088 |
aney | -0.084 |
ax | -0.084 |
Token | explore |
Token ID | 7301 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
oll | +0.016 |
ier | +0.016 |
aney | +0.015 |
contain | +0.015 |
ver | +0.014 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.012 |
Are | -0.012 |
Fox | -0.011 |
We | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Fox | -0.001 |
Come | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Are | +0.019 |
Raw | +0.019 |
AAAA | +0.018 |
Fox | +0.018 |
cave | +0.017 |
Neg logit contributions | |
oll | -0.041 |
ier | -0.040 |
aney | -0.040 |
ax | -0.038 |
ige | -0.038 |
Token | perfect |
Token ID | 2818 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
cave | +0.004 |
Fox | +0.004 |
things | +0.004 |
Are | +0.004 |
noise | +0.004 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.008 |
aney | -0.008 |
ax | -0.008 |
contain | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
aney | +0.005 |
oll | +0.004 |
contain | +0.004 |
ax | +0.004 |
ver | +0.004 |
Neg logit contributions | |
things | -0.002 |
cave | -0.002 |
We | -0.002 |
Fox | -0.002 |
places | -0.002 |
Token | Exc |
Token ID | 25268 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
oll | +0.013 |
aney | +0.012 |
ier | +0.012 |
contain | +0.012 |
ver | +0.011 |
Neg logit contributions | |
AAAA | -0.009 |
Raw | -0.008 |
Are | -0.008 |
Ar | -0.008 |
Fox | -0.007 |
Token | ited |
Token ID | 863 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
oll | +0.027 |
ier | +0.025 |
aces | +0.024 |
aney | +0.022 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.053 |
Raw | -0.053 |
oc | -0.052 |
Look | -0.050 |
Are | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
oll | +0.396 |
ier | +0.383 |
aney | +0.367 |
contain | +0.356 |
ver | +0.346 |
Neg logit contributions | |
AAAA | -0.336 |
Are | -0.332 |
Raw | -0.324 |
Fox | -0.322 |
We | -0.318 |
Token | she |
Token ID | 673 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
oll | +0.005 |
ier | +0.005 |
aney | +0.005 |
contain | +0.005 |
ver | +0.005 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
Come | -0.005 |
Ar | -0.005 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.010 |
aney | +0.009 |
contain | +0.009 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.008 |
Raw | -0.008 |
Are | -0.008 |
Fox | -0.007 |
We | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
AAAA | +0.024 |
Raw | +0.023 |
Are | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
oll | -0.029 |
ier | -0.029 |
aney | -0.028 |
contain | -0.027 |
ax | -0.026 |
Token | get |
Token ID | 651 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.016 |
contain | +0.016 |
aney | +0.016 |
ax | +0.015 |
Neg logit contributions | |
AAAA | -0.015 |
Raw | -0.014 |
Are | -0.014 |
Fox | -0.013 |
We | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
oll | +0.052 |
aney | +0.052 |
ier | +0.051 |
contain | +0.048 |
ige | +0.048 |
Neg logit contributions | |
Are | -0.021 |
Fox | -0.021 |
We | -0.021 |
Come | -0.020 |
AAAA | -0.020 |
Token | eating |
Token ID | 6600 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ier | +0.017 |
oll | +0.017 |
contain | +0.015 |
about | +0.015 |
like | +0.014 |
Neg logit contributions | |
AAAA | -0.019 |
Raw | -0.017 |
Quick | -0.017 |
Ar | -0.016 |
Are | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
AAAA | +0.061 |
Raw | +0.059 |
Are | +0.059 |
Fox | +0.056 |
We | +0.054 |
Neg logit contributions | |
oll | -0.111 |
ier | -0.109 |
aney | -0.105 |
contain | -0.101 |
ver | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Fox | +0.021 |
We | +0.021 |
Are | +0.021 |
things | +0.020 |
Raw | +0.020 |
Neg logit contributions | |
oll | -0.031 |
aney | -0.031 |
ier | -0.031 |
ige | -0.029 |
contain | -0.029 |
Token | resting |
Token ID | 19186 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
oll | +0.003 |
ier | +0.003 |
contain | +0.003 |
aney | +0.003 |
ax | +0.003 |
Neg logit contributions | |
AAAA | -0.003 |
Raw | -0.003 |
Are | -0.003 |
Fox | -0.003 |
Ar | -0.002 |
Token | afterward |
Token ID | 20875 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
AAAA | +0.074 |
Raw | +0.072 |
Are | +0.072 |
Fox | +0.068 |
We | +0.067 |
Neg logit contributions | |
oll | -0.087 |
ier | -0.086 |
aney | -0.081 |
contain | -0.078 |
ver | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Are | +0.324 |
Fox | +0.320 |
We | +0.316 |
AAAA | +0.312 |
Raw | +0.311 |
Neg logit contributions | |
oll | -0.460 |
aney | -0.450 |
ier | -0.448 |
contain | -0.424 |
ige | -0.412 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
oll | +0.017 |
ver | +0.016 |
he | +0.015 |
about | +0.014 |
aney | +0.014 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.012 |
pans | -0.011 |
situations | -0.011 |
cave | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.021 |
he | +0.020 |
aney | +0.020 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Are | -0.010 |
Sorry | -0.010 |
situations | -0.010 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ier | +0.061 |
oll | +0.061 |
contain | +0.058 |
ige | +0.057 |
aces | +0.055 |
Neg logit contributions | |
We | -0.031 |
things | -0.031 |
Are | -0.030 |
Fox | -0.030 |
cave | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
AAAA | +0.059 |
Raw | +0.058 |
Are | +0.057 |
Fox | +0.055 |
We | +0.053 |
Neg logit contributions | |
oll | -0.088 |
ier | -0.087 |
aney | -0.083 |
contain | -0.080 |
ver | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
AAAA | +0.123 |
Are | +0.123 |
Fox | +0.120 |
Raw | +0.120 |
We | +0.118 |
Neg logit contributions | |
oll | -0.181 |
ier | -0.175 |
aney | -0.170 |
contain | -0.165 |
ax | -0.158 |
Token | books |
Token ID | 3835 |
Feature activation | +3.78e-04 |
Pos logit contributions | |
AAAA | +0.012 |
Raw | +0.012 |
Are | +0.011 |
Fox | +0.011 |
Come | +0.011 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.020 |
aney | -0.019 |
contain | -0.019 |
ax | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
oll | +0.000 |
aney | +0.000 |
ige | +0.000 |
ax | +0.000 |
ipp | +0.000 |
Neg logit contributions | |
We | -0.000 |
things | -0.000 |
sounds | -0.000 |
cave | -0.000 |
packages | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.008 |
Peter | +0.008 |
Are | +0.007 |
oc | +0.007 |
Neg logit contributions | |
oll | -0.021 |
aney | -0.020 |
ier | -0.019 |
contain | -0.019 |
ill | -0.018 |
Token | see |
Token ID | 766 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Are | +0.018 |
Raw | +0.017 |
Fox | +0.017 |
We | +0.016 |
AAAA | +0.016 |
Neg logit contributions | |
oll | -0.036 |
ier | -0.035 |
aney | -0.034 |
ige | -0.032 |
ipp | -0.031 |
Token | alt |
Token ID | 5988 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
things | +0.067 |
Are | +0.066 |
Fox | +0.065 |
We | +0.063 |
AAAA | +0.063 |
Neg logit contributions | |
oll | -0.157 |
ier | -0.153 |
aney | -0.149 |
contain | -0.146 |
ver | -0.145 |
Token | ars |
Token ID | 945 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
AAAA | +0.356 |
Are | +0.345 |
Raw | +0.344 |
We | +0.331 |
Come | +0.325 |
Neg logit contributions | |
oll | -0.393 |
ier | -0.386 |
aney | -0.364 |
contain | -0.349 |
ax | -0.331 |
Token | and |
Token ID | 290 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
oll | +0.062 |
ier | +0.057 |
aney | +0.056 |
ige | +0.054 |
contain | +0.053 |
Neg logit contributions | |
We | -0.024 |
things | -0.024 |
Fox | -0.024 |
Are | -0.024 |
sounds | -0.023 |
Token | offerings |
Token ID | 18369 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.013 |
Are | +0.013 |
Fox | +0.013 |
Come | +0.012 |
Neg logit contributions | |
oll | -0.019 |
ier | -0.019 |
aney | -0.018 |
contain | -0.018 |
ax | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Are | +0.084 |
Fox | +0.083 |
things | +0.083 |
We | +0.083 |
AAAA | +0.082 |
Neg logit contributions | |
oll | -0.148 |
aney | -0.139 |
ier | -0.137 |
contain | -0.135 |
ige | -0.130 |
Token | priests |
Token ID | 17345 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
AAAA | +0.013 |
Raw | +0.012 |
Are | +0.012 |
Fox | +0.012 |
We | +0.012 |
Neg logit contributions | |
oll | -0.021 |
ier | -0.021 |
aney | -0.020 |
contain | -0.019 |
ver | -0.018 |
Token | little |
Token ID | 1310 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
AAAA | +0.010 |
Raw | +0.009 |
Are | +0.009 |
Fox | +0.009 |
Look | +0.008 |
Neg logit contributions | |
oll | -0.021 |
ier | -0.021 |
aney | -0.020 |
contain | -0.019 |
ver | -0.019 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
AAAA | +0.002 |
Raw | +0.002 |
Are | +0.002 |
Fox | +0.002 |
We | +0.002 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
contain | -0.003 |
ax | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
AAAA | +0.004 |
Are | +0.004 |
Fox | +0.004 |
oc | +0.004 |
Raw | +0.004 |
Neg logit contributions | |
aney | -0.013 |
oll | -0.013 |
contain | -0.013 |
ier | -0.013 |
ige | -0.012 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Fox | +0.004 |
AAAA | +0.004 |
cave | +0.004 |
Raw | +0.004 |
things | +0.004 |
Neg logit contributions | |
aney | -0.012 |
oll | -0.011 |
ier | -0.011 |
contain | -0.011 |
ill | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
aney | +0.113 |
oll | +0.112 |
ier | +0.110 |
contain | +0.104 |
ige | +0.103 |
Neg logit contributions | |
Are | -0.085 |
Fox | -0.083 |
AAAA | -0.083 |
We | -0.081 |
Raw | -0.080 |
Token | bec |
Token ID | 639 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
oll | +0.005 |
ier | +0.005 |
aney | +0.004 |
contain | +0.004 |
ver | +0.004 |
Neg logit contributions | |
AAAA | -0.004 |
Raw | -0.004 |
Are | -0.004 |
Fox | -0.003 |
Come | -0.003 |
Token | as |
Token ID | 292 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
AAAA | +0.346 |
Peter | +0.331 |
Look | +0.328 |
Raw | +0.324 |
Are | +0.320 |
Neg logit contributions | |
contain | -0.360 |
oll | -0.347 |
aney | -0.342 |
ier | -0.311 |
ilies | -0.300 |
Token | ue |
Token ID | 518 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
oll | +0.202 |
aney | +0.192 |
ige | +0.180 |
fourteen | +0.173 |
contain | +0.172 |
Neg logit contributions | |
things | -0.108 |
Fox | -0.105 |
Are | -0.097 |
We | -0.096 |
cave | -0.091 |
Token | he |
Token ID | 339 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
oll | +0.061 |
contain | +0.061 |
ier | +0.061 |
aney | +0.061 |
obb | +0.058 |
Neg logit contributions | |
things | -0.017 |
Fox | -0.016 |
We | -0.014 |
sounds | -0.013 |
cave | -0.013 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
aney | +0.019 |
ier | +0.019 |
oll | +0.018 |
contain | +0.017 |
ax | +0.017 |
Neg logit contributions | |
Raw | -0.010 |
Are | -0.009 |
AAAA | -0.009 |
Fox | -0.009 |
We | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
oll | +0.035 |
aney | +0.035 |
ier | +0.035 |
ige | +0.033 |
contain | +0.033 |
Neg logit contributions | |
Raw | -0.018 |
AAAA | -0.017 |
We | -0.016 |
Are | -0.016 |
Fox | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Are | +0.001 |
AAAA | +0.001 |
Raw | +0.001 |
Fox | +0.001 |
We | +0.001 |
Neg logit contributions | |
ier | -0.002 |
oll | -0.002 |
aney | -0.001 |
contain | -0.001 |
ver | -0.001 |
Token | always |
Token ID | 1464 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Are | +0.008 |
AAAA | +0.008 |
Raw | +0.008 |
Fox | +0.008 |
We | +0.007 |
Neg logit contributions | |
ier | -0.011 |
oll | -0.011 |
aney | -0.011 |
contain | -0.010 |
ver | -0.010 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Are | +0.017 |
AAAA | +0.017 |
Raw | +0.017 |
Fox | +0.016 |
We | +0.016 |
Neg logit contributions | |
oll | -0.021 |
ier | -0.020 |
aney | -0.019 |
contain | -0.018 |
ax | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
oll | +0.111 |
aney | +0.110 |
ier | +0.107 |
ige | +0.101 |
ver | +0.099 |
Neg logit contributions | |
Are | -0.066 |
things | -0.061 |
Fox | -0.060 |
We | -0.060 |
AAAA | -0.059 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Are | +0.010 |
AAAA | +0.010 |
Raw | +0.010 |
We | +0.009 |
Fox | +0.009 |
Neg logit contributions | |
oll | -0.015 |
ier | -0.015 |
aney | -0.015 |
contain | -0.014 |
ige | -0.014 |
Token | afterward |
Token ID | 20875 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.020 |
aney | +0.020 |
contain | +0.019 |
ver | +0.018 |
Neg logit contributions | |
AAAA | -0.018 |
Are | -0.018 |
Raw | -0.018 |
Fox | -0.017 |
We | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Fox | +0.234 |
We | +0.227 |
things | +0.226 |
Are | +0.220 |
Water | +0.200 |
Neg logit contributions | |
oll | -0.456 |
aney | -0.455 |
ier | -0.433 |
contain | -0.429 |
ige | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
oll | +0.015 |
aney | +0.014 |
ier | +0.014 |
contain | +0.013 |
ax | +0.013 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.006 |
Are | -0.006 |
Fox | -0.005 |
Ar | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
AAAA | +0.010 |
Raw | +0.009 |
Are | +0.009 |
Fox | +0.008 |
We | +0.008 |
Neg logit contributions | |
oll | -0.028 |
ier | -0.028 |
aney | -0.027 |
contain | -0.026 |
ver | -0.026 |
Token | One |
Token ID | 3198 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
AAAA | +0.016 |
Raw | +0.016 |
Are | +0.015 |
Fox | +0.015 |
Look | +0.014 |
Neg logit contributions | |
ier | -0.019 |
oll | -0.019 |
aney | -0.018 |
contain | -0.017 |
ax | -0.016 |
Token | night |
Token ID | 1755 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Are | +0.021 |
things | +0.020 |
AAAA | +0.020 |
Fox | +0.020 |
We | +0.020 |
Neg logit contributions | |
ier | -0.050 |
oll | -0.048 |
aney | -0.046 |
ige | -0.045 |
aces | -0.045 |
Token | canned |
Token ID | 32530 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
AAAA | +0.004 |
Raw | +0.004 |
Are | +0.003 |
Fox | +0.003 |
Come | +0.003 |
Neg logit contributions | |
oll | -0.005 |
ier | -0.005 |
contain | -0.004 |
aney | -0.004 |
ax | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
Are | +0.025 |
AAAA | +0.025 |
Raw | +0.024 |
Fox | +0.024 |
We | +0.024 |
Neg logit contributions | |
oll | -0.038 |
ier | -0.036 |
aney | -0.036 |
contain | -0.034 |
ver | -0.034 |
Token | jar |
Token ID | 17379 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
AAAA | +0.003 |
Raw | +0.002 |
Are | +0.002 |
Fox | +0.002 |
Come | +0.002 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
contain | -0.003 |
ax | -0.003 |
Token | red |
Token ID | 445 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
oll | +0.087 |
aney | +0.083 |
ige | +0.081 |
ax | +0.079 |
contain | +0.077 |
Neg logit contributions | |
things | -0.053 |
We | -0.050 |
Fox | -0.049 |
sounds | -0.047 |
noise | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
Are | +0.013 |
AAAA | +0.013 |
Fox | +0.013 |
Raw | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.019 |
aney | -0.019 |
contain | -0.018 |
ax | -0.018 |
Token | bottled |
Token ID | 34123 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
AAAA | +0.003 |
Raw | +0.003 |
Are | +0.003 |
Fox | +0.003 |
We | +0.003 |
Neg logit contributions | |
oll | -0.004 |
ier | -0.004 |
aney | -0.004 |
contain | -0.004 |
ax | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
AAAA | +0.258 |
Are | +0.254 |
Raw | +0.250 |
Fox | +0.245 |
We | +0.238 |
Neg logit contributions | |
oll | -0.428 |
ier | -0.421 |
aney | -0.402 |
contain | -0.390 |
ver | -0.375 |
Token | vacuum |
Token ID | 17076 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
AAAA | +0.003 |
Raw | +0.003 |
Are | +0.003 |
Fox | +0.003 |
We | +0.003 |
Neg logit contributions | |
oll | -0.005 |
ier | -0.004 |
aney | -0.004 |
contain | -0.004 |
ax | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
oll | +0.113 |
aney | +0.108 |
ier | +0.104 |
contain | +0.103 |
ige | +0.099 |
Neg logit contributions | |
Are | -0.072 |
AAAA | -0.071 |
Fox | -0.069 |
We | -0.069 |
Raw | -0.068 |
Token | se |
Token ID | 325 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
AAAA | +0.113 |
Raw | +0.112 |
Are | +0.111 |
Fox | +0.108 |
We | +0.106 |
Neg logit contributions | |
oll | -0.137 |
ier | -0.133 |
aney | -0.128 |
contain | -0.124 |
ige | -0.116 |
Token | aled |
Token ID | 3021 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
AAAA | +0.080 |
Are | +0.080 |
Fox | +0.080 |
We | +0.078 |
Raw | +0.077 |
Neg logit contributions | |
oll | -0.115 |
aney | -0.106 |
ier | -0.105 |
contain | -0.103 |
ax | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
oll | +0.014 |
ier | +0.014 |
contain | +0.014 |
aney | +0.014 |
salon | +0.013 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Are | -0.011 |
Come | -0.010 |
Peter | -0.010 |
Token | store |
Token ID | 3650 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
AAAA | +0.020 |
Are | +0.019 |
Raw | +0.019 |
Fox | +0.018 |
We | +0.018 |
Neg logit contributions | |
oll | -0.031 |
ier | -0.030 |
aney | -0.029 |
contain | -0.028 |
salon | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
oll | +0.149 |
ier | +0.138 |
aney | +0.138 |
contain | +0.130 |
ige | +0.128 |
Neg logit contributions | |
We | -0.069 |
Are | -0.067 |
things | -0.066 |
Fox | -0.066 |
cave | -0.064 |
Token | buy |
Token ID | 2822 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
AAAA | +0.002 |
Raw | +0.002 |
Are | +0.002 |
Fox | +0.002 |
We | +0.002 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.002 |
contain | -0.002 |
ver | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
oll | +0.181 |
ier | +0.179 |
aney | +0.172 |
contain | +0.167 |
ver | +0.162 |
Neg logit contributions | |
AAAA | -0.100 |
Are | -0.098 |
Raw | -0.097 |
Fox | -0.094 |
We | -0.091 |
Token | bottled |
Token ID | 34123 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
oll | +0.100 |
ier | +0.099 |
aney | +0.098 |
ver | +0.094 |
contain | +0.092 |
Neg logit contributions | |
things | -0.045 |
Are | -0.044 |
Raw | -0.043 |
AAAA | -0.043 |
Water | -0.042 |
Token | water |
Token ID | 1660 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
AAAA | +0.269 |
Raw | +0.261 |
Are | +0.258 |
Fox | +0.244 |
We | +0.236 |
Neg logit contributions | |
oll | -0.423 |
ier | -0.418 |
aney | -0.398 |
contain | -0.383 |
ax | -0.369 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Fox | +0.013 |
We | +0.013 |
things | +0.013 |
Come | +0.012 |
Are | +0.012 |
Neg logit contributions | |
oll | -0.022 |
aney | -0.022 |
ier | -0.021 |
contain | -0.021 |
ver | -0.020 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
oll | +0.010 |
aney | +0.010 |
ier | +0.009 |
ver | +0.009 |
ill | +0.009 |
Neg logit contributions | |
AAAA | -0.007 |
Raw | -0.007 |
cave | -0.006 |
Ar | -0.006 |
Fox | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ier | +0.013 |
oll | +0.012 |
aney | +0.012 |
contain | +0.011 |
ax | +0.011 |
Neg logit contributions | |
AAAA | -0.007 |
Are | -0.007 |
Raw | -0.007 |
Fox | -0.007 |
We | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Are | +0.008 |
AAAA | +0.007 |
Fox | +0.007 |
We | +0.007 |
noise | +0.007 |
Neg logit contributions | |
ier | -0.013 |
oll | -0.013 |
aney | -0.012 |
contain | -0.012 |
ax | -0.012 |
Token | ," |
Token ID | 553 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.011 |
Look | +0.010 |
Peter | +0.010 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.009 |
aney | -0.008 |
ver | -0.008 |
contain | -0.008 |
Token | Be |
Token ID | 3856 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.014 |
Are | +0.013 |
Fox | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.019 |
aney | -0.018 |
contain | -0.018 |
ver | -0.017 |
Token | good |
Token ID | 922 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
oll | +0.143 |
ier | +0.141 |
aney | +0.133 |
contain | +0.128 |
ver | +0.123 |
Neg logit contributions | |
AAAA | -0.124 |
Raw | -0.121 |
Are | -0.121 |
Fox | -0.116 |
We | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
Are | +0.035 |
Come | +0.034 |
AAAA | +0.033 |
Fox | +0.033 |
We | +0.033 |
Neg logit contributions | |
aney | -0.045 |
oll | -0.044 |
ier | -0.042 |
contain | -0.041 |
ige | -0.041 |
Token | Holly |
Token ID | 7764 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
oll | +0.008 |
ier | +0.008 |
aney | +0.007 |
contain | +0.007 |
ver | +0.007 |
Neg logit contributions | |
AAAA | -0.005 |
Are | -0.005 |
Raw | -0.005 |
Fox | -0.005 |
We | -0.005 |
Token | ,. |
Token ID | 38508 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
oll | +0.057 |
ier | +0.055 |
aney | +0.053 |
contain | +0.050 |
ige | +0.049 |
Neg logit contributions | |
Fox | -0.034 |
Are | -0.034 |
AAAA | -0.033 |
We | -0.031 |
Raw | -0.031 |
Token | I |
Token ID | 314 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
AAAA | +0.320 |
Raw | +0.302 |
Ar | +0.295 |
Look | +0.293 |
Are | +0.293 |
Neg logit contributions | |
oll | -0.354 |
ier | -0.321 |
aney | -0.315 |
contain | -0.299 |
ax | -0.294 |
Token | 'll |
Token ID | 1183 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
oll | +0.014 |
ier | +0.014 |
aney | +0.013 |
ige | +0.013 |
contain | +0.013 |
Neg logit contributions | |
Raw | -0.008 |
Are | -0.007 |
AAAA | -0.007 |
Ar | -0.007 |
Fox | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
AAAA | +0.072 |
Are | +0.072 |
Raw | +0.071 |
Fox | +0.071 |
We | +0.068 |
Neg logit contributions | |
oll | -0.120 |
ier | -0.118 |
aney | -0.117 |
ige | -0.106 |
ax | -0.105 |
Token | back |
Token ID | 736 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
oll | +0.037 |
ier | +0.036 |
aney | +0.034 |
contain | +0.033 |
ax | +0.032 |
Neg logit contributions | |
AAAA | -0.031 |
Raw | -0.030 |
Are | -0.030 |
Fox | -0.029 |
We | -0.028 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.009 |
Are | +0.009 |
Fox | +0.008 |
We | +0.008 |
Neg logit contributions | |
oll | -0.011 |
ier | -0.011 |
aney | -0.010 |
contain | -0.010 |
ver | -0.009 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
AAAA | +0.008 |
Are | +0.008 |
Raw | +0.008 |
Fox | +0.007 |
We | +0.007 |
Neg logit contributions | |
oll | -0.012 |
ier | -0.012 |
aney | -0.012 |
contain | -0.011 |
ver | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
oll | +0.035 |
ier | +0.034 |
aney | +0.034 |
contain | +0.032 |
ige | +0.031 |
Neg logit contributions | |
Fox | -0.025 |
Are | -0.025 |
We | -0.024 |
AAAA | -0.024 |
Raw | -0.023 |
Token | |
Token ID | 220 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.020 |
aney | +0.020 |
contain | +0.019 |
ax | +0.019 |
Neg logit contributions | |
AAAA | -0.008 |
Raw | -0.007 |
Are | -0.007 |
Fox | -0.007 |
We | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
oll | +0.057 |
ier | +0.056 |
aney | +0.055 |
ver | +0.052 |
contain | +0.052 |
Neg logit contributions | |
AAAA | -0.020 |
Raw | -0.019 |
Are | -0.018 |
Fox | -0.017 |
We | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.004 |
We | +0.004 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.013 |
contain | -0.012 |
ver | -0.012 |
Token | * |
Token ID | 9 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.006 |
Are | +0.006 |
Look | +0.005 |
We | +0.005 |
Neg logit contributions | |
ier | -0.011 |
oll | -0.011 |
aney | -0.010 |
contain | -0.010 |
ver | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
AAAA | +0.221 |
Are | +0.213 |
Raw | +0.211 |
Fox | +0.197 |
We | +0.197 |
Neg logit contributions | |
oll | -0.421 |
ier | -0.417 |
aney | -0.396 |
contain | -0.388 |
ax | -0.371 |
Token | End |
Token ID | 5268 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
oll | +0.055 |
ier | +0.053 |
aney | +0.050 |
contain | +0.048 |
ax | +0.047 |
Neg logit contributions | |
AAAA | -0.067 |
Are | -0.065 |
Raw | -0.064 |
Fox | -0.062 |
We | -0.062 |
Token | * |
Token ID | 9 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
oll | +0.032 |
ier | +0.030 |
aney | +0.029 |
contain | +0.027 |
he | +0.027 |
Neg logit contributions | |
AAAA | -0.039 |
Raw | -0.039 |
Are | -0.038 |
Fox | -0.037 |
Look | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
AAAA | +0.282 |
Raw | +0.275 |
Are | +0.274 |
Fox | +0.262 |
We | +0.256 |
Neg logit contributions | |
oll | -0.355 |
ier | -0.351 |
aney | -0.333 |
contain | -0.320 |
ver | -0.306 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
oll | +0.025 |
he | +0.025 |
ier | +0.024 |
aney | +0.024 |
ill | +0.023 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Sorry | -0.010 |
Are | -0.010 |
Fox | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
oll | +0.057 |
ier | +0.056 |
aney | +0.055 |
ver | +0.052 |
contain | +0.052 |
Neg logit contributions | |
AAAA | -0.020 |
Raw | -0.019 |
Are | -0.018 |
Fox | -0.017 |
We | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.004 |
We | +0.004 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.013 |
contain | -0.012 |
ver | -0.012 |
Token | * |
Token ID | 9 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.006 |
Are | +0.006 |
Look | +0.005 |
We | +0.005 |
Neg logit contributions | |
ier | -0.011 |
oll | -0.011 |
aney | -0.010 |
contain | -0.010 |
ver | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
AAAA | +0.221 |
Are | +0.213 |
Raw | +0.211 |
Fox | +0.197 |
We | +0.197 |
Neg logit contributions | |
oll | -0.421 |
ier | -0.417 |
aney | -0.396 |
contain | -0.388 |
ax | -0.371 |
Token | End |
Token ID | 5268 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
oll | +0.055 |
ier | +0.053 |
aney | +0.050 |
contain | +0.048 |
ax | +0.047 |
Neg logit contributions | |
AAAA | -0.067 |
Are | -0.065 |
Raw | -0.064 |
Fox | -0.062 |
We | -0.062 |
Token | * |
Token ID | 9 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
oll | +0.032 |
ier | +0.030 |
aney | +0.029 |
contain | +0.027 |
he | +0.027 |
Neg logit contributions | |
AAAA | -0.039 |
Raw | -0.039 |
Are | -0.038 |
Fox | -0.037 |
Look | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
AAAA | +0.282 |
Raw | +0.275 |
Are | +0.274 |
Fox | +0.262 |
We | +0.256 |
Neg logit contributions | |
oll | -0.355 |
ier | -0.351 |
aney | -0.333 |
contain | -0.320 |
ver | -0.306 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
oll | +0.025 |
he | +0.025 |
ier | +0.024 |
aney | +0.024 |
ill | +0.023 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Sorry | -0.010 |
Are | -0.010 |
Fox | -0.010 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
oll | +0.063 |
ier | +0.062 |
ige | +0.059 |
pper | +0.059 |
contain | +0.058 |
Neg logit contributions | |
things | -0.031 |
We | -0.031 |
Are | -0.030 |
cave | -0.029 |
| -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
AAAA | +0.062 |
Raw | +0.060 |
Are | +0.059 |
Fox | +0.057 |
We | +0.055 |
Neg logit contributions | |
oll | -0.089 |
ier | -0.087 |
aney | -0.084 |
contain | -0.081 |
ver | -0.078 |
Token | time |
Token ID | 640 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
AAAA | +0.002 |
Raw | +0.002 |
Are | +0.002 |
We | +0.002 |
Ar | +0.002 |
Neg logit contributions | |
ier | -0.003 |
oll | -0.003 |
contain | -0.003 |
aney | -0.003 |
aces | -0.003 |
Token | work |
Token ID | 670 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
AAAA | +0.001 |
Are | +0.001 |
Raw | +0.001 |
Fox | +0.001 |
We | +0.001 |
Neg logit contributions | |
oll | -0.001 |
ier | -0.001 |
aney | -0.001 |
contain | -0.001 |
ax | -0.001 |
Token | hard |
Token ID | 1327 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
AAAA | +0.035 |
Are | +0.035 |
Raw | +0.034 |
We | +0.034 |
Fox | +0.033 |
Neg logit contributions | |
oll | -0.057 |
aney | -0.055 |
ier | -0.052 |
contain | -0.052 |
ige | -0.050 |
Token | ." |
Token ID | 526 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Are | +0.017 |
AAAA | +0.017 |
Raw | +0.017 |
Fox | +0.017 |
We | +0.017 |
Neg logit contributions | |
oll | -0.027 |
aney | -0.026 |
ier | -0.025 |
contain | -0.025 |
ige | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
oll | +0.022 |
aney | +0.021 |
ax | +0.020 |
ier | +0.020 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.014 |
Raw | -0.014 |
Ar | -0.012 |
cave | -0.012 |
Are | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.006 |
Are | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.012 |
aney | -0.011 |
ier | -0.011 |
contain | -0.011 |
he | -0.010 |
Token | * |
Token ID | 9 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
AAAA | +0.007 |
Are | +0.007 |
Raw | +0.007 |
Fox | +0.007 |
We | +0.007 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.009 |
aney | -0.009 |
contain | -0.009 |
ax | -0.008 |
Token | wh |
Token ID | 1929 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
AAAA | +0.190 |
Are | +0.183 |
Raw | +0.180 |
Fox | +0.173 |
We | +0.167 |
Neg logit contributions | |
oll | -0.439 |
ier | -0.436 |
aney | -0.419 |
contain | -0.408 |
ax | -0.390 |
Token | istle |
Token ID | 12535 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
oll | +0.004 |
contain | +0.004 |
ier | +0.004 |
ilies | +0.004 |
salon | +0.004 |
Neg logit contributions | |
AAAA | -0.005 |
Peter | -0.005 |
oc | -0.005 |
Andy | -0.005 |
Come | -0.005 |
Token | sound |
Token ID | 2128 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
oll | +0.200 |
ier | +0.191 |
aney | +0.188 |
ige | +0.178 |
contain | +0.176 |
Neg logit contributions | |
Are | -0.101 |
AAAA | -0.101 |
We | -0.096 |
Raw | -0.095 |
Fox | -0.093 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Are | +0.052 |
AAAA | +0.048 |
We | +0.047 |
Fox | +0.046 |
noise | +0.046 |
Neg logit contributions | |
oll | -0.073 |
aney | -0.069 |
salon | -0.064 |
ige | -0.064 |
ax | -0.063 |
Token | One |
Token ID | 3198 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
oll | +0.029 |
ier | +0.028 |
he | +0.028 |
aney | +0.027 |
ill | +0.027 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Sorry | -0.012 |
Are | -0.011 |
Fox | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -9.64e-05 |
Pos logit contributions | |
oll | +0.094 |
ier | +0.093 |
aney | +0.090 |
contain | +0.085 |
ver | +0.084 |
Neg logit contributions | |
AAAA | -0.051 |
Are | -0.050 |
Raw | -0.049 |
Fox | -0.048 |
things | -0.045 |
Token | sweater |
Token ID | 35685 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Are | +0.000 |
AAAA | +0.000 |
things | +0.000 |
Fox | +0.000 |
Raw | +0.000 |
Neg logit contributions | |
ier | -0.000 |
oll | -0.000 |
aney | -0.000 |
contain | -0.000 |
ax | -0.000 |
Token | * |
Token ID | 1635 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
oll | +0.081 |
aney | +0.078 |
ier | +0.077 |
ax | +0.073 |
contain | +0.073 |
Neg logit contributions | |
AAAA | -0.039 |
Are | -0.039 |
Raw | -0.038 |
Fox | -0.037 |
things | -0.036 |
Token | po |
Token ID | 7501 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.005 |
Come | +0.005 |
Neg logit contributions | |
oll | -0.006 |
ier | -0.006 |
aney | -0.006 |
contain | -0.005 |
ige | -0.005 |
Token | pped |
Token ID | 1496 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
AAAA | +0.105 |
Raw | +0.103 |
Are | +0.103 |
Look | +0.100 |
Come | +0.099 |
Neg logit contributions | |
oll | -0.081 |
aney | -0.076 |
ier | -0.076 |
contain | -0.076 |
ver | -0.069 |
Token | * |
Token ID | 9 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
oll | +0.131 |
ier | +0.127 |
aney | +0.123 |
contain | +0.119 |
ver | +0.115 |
Neg logit contributions | |
AAAA | -0.081 |
Are | -0.079 |
Raw | -0.079 |
Fox | -0.076 |
We | -0.074 |
Token | ! |
Token ID | 0 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
AAAA | +0.233 |
Are | +0.230 |
Raw | +0.225 |
Fox | +0.217 |
We | +0.215 |
Neg logit contributions | |
oll | -0.386 |
ier | -0.379 |
aney | -0.364 |
contain | -0.353 |
ver | -0.339 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.027 |
Ar | +0.027 |
cave | +0.026 |
Peter | +0.025 |
Neg logit contributions | |
oll | -0.041 |
aney | -0.039 |
ier | -0.036 |
ver | -0.035 |
ax | -0.035 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
ige | +0.001 |
contain | +0.001 |
Neg logit contributions | |
Are | -0.000 |
AAAA | -0.000 |
Raw | -0.000 |
We | -0.000 |
Fox | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
AAAA | +0.007 |
Raw | +0.007 |
Are | +0.006 |
Ar | +0.006 |
Fox | +0.006 |
Neg logit contributions | |
ier | -0.008 |
oll | -0.008 |
aney | -0.007 |
contain | -0.007 |
ax | -0.007 |
Token | looked |
Token ID | 3114 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Are | +0.001 |
AAAA | +0.001 |
Raw | +0.001 |
Fox | +0.001 |
We | +0.001 |
Neg logit contributions | |
oll | -0.001 |
ier | -0.001 |
aney | -0.001 |
contain | -0.001 |
ige | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
oll | +0.008 |
ier | +0.008 |
contain | +0.007 |
aney | +0.007 |
ver | +0.007 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
Come | -0.005 |
We | -0.005 |
Token | heard |
Token ID | 2982 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.016 |
aney | +0.016 |
contain | +0.016 |
ver | +0.015 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.010 |
Are | -0.010 |
Fox | -0.010 |
Peter | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
AAAA | +0.021 |
Raw | +0.020 |
Are | +0.020 |
Fox | +0.019 |
We | +0.019 |
Neg logit contributions | |
oll | -0.036 |
ier | -0.036 |
aney | -0.034 |
contain | -0.033 |
ver | -0.032 |
Token | whistle |
Token ID | 16121 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
AAAA | +0.005 |
Come | +0.005 |
keeping | +0.005 |
Raw | +0.005 |
situations | +0.005 |
Neg logit contributions | |
contain | -0.008 |
ier | -0.008 |
aney | -0.008 |
oll | -0.008 |
isy | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
oll | +0.006 |
aney | +0.006 |
ier | +0.005 |
ige | +0.005 |
ax | +0.005 |
Neg logit contributions | |
Are | -0.003 |
AAAA | -0.003 |
Raw | -0.003 |
Fox | -0.003 |
We | -0.003 |
Token | * |
Token ID | 9 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.026 |
situations | +0.025 |
things | +0.025 |
places | +0.025 |
Neg logit contributions | |
oll | -0.041 |
aney | -0.038 |
ver | -0.037 |
contain | -0.036 |
ax | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
Raw | +0.203 |
AAAA | +0.202 |
Are | +0.190 |
Fox | +0.186 |
Sorry | +0.180 |
Neg logit contributions | |
oll | -0.397 |
ier | -0.393 |
aney | -0.373 |
contain | -0.372 |
he | -0.360 |
Token | was |
Token ID | 373 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
oll | +0.005 |
ier | +0.005 |
aney | +0.005 |
contain | +0.005 |
ver | +0.005 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.004 |
Fox | -0.004 |
Come | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Are | +0.009 |
AAAA | +0.009 |
Fox | +0.009 |
Raw | +0.009 |
We | +0.008 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.012 |
aney | -0.012 |
contain | -0.011 |
ige | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
AAAA | +0.023 |
Are | +0.023 |
Raw | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
oll | -0.027 |
ier | -0.027 |
aney | -0.025 |
contain | -0.024 |
ver | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
ier | +0.027 |
oll | +0.026 |
contain | +0.023 |
aney | +0.023 |
ax | +0.023 |
Neg logit contributions | |
AAAA | -0.033 |
Raw | -0.033 |
Are | -0.031 |
Look | -0.030 |
Ar | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Fox | +0.006 |
Raw | +0.006 |
Are | +0.006 |
Fire | +0.006 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.013 |
contain | -0.012 |
ver | -0.012 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
AAAA | +0.008 |
Come | +0.008 |
Raw | +0.008 |
Are | +0.007 |
situations | +0.007 |
Neg logit contributions | |
ier | -0.009 |
oll | -0.009 |
aney | -0.009 |
contain | -0.009 |
ige | -0.008 |
Token | * |
Token ID | 1635 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
AAAA | +0.012 |
Raw | +0.012 |
Ar | +0.011 |
Peter | +0.011 |
Are | +0.011 |
Neg logit contributions | |
ier | -0.026 |
oll | -0.025 |
aney | -0.025 |
contain | -0.024 |
he | -0.023 |
Token | be |
Token ID | 1350 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
AAAA | +0.007 |
Raw | +0.007 |
Are | +0.007 |
Fox | +0.007 |
We | +0.006 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.009 |
aney | -0.009 |
contain | -0.008 |
ver | -0.008 |
Token | ep |
Token ID | 538 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
AAAA | +0.055 |
Raw | +0.053 |
Are | +0.053 |
Fox | +0.049 |
We | +0.049 |
Neg logit contributions | |
oll | -0.109 |
ier | -0.107 |
aney | -0.103 |
contain | -0.100 |
ver | -0.097 |
Token | * |
Token ID | 9 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
AAAA | +0.008 |
Are | +0.008 |
We | +0.007 |
Raw | +0.007 |
Fox | +0.007 |
Neg logit contributions | |
oll | -0.012 |
aney | -0.011 |
ier | -0.011 |
contain | -0.011 |
ige | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
AAAA | +0.237 |
Are | +0.231 |
Raw | +0.229 |
Fox | +0.222 |
We | +0.218 |
Neg logit contributions | |
oll | -0.373 |
ier | -0.363 |
aney | -0.350 |
contain | -0.337 |
ver | -0.325 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
oll | +0.070 |
ier | +0.068 |
aney | +0.066 |
contain | +0.063 |
ver | +0.062 |
Neg logit contributions | |
AAAA | -0.037 |
Raw | -0.036 |
Are | -0.035 |
Fox | -0.035 |
We | -0.033 |
Token | oven |
Token ID | 14361 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
AAAA | +0.019 |
Raw | +0.018 |
Are | +0.018 |
Fox | +0.018 |
We | +0.017 |
Neg logit contributions | |
oll | -0.022 |
ier | -0.021 |
aney | -0.020 |
contain | -0.020 |
ver | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
oll | +0.112 |
ier | +0.106 |
aney | +0.105 |
contain | +0.099 |
ver | +0.098 |
Neg logit contributions | |
Are | -0.073 |
AAAA | -0.072 |
We | -0.072 |
Fox | -0.071 |
Raw | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
oll | +0.013 |
aney | +0.013 |
ver | +0.013 |
contain | +0.013 |
ax | +0.012 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
Ar | -0.008 |
situations | -0.008 |
things | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
Fox | +0.101 |
Are | +0.093 |
We | +0.089 |
Come | +0.089 |
things | +0.084 |
Neg logit contributions | |
oll | -0.155 |
ier | -0.155 |
aney | -0.148 |
contain | -0.147 |
obb | -0.140 |
Token | some |
Token ID | 617 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Are | -0.000 |
Raw | -0.000 |
Fox | -0.000 |
We | -0.000 |
Token | funny |
Token ID | 8258 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ier | +0.090 |
oll | +0.089 |
aney | +0.088 |
ver | +0.085 |
contain | +0.082 |
Neg logit contributions | |
things | -0.058 |
Are | -0.056 |
Raw | -0.055 |
Fox | -0.054 |
AAAA | -0.054 |
Token | little |
Token ID | 1310 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
AAAA | +0.037 |
Raw | +0.036 |
Are | +0.035 |
Fox | +0.034 |
We | +0.032 |
Neg logit contributions | |
oll | -0.056 |
ier | -0.055 |
aney | -0.053 |
contain | -0.051 |
ax | -0.049 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.014 |
Are | +0.014 |
Fox | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.020 |
aney | -0.019 |
contain | -0.018 |
ax | -0.017 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Fox | +0.070 |
We | +0.067 |
Are | +0.064 |
Come | +0.063 |
things | +0.061 |
Neg logit contributions | |
oll | -0.121 |
ier | -0.117 |
contain | -0.114 |
aney | -0.114 |
ige | -0.108 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
AAAA | +0.303 |
Are | +0.299 |
Raw | +0.297 |
We | +0.296 |
Fox | +0.295 |
Neg logit contributions | |
ier | -0.272 |
oll | -0.271 |
contain | -0.260 |
aney | -0.255 |
ax | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
oll | +0.114 |
aney | +0.109 |
ier | +0.107 |
ige | +0.107 |
obb | +0.104 |
Neg logit contributions | |
Fox | -0.051 |
We | -0.047 |
things | -0.045 |
Are | -0.044 |
cave | -0.042 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
oll | +0.016 |
aney | +0.016 |
ier | +0.015 |
ax | +0.014 |
ver | +0.014 |
Neg logit contributions | |
AAAA | -0.009 |
Raw | -0.009 |
Are | -0.008 |
cave | -0.008 |
Ar | -0.008 |
Token | m |
Token ID | 285 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ier | +0.077 |
oll | +0.077 |
aney | +0.072 |
contain | +0.070 |
ver | +0.067 |
Neg logit contributions | |
AAAA | -0.051 |
Are | -0.050 |
Raw | -0.049 |
Fox | -0.048 |
We | -0.046 |
Token | ama |
Token ID | 1689 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ier | +0.016 |
contain | +0.015 |
oll | +0.015 |
aney | +0.014 |
ver | +0.013 |
Neg logit contributions | |
Fox | -0.009 |
Are | -0.009 |
Raw | -0.009 |
We | -0.009 |
oc | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
oll | +0.028 |
ier | +0.028 |
aney | +0.026 |
contain | +0.025 |
ax | +0.024 |
Neg logit contributions | |
AAAA | -0.023 |
Are | -0.022 |
Raw | -0.022 |
Fox | -0.021 |
We | -0.021 |
Token | handle |
Token ID | 5412 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ier | +0.017 |
oll | +0.017 |
contain | +0.016 |
aney | +0.016 |
ver | +0.015 |
Neg logit contributions | |
AAAA | -0.014 |
Raw | -0.014 |
Are | -0.013 |
Come | -0.013 |
We | -0.013 |
Token | problems |
Token ID | 2761 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
AAAA | +0.024 |
Raw | +0.024 |
Are | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
oll | -0.043 |
ier | -0.043 |
aney | -0.041 |
contain | -0.039 |
ver | -0.038 |
Token | before |
Token ID | 878 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
We | +0.022 |
AAAA | +0.021 |
Are | +0.021 |
Fox | +0.021 |
things | +0.021 |
Neg logit contributions | |
oll | -0.033 |
aney | -0.032 |
ier | -0.031 |
ige | -0.029 |
contain | -0.029 |
Token | they |
Token ID | 484 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
ier | +0.101 |
oll | +0.093 |
contain | +0.091 |
ver | +0.087 |
aney | +0.085 |
Neg logit contributions | |
Raw | -0.070 |
AAAA | -0.069 |
Are | -0.066 |
Look | -0.064 |
Ar | -0.063 |
Token | escalate |
Token ID | 38302 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
AAAA | +0.004 |
Are | +0.004 |
Raw | +0.004 |
Fox | +0.004 |
We | +0.004 |
Neg logit contributions | |
oll | -0.006 |
aney | -0.006 |
ier | -0.006 |
ax | -0.006 |
ige | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
AAAA | +0.265 |
Are | +0.260 |
Raw | +0.258 |
Fox | +0.253 |
We | +0.251 |
Neg logit contributions | |
oll | -0.332 |
ier | -0.320 |
aney | -0.310 |
contain | -0.297 |
ax | -0.285 |
Token | Just |
Token ID | 2329 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
oll | +0.012 |
aney | +0.011 |
ver | +0.011 |
ier | +0.011 |
ill | +0.010 |
Neg logit contributions | |
AAAA | -0.007 |
Raw | -0.006 |
Are | -0.006 |
pans | -0.005 |
cave | -0.005 |
Token | like |
Token ID | 588 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Are | +0.043 |
Fox | +0.042 |
AAAA | +0.040 |
We | +0.040 |
things | +0.039 |
Neg logit contributions | |
oll | -0.046 |
aney | -0.046 |
ier | -0.045 |
ige | -0.040 |
ax | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
ier | +0.019 |
oll | +0.019 |
aney | +0.018 |
contain | +0.018 |
ver | +0.017 |
Neg logit contributions | |
AAAA | -0.016 |
Raw | -0.016 |
Are | -0.015 |
Look | -0.014 |
Come | -0.014 |
Token | this |
Token ID | 428 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
AAAA | +0.034 |
Are | +0.033 |
Fox | +0.033 |
Raw | +0.033 |
We | +0.032 |
Neg logit contributions | |
oll | -0.050 |
ier | -0.049 |
aney | -0.048 |
contain | -0.045 |
ax | -0.044 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ier | +0.005 |
oll | +0.005 |
aney | +0.005 |
contain | +0.005 |
ver | +0.005 |
Neg logit contributions | |
Are | -0.003 |
Raw | -0.003 |
AAAA | -0.003 |
Fox | -0.003 |
We | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
Are | +0.063 |
We | +0.063 |
AAAA | +0.061 |
Raw | +0.060 |
Fox | +0.060 |
Neg logit contributions | |
oll | -0.102 |
ier | -0.098 |
aney | -0.095 |
contain | -0.091 |
ax | -0.090 |
Token | admire |
Token ID | 21099 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
oll | +0.000 |
ier | +0.000 |
aney | +0.000 |
contain | +0.000 |
ver | +0.000 |
Neg logit contributions | |
AAAA | -0.000 |
Are | -0.000 |
Raw | -0.000 |
Fox | -0.000 |
We | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
AAAA | +0.014 |
Are | +0.014 |
Fox | +0.013 |
Raw | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.033 |
ier | -0.032 |
aney | -0.031 |
contain | -0.030 |
ver | -0.029 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
oll | +0.005 |
ier | +0.005 |
aney | +0.004 |
contain | +0.004 |
ver | +0.004 |
Neg logit contributions | |
AAAA | -0.003 |
Raw | -0.003 |
Are | -0.003 |
Fox | -0.003 |
We | -0.003 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Fox | +0.069 |
Are | +0.069 |
We | +0.068 |
AAAA | +0.066 |
Raw | +0.066 |
Neg logit contributions | |
oll | -0.118 |
ier | -0.113 |
aney | -0.112 |
contain | -0.107 |
ver | -0.104 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
AAAA | +0.297 |
Are | +0.292 |
We | +0.291 |
Raw | +0.290 |
Fox | +0.287 |
Neg logit contributions | |
oll | -0.285 |
ier | -0.274 |
contain | -0.265 |
aney | -0.264 |
ver | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
oll | +0.100 |
aney | +0.096 |
ier | +0.093 |
ige | +0.090 |
contain | +0.087 |
Neg logit contributions | |
Fox | -0.059 |
We | -0.058 |
Are | -0.058 |
things | -0.056 |
cave | -0.054 |
Token | They |
Token ID | 1119 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
AAAA | +0.007 |
Raw | +0.006 |
situations | +0.006 |
Fox | +0.005 |
cave | +0.005 |
Neg logit contributions | |
oll | -0.014 |
aney | -0.013 |
ax | -0.013 |
ier | -0.012 |
ill | -0.012 |
Token | also |
Token ID | 635 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Fox | +0.023 |
Are | +0.023 |
Raw | +0.023 |
AAAA | +0.021 |
sounds | +0.021 |
Neg logit contributions | |
oll | -0.044 |
ier | -0.043 |
aney | -0.039 |
aces | -0.036 |
ver | -0.035 |
Token | see |
Token ID | 766 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
oll | +0.081 |
ier | +0.079 |
aney | +0.073 |
ver | +0.070 |
ax | +0.068 |
Neg logit contributions | |
Are | -0.043 |
AAAA | -0.040 |
Raw | -0.039 |
We | -0.038 |
sounds | -0.038 |
Token | stretch |
Token ID | 7539 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
oll | +0.035 |
ier | +0.033 |
aney | +0.031 |
ver | +0.031 |
ax | +0.030 |
Neg logit contributions | |
Raw | -0.019 |
Fox | -0.019 |
Are | -0.019 |
AAAA | -0.018 |
We | -0.018 |
Token | out |
Token ID | 503 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
oll | +0.039 |
ier | +0.037 |
aney | +0.035 |
ige | +0.033 |
contain | +0.033 |
Neg logit contributions | |
Fox | -0.021 |
We | -0.020 |
Are | -0.020 |
AAAA | -0.020 |
Raw | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
oll | +0.089 |
ier | +0.082 |
aney | +0.079 |
ige | +0.079 |
ax | +0.078 |
Neg logit contributions | |
We | -0.058 |
Fox | -0.058 |
things | -0.057 |
Are | -0.057 |
AAAA | -0.056 |
Token | enormous |
Token ID | 9812 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.014 |
Are | +0.014 |
Fox | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.018 |
ier | -0.018 |
aney | -0.017 |
contain | -0.016 |
ver | -0.016 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
oll | +0.126 |
ier | +0.124 |
aney | +0.118 |
contain | +0.113 |
ver | +0.111 |
Neg logit contributions | |
AAAA | -0.084 |
Raw | -0.082 |
Are | -0.082 |
Fox | -0.079 |
We | -0.077 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Fox | +0.062 |
We | +0.060 |
Are | +0.060 |
AAAA | +0.057 |
Come | +0.056 |
Neg logit contributions | |
oll | -0.136 |
ier | -0.129 |
aney | -0.127 |
contain | -0.126 |
ax | -0.121 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
AAAA | +0.275 |
We | +0.271 |
Fox | +0.267 |
Raw | +0.265 |
Come | +0.261 |
Neg logit contributions | |
oll | -0.290 |
ier | -0.282 |
contain | -0.280 |
aney | -0.270 |
ax | -0.257 |
Token | would |
Token ID | 561 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
oll | +0.105 |
aney | +0.097 |
ier | +0.094 |
ige | +0.094 |
ax | +0.091 |
Neg logit contributions | |
Fox | -0.059 |
We | -0.058 |
Are | -0.056 |
things | -0.055 |
AAAA | -0.053 |
Token | show |
Token ID | 905 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
oll | +0.038 |
ier | +0.035 |
aney | +0.033 |
ver | +0.033 |
ax | +0.032 |
Neg logit contributions | |
Raw | -0.020 |
Fox | -0.019 |
Are | -0.019 |
AAAA | -0.018 |
We | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.010 |
aney | +0.010 |
contain | +0.009 |
ax | +0.009 |
Neg logit contributions | |
Are | -0.007 |
AAAA | -0.007 |
Raw | -0.006 |
Fox | -0.006 |
We | -0.006 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
AAAA | +0.023 |
Raw | +0.022 |
Are | +0.022 |
Fox | +0.021 |
We | +0.021 |
Neg logit contributions | |
oll | -0.036 |
ier | -0.035 |
aney | -0.033 |
contain | -0.032 |
ver | -0.031 |
Token | back |
Token ID | 736 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
ier | +0.025 |
oll | +0.024 |
aney | +0.023 |
contain | +0.022 |
ax | +0.022 |
Neg logit contributions | |
AAAA | -0.022 |
Raw | -0.022 |
Are | -0.021 |
We | -0.020 |
Sorry | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
AAAA | +0.003 |
Raw | +0.003 |
Are | +0.003 |
Fox | +0.003 |
We | +0.003 |
Neg logit contributions | |
oll | -0.004 |
ier | -0.004 |
aney | -0.004 |
contain | -0.004 |
ax | -0.004 |
Token | lots |
Token ID | 6041 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
Fox | +0.033 |
AAAA | +0.033 |
Raw | +0.032 |
Are | +0.032 |
Look | +0.030 |
Neg logit contributions | |
oll | -0.075 |
ier | -0.075 |
aney | -0.071 |
ver | -0.069 |
contain | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
things | +0.007 |
We | +0.006 |
packages | +0.006 |
noise | +0.006 |
Fox | +0.006 |
Neg logit contributions | |
oll | -0.006 |
ver | -0.006 |
pper | -0.005 |
aney | -0.005 |
ige | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
oll | +0.094 |
ier | +0.093 |
aney | +0.089 |
contain | +0.086 |
ver | +0.085 |
Neg logit contributions | |
AAAA | -0.056 |
Raw | -0.055 |
Are | -0.054 |
Fox | -0.053 |
We | -0.050 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Fox | +0.060 |
AAAA | +0.058 |
We | +0.058 |
Are | +0.057 |
things | +0.055 |
Neg logit contributions | |
oll | -0.136 |
ier | -0.128 |
contain | -0.128 |
aney | -0.128 |
ver | -0.122 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
AAAA | +0.299 |
Are | +0.290 |
We | +0.289 |
Fox | +0.288 |
Raw | +0.287 |
Neg logit contributions | |
oll | -0.272 |
ier | -0.265 |
contain | -0.260 |
aney | -0.256 |
ver | -0.237 |
Token | to |
Token ID | 284 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
oll | +0.105 |
aney | +0.099 |
ier | +0.096 |
contain | +0.093 |
ige | +0.092 |
Neg logit contributions | |
Fox | -0.054 |
We | -0.054 |
things | -0.051 |
Are | -0.050 |
AAAA | -0.049 |
Token | fill |
Token ID | 6070 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
oll | +0.017 |
ier | +0.016 |
aney | +0.016 |
ver | +0.015 |
aces | +0.014 |
Neg logit contributions | |
Are | -0.010 |
Fox | -0.010 |
AAAA | -0.009 |
Raw | -0.009 |
We | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
oll | +0.074 |
ier | +0.074 |
aney | +0.071 |
contain | +0.068 |
ax | +0.065 |
Neg logit contributions | |
AAAA | -0.048 |
Raw | -0.046 |
Are | -0.046 |
Fox | -0.043 |
We | -0.042 |
Token | prince |
Token ID | 19716 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
AAAA | +0.010 |
Raw | +0.010 |
Are | +0.010 |
Fox | +0.010 |
We | +0.009 |
Neg logit contributions | |
oll | -0.019 |
ier | -0.019 |
aney | -0.018 |
contain | -0.017 |
ver | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Are | +0.011 |
We | +0.011 |
AAAA | +0.011 |
Fox | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
ier | -0.024 |
oll | -0.024 |
salon | -0.022 |
aces | -0.022 |
aney | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ier | +0.016 |
oll | +0.016 |
aney | +0.015 |
contain | +0.014 |
ax | +0.014 |
Neg logit contributions | |
AAAA | -0.018 |
Raw | -0.018 |
Are | -0.017 |
Look | -0.016 |
Fox | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Fox | +0.026 |
things | +0.022 |
Farmer | +0.020 |
Are | +0.020 |
cave | +0.020 |
Neg logit contributions | |
ier | -0.093 |
oll | -0.091 |
aney | -0.089 |
ver | -0.087 |
salon | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
things | +0.012 |
Fox | +0.012 |
cave | +0.012 |
We | +0.011 |
Are | +0.011 |
Neg logit contributions | |
oll | -0.027 |
ier | -0.026 |
ver | -0.025 |
aney | -0.024 |
ige | -0.024 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
AAAA | +0.015 |
Raw | +0.014 |
Are | +0.014 |
Fox | +0.013 |
We | +0.013 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
aney | -0.023 |
contain | -0.022 |
ax | -0.021 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Fox | +0.060 |
Are | +0.059 |
AAAA | +0.059 |
We | +0.057 |
Raw | +0.055 |
Neg logit contributions | |
oll | -0.131 |
ier | -0.126 |
aney | -0.125 |
contain | -0.122 |
ver | -0.117 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
AAAA | +0.317 |
Are | +0.310 |
Raw | +0.309 |
Fox | +0.305 |
We | +0.302 |
Neg logit contributions | |
oll | -0.262 |
ier | -0.254 |
aney | -0.245 |
contain | -0.242 |
ver | -0.223 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
oll | +0.104 |
aney | +0.099 |
ier | +0.096 |
ige | +0.093 |
salon | +0.092 |
Neg logit contributions | |
Fox | -0.060 |
We | -0.057 |
Are | -0.057 |
things | -0.055 |
AAAA | -0.054 |
Token | he |
Token ID | 339 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ax | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Fox | -0.001 |
We | -0.001 |
Token | ordered |
Token ID | 6149 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
oll | +0.016 |
ier | +0.016 |
aney | +0.015 |
contain | +0.014 |
ver | +0.014 |
Neg logit contributions | |
AAAA | -0.010 |
Fox | -0.010 |
Raw | -0.010 |
Are | -0.010 |
We | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
oll | +0.039 |
ier | +0.038 |
aney | +0.037 |
ver | +0.035 |
contain | +0.035 |
Neg logit contributions | |
AAAA | -0.020 |
Fox | -0.020 |
Are | -0.019 |
Raw | -0.019 |
We | -0.018 |
Token | something |
Token ID | 1223 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.000 |
Are | -0.000 |
Raw | -0.000 |
Fox | -0.000 |
Look | -0.000 |
Token | moving |
Token ID | 3867 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
oll | +0.051 |
ier | +0.050 |
aney | +0.049 |
ver | +0.046 |
contain | +0.045 |
Neg logit contributions | |
Are | -0.034 |
AAAA | -0.033 |
Raw | -0.033 |
Fox | -0.032 |
We | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Are | +0.011 |
Raw | +0.011 |
Fox | +0.011 |
Come | +0.010 |
Neg logit contributions | |
oll | -0.018 |
ier | -0.017 |
aney | -0.017 |
ige | -0.015 |
contain | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
AAAA | +0.034 |
Are | +0.033 |
Raw | +0.033 |
We | +0.031 |
Fox | +0.031 |
Neg logit contributions | |
ier | -0.050 |
oll | -0.050 |
aney | -0.048 |
contain | -0.047 |
ax | -0.044 |
Token | wild |
Token ID | 4295 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
AAAA | +0.013 |
Raw | +0.012 |
Are | +0.012 |
Fox | +0.012 |
We | +0.011 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
aney | -0.023 |
contain | -0.022 |
ver | -0.021 |
Token | fl |
Token ID | 2704 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
ier | +0.033 |
oll | +0.032 |
aney | +0.031 |
contain | +0.030 |
ax | +0.029 |
Neg logit contributions | |
AAAA | -0.021 |
Raw | -0.020 |
Are | -0.020 |
Fox | -0.019 |
We | -0.019 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
AAAA | +0.297 |
Fox | +0.285 |
Raw | +0.285 |
Are | +0.280 |
We | +0.278 |
Neg logit contributions | |
oll | -0.275 |
ier | -0.273 |
aney | -0.265 |
contain | -0.264 |
ver | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
oll | +0.109 |
aney | +0.104 |
ier | +0.104 |
ige | +0.097 |
ver | +0.095 |
Neg logit contributions | |
Are | -0.063 |
Fox | -0.062 |
We | -0.062 |
AAAA | -0.061 |
cave | -0.059 |
Token | It |
Token ID | 632 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
oll | +0.018 |
aney | +0.017 |
ax | +0.016 |
ier | +0.016 |
contain | +0.016 |
Neg logit contributions | |
AAAA | -0.011 |
Raw | -0.011 |
Ar | -0.010 |
situations | -0.010 |
cave | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
oll | +0.023 |
ier | +0.023 |
aney | +0.022 |
contain | +0.021 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.011 |
Are | -0.011 |
We | -0.011 |
Come | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
AAAA | +0.010 |
Fox | +0.010 |
Raw | +0.010 |
Are | +0.010 |
Look | +0.009 |
Neg logit contributions | |
oll | -0.019 |
ier | -0.019 |
aney | -0.018 |
contain | -0.018 |
ver | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
AAAA | +0.018 |
Are | +0.018 |
Raw | +0.018 |
Fox | +0.017 |
We | +0.017 |
Neg logit contributions | |
oll | -0.037 |
ier | -0.036 |
aney | -0.035 |
contain | -0.034 |
ver | -0.033 |
Token | rest |
Token ID | 1334 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
AAAA | +0.007 |
Are | +0.007 |
Raw | +0.007 |
Fox | +0.007 |
We | +0.007 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.012 |
contain | -0.012 |
ver | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
oll | +0.051 |
ige | +0.045 |
aney | +0.044 |
ver | +0.044 |
contain | +0.043 |
Neg logit contributions | |
We | -0.048 |
things | -0.047 |
cave | -0.043 |
places | -0.042 |
Fox | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
oll | +0.096 |
ier | +0.096 |
aney | +0.091 |
contain | +0.088 |
ver | +0.085 |
Neg logit contributions | |
AAAA | -0.057 |
Raw | -0.055 |
Are | -0.055 |
Fox | -0.052 |
We | -0.050 |
Token | or |
Token ID | 393 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.009 |
Are | +0.009 |
Fox | +0.008 |
Come | +0.008 |
Neg logit contributions | |
oll | -0.015 |
ier | -0.015 |
aney | -0.014 |
contain | -0.014 |
ax | -0.013 |
Token | nam |
Token ID | 7402 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Are | +0.068 |
AAAA | +0.068 |
Raw | +0.066 |
Fox | +0.065 |
We | +0.064 |
Neg logit contributions | |
oll | -0.093 |
ier | -0.090 |
aney | -0.087 |
contain | -0.081 |
ax | -0.079 |
Token | ents |
Token ID | 658 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
oll | +0.107 |
ier | +0.097 |
contain | +0.073 |
aney | +0.071 |
ver | +0.059 |
Neg logit contributions | |
AAAA | -0.394 |
We | -0.393 |
Are | -0.392 |
Peter | -0.390 |
Raw | -0.390 |
Token | onto |
Token ID | 4291 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
oll | +0.375 |
aney | +0.334 |
ige | +0.333 |
ax | +0.314 |
icate | +0.313 |
Neg logit contributions | |
We | -0.137 |
things | -0.130 |
Fox | -0.128 |
cave | -0.118 |
Run | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
oll | +0.072 |
ier | +0.070 |
aney | +0.067 |
contain | +0.065 |
ax | +0.063 |
Neg logit contributions | |
AAAA | -0.038 |
Fox | -0.037 |
Are | -0.037 |
Raw | -0.037 |
We | -0.035 |
Token | tree |
Token ID | 5509 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Are | +0.011 |
Raw | +0.011 |
Fox | +0.011 |
We | +0.010 |
Neg logit contributions | |
oll | -0.018 |
ier | -0.018 |
aney | -0.017 |
contain | -0.017 |
ver | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
oll | +0.056 |
ier | +0.052 |
aney | +0.049 |
ax | +0.048 |
ige | +0.048 |
Neg logit contributions | |
We | -0.026 |
Fox | -0.026 |
cave | -0.024 |
Are | -0.024 |
things | -0.023 |
Token | sail |
Token ID | 14936 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
oll | +0.022 |
ier | +0.022 |
aney | +0.020 |
ige | +0.019 |
ver | +0.019 |
Neg logit contributions | |
Are | -0.011 |
Fox | -0.011 |
Raw | -0.011 |
noise | -0.010 |
AAAA | -0.010 |
Token | there |
Token ID | 612 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Fox | +0.022 |
Raw | +0.022 |
AAAA | +0.022 |
Are | +0.022 |
things | +0.021 |
Neg logit contributions | |
oll | -0.037 |
aney | -0.035 |
ier | -0.035 |
contain | -0.033 |
ige | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Fox | +0.024 |
We | +0.023 |
things | +0.023 |
Are | +0.023 |
cave | +0.022 |
Neg logit contributions | |
oll | -0.047 |
aney | -0.045 |
ier | -0.044 |
ige | -0.044 |
contain | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
oll | +0.015 |
aney | +0.015 |
ax | +0.014 |
ver | +0.014 |
ill | +0.014 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
situations | -0.008 |
things | -0.008 |
pans | -0.008 |
Token | books |
Token ID | 3835 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ier | +0.002 |
oll | +0.002 |
aney | +0.002 |
contain | +0.002 |
ver | +0.002 |
Neg logit contributions | |
AAAA | -0.001 |
Are | -0.001 |
Raw | -0.001 |
Fox | -0.001 |
We | -0.001 |
Token | he |
Token ID | 258 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
oll | +0.009 |
ige | +0.008 |
aney | +0.008 |
ax | +0.008 |
ipp | +0.008 |
Neg logit contributions | |
Are | -0.007 |
AAAA | -0.007 |
noise | -0.007 |
cave | -0.007 |
things | -0.007 |
Token | lf |
Token ID | 1652 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
oll | +0.321 |
ier | +0.318 |
aney | +0.304 |
contain | +0.293 |
ver | +0.280 |
Neg logit contributions | |
AAAA | -0.232 |
Raw | -0.224 |
Are | -0.223 |
Fox | -0.211 |
Come | -0.208 |
Token | was |
Token ID | 373 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
oll | +0.078 |
ier | +0.074 |
aney | +0.072 |
ige | +0.071 |
ax | +0.070 |
Neg logit contributions | |
things | -0.027 |
Fox | -0.027 |
Are | -0.026 |
AAAA | -0.026 |
cave | -0.026 |
Token | too |
Token ID | 1165 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
cave | +0.009 |
noise | +0.009 |
Fox | +0.009 |
Are | +0.008 |
things | +0.008 |
Neg logit contributions | |
oll | -0.018 |
aney | -0.017 |
ier | -0.017 |
contain | -0.016 |
ax | -0.016 |
Token | big |
Token ID | 1263 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
oll | +0.007 |
ier | +0.007 |
aney | +0.007 |
contain | +0.007 |
aces | +0.007 |
Neg logit contributions | |
AAAA | -0.003 |
Fox | -0.003 |
We | -0.003 |
Are | -0.003 |
Ar | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Are | +0.004 |
We | +0.004 |
Fox | +0.004 |
AAAA | +0.004 |
Come | +0.004 |
Neg logit contributions | |
aney | -0.006 |
oll | -0.006 |
ier | -0.006 |
contain | -0.006 |
ige | -0.005 |
Token | So |
Token ID | 2396 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
AAAA | +0.008 |
Are | +0.007 |
Fox | +0.007 |
Raw | +0.007 |
Come | +0.007 |
Neg logit contributions | |
oll | -0.008 |
ier | -0.008 |
aney | -0.008 |
contain | -0.008 |
ver | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
AAAA | +0.021 |
Raw | +0.021 |
Are | +0.019 |
Look | +0.019 |
Come | +0.018 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
contain | -0.022 |
aney | -0.022 |
ver | -0.022 |
Token | two |
Token ID | 734 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
AAAA | +0.013 |
Raw | +0.012 |
Are | +0.012 |
Fox | +0.012 |
We | +0.011 |
Neg logit contributions | |
oll | -0.024 |
ier | -0.024 |
aney | -0.023 |
contain | -0.022 |
ver | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
oll | +0.039 |
ier | +0.038 |
aney | +0.038 |
contain | +0.035 |
ige | +0.035 |
Neg logit contributions | |
things | -0.033 |
Are | -0.033 |
AAAA | -0.032 |
We | -0.032 |
Raw | -0.031 |
Token | them |
Token ID | 606 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
oll | +0.093 |
ier | +0.093 |
aney | +0.088 |
contain | +0.086 |
ver | +0.085 |
Neg logit contributions | |
AAAA | -0.050 |
Raw | -0.048 |
Fox | -0.046 |
Are | -0.045 |
Look | -0.045 |
Token | swung |
Token ID | 28507 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
oll | +0.016 |
ier | +0.016 |
aney | +0.014 |
ax | +0.014 |
iness | +0.014 |
Neg logit contributions | |
AAAA | -0.006 |
Quick | -0.006 |
B | -0.006 |
houses | -0.005 |
turns | -0.005 |
Token | together |
Token ID | 1978 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
oll | +0.311 |
ier | +0.300 |
aney | +0.283 |
contain | +0.273 |
ver | +0.267 |
Neg logit contributions | |
AAAA | -0.156 |
Raw | -0.149 |
Are | -0.143 |
Fox | -0.143 |
Look | -0.140 |
Token | for |
Token ID | 329 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
things | +0.049 |
Fox | +0.043 |
houses | +0.043 |
Water | +0.041 |
places | +0.040 |
Neg logit contributions | |
oll | -0.151 |
ier | -0.145 |
aney | -0.135 |
ax | -0.132 |
ige | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
AAAA | +0.002 |
Raw | +0.002 |
Are | +0.002 |
Fox | +0.002 |
We | +0.002 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
contain | -0.003 |
ver | -0.003 |
Token | rest |
Token ID | 1334 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
AAAA | +0.013 |
Are | +0.013 |
Raw | +0.013 |
Fox | +0.012 |
We | +0.012 |
Neg logit contributions | |
oll | -0.025 |
ier | -0.024 |
aney | -0.024 |
contain | -0.022 |
ver | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
oll | +0.059 |
ige | +0.058 |
contain | +0.054 |
ax | +0.053 |
fourteen | +0.053 |
Neg logit contributions | |
things | -0.063 |
We | -0.062 |
cave | -0.058 |
Fox | -0.057 |
situations | -0.057 |
Token | kept |
Token ID | 4030 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ier | +0.045 |
oll | +0.043 |
aney | +0.041 |
contain | +0.040 |
ax | +0.038 |
Neg logit contributions | |
AAAA | -0.027 |
Raw | -0.027 |
Are | -0.027 |
Fox | -0.026 |
We | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Raw | +0.028 |
AAAA | +0.027 |
Are | +0.026 |
Sorry | +0.025 |
Ro | +0.025 |
Neg logit contributions | |
oll | -0.034 |
ier | -0.032 |
ax | -0.030 |
contain | -0.030 |
ige | -0.029 |
Token | on |
Token ID | 319 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
cave | +0.022 |
Fox | +0.021 |
things | +0.021 |
Are | +0.020 |
AAAA | +0.019 |
Neg logit contributions | |
oll | -0.041 |
ier | -0.039 |
aney | -0.039 |
ax | -0.037 |
ige | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
AAAA | +0.000 |
Raw | +0.000 |
Are | +0.000 |
Fox | +0.000 |
We | +0.000 |
Neg logit contributions | |
oll | -0.001 |
ier | -0.001 |
aney | -0.001 |
contain | -0.001 |
ver | -0.001 |
Token | bed |
Token ID | 3996 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ier | +0.001 |
oll | +0.001 |
aney | +0.001 |
ver | +0.001 |
ax | +0.001 |
Neg logit contributions | |
cave | -0.000 |
Are | -0.000 |
Fox | -0.000 |
AAAA | -0.000 |
things | -0.000 |
Token | side |
Token ID | 1589 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
cave | +0.013 |
things | +0.012 |
noise | +0.012 |
Fox | +0.012 |
voice | +0.011 |
Neg logit contributions | |
aney | -0.038 |
oll | -0.038 |
vious | -0.036 |
ige | -0.036 |
ax | -0.036 |
Token | table |
Token ID | 3084 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
oll | +0.256 |
ier | +0.254 |
aney | +0.239 |
contain | +0.228 |
ver | +0.226 |
Neg logit contributions | |
AAAA | -0.153 |
Are | -0.150 |
Raw | -0.149 |
Fox | -0.146 |
We | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
things | +0.011 |
cave | +0.011 |
Fox | +0.010 |
places | +0.010 |
noise | +0.009 |
Neg logit contributions | |
oll | -0.033 |
aney | -0.031 |
ier | -0.031 |
ige | -0.030 |
ax | -0.030 |
Token | looked |
Token ID | 3114 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
oll | +0.002 |
ier | +0.002 |
aney | +0.002 |
contain | +0.002 |
ver | +0.002 |
Neg logit contributions | |
AAAA | -0.002 |
Raw | -0.002 |
Are | -0.002 |
Fox | -0.002 |
We | -0.002 |
Token | at |
Token ID | 379 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
oll | +0.062 |
ier | +0.060 |
aney | +0.059 |
ver | +0.055 |
contain | +0.054 |
Neg logit contributions | |
Are | -0.053 |
AAAA | -0.051 |
We | -0.051 |
things | -0.050 |
Fox | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
oll | +0.046 |
ier | +0.045 |
aney | +0.045 |
contain | +0.043 |
ver | +0.042 |
Neg logit contributions | |
things | -0.010 |
shadows | -0.008 |
Fox | -0.007 |
Water | -0.007 |
Look | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
oll | +0.184 |
aney | +0.178 |
ier | +0.173 |
ige | +0.171 |
wy | +0.169 |
Neg logit contributions | |
We | -0.041 |
Run | -0.040 |
sounds | -0.040 |
things | -0.039 |
Come | -0.038 |
Token | held |
Token ID | 2714 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.009 |
Are | +0.009 |
Fox | +0.009 |
We | +0.008 |
Neg logit contributions | |
oll | -0.011 |
ier | -0.011 |
aney | -0.010 |
contain | -0.010 |
ver | -0.009 |
Token | tight |
Token ID | 5381 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
oll | +0.045 |
ier | +0.043 |
aney | +0.041 |
contain | +0.040 |
ver | +0.039 |
Neg logit contributions | |
AAAA | -0.028 |
Raw | -0.027 |
Are | -0.027 |
Fox | -0.024 |
We | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aney | +0.062 |
oll | +0.062 |
ier | +0.061 |
contain | +0.058 |
ige | +0.056 |
Neg logit contributions | |
Fox | -0.036 |
things | -0.034 |
Are | -0.034 |
Come | -0.033 |
Raw | -0.033 |
Token | Wh |
Token ID | 854 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
AAAA | +0.006 |
Peter | +0.005 |
Raw | +0.005 |
situations | +0.005 |
cave | +0.005 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.008 |
ver | -0.008 |
aney | -0.008 |
aces | -0.008 |
Token | isk |
Token ID | 1984 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
oll | +0.094 |
ier | +0.092 |
contain | +0.088 |
aney | +0.087 |
ver | +0.077 |
Neg logit contributions | |
AAAA | -0.134 |
Raw | -0.130 |
Are | -0.128 |
Fox | -0.126 |
Come | -0.123 |
Token | ers |
Token ID | 364 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
oll | +0.275 |
ier | +0.258 |
aney | +0.250 |
contain | +0.246 |
ax | +0.227 |
Neg logit contributions | |
AAAA | -0.336 |
Raw | -0.329 |
Are | -0.318 |
Fox | -0.315 |
Look | -0.310 |
Token | pushed |
Token ID | 7121 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Look | +0.003 |
AAAA | +0.003 |
Raw | +0.002 |
sounds | +0.002 |
Are | +0.002 |
Neg logit contributions | |
oll | -0.008 |
ier | -0.008 |
aney | -0.007 |
ust | -0.007 |
ige | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.010 |
aney | +0.009 |
contain | +0.009 |
ax | +0.009 |
Neg logit contributions | |
AAAA | -0.009 |
Raw | -0.008 |
Are | -0.008 |
cave | -0.008 |
Sorry | -0.008 |
Token | gently |
Token ID | 15165 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
AAAA | +0.051 |
Fox | +0.050 |
things | +0.050 |
Are | +0.050 |
Raw | +0.048 |
Neg logit contributions | |
oll | -0.115 |
ier | -0.115 |
aney | -0.113 |
ige | -0.104 |
contain | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
Are | +0.009 |
AAAA | +0.009 |
Fox | +0.008 |
things | +0.008 |
Raw | +0.008 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.020 |
aney | -0.020 |
ver | -0.018 |
ige | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.026 |
Are | +0.026 |
Fox | +0.025 |
We | +0.024 |
Neg logit contributions | |
oll | -0.033 |
ier | -0.032 |
aney | -0.031 |
contain | -0.029 |
ver | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ier | +0.019 |
oll | +0.019 |
aney | +0.017 |
ver | +0.017 |
contain | +0.017 |
Neg logit contributions | |
Raw | -0.022 |
AAAA | -0.022 |
Are | -0.021 |
Peter | -0.021 |
Look | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
ier | +0.001 |
oll | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Come | -0.001 |
Fox | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
situations | +0.005 |
Come | +0.005 |
Raw | +0.005 |
AAAA | +0.005 |
keeping | +0.005 |
Neg logit contributions | |
ier | -0.005 |
oll | -0.005 |
aney | -0.004 |
ver | -0.004 |
contain | -0.004 |
Token | boy |
Token ID | 2933 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
AAAA | +0.001 |
Raw | +0.001 |
Peter | +0.001 |
Look | +0.001 |
inct | +0.001 |
Neg logit contributions | |
ier | -0.001 |
oll | -0.001 |
igator | -0.001 |
vious | -0.001 |
contain | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Raw | +0.039 |
Peter | +0.038 |
AAAA | +0.038 |
Are | +0.037 |
Fox | +0.036 |
Neg logit contributions | |
ier | -0.024 |
oll | -0.024 |
aney | -0.022 |
ver | -0.022 |
ill | -0.020 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
oll | +0.015 |
ier | +0.015 |
aney | +0.015 |
contain | +0.014 |
ver | +0.014 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Are | -0.012 |
Peter | -0.011 |
Look | -0.011 |
Token | came |
Token ID | 1625 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
AAAA | +0.026 |
Raw | +0.026 |
Are | +0.025 |
Fox | +0.024 |
We | +0.024 |
Neg logit contributions | |
oll | -0.037 |
ier | -0.037 |
aney | -0.035 |
contain | -0.033 |
ax | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ier | +0.032 |
contain | +0.031 |
ver | +0.029 |
aney | +0.029 |
oll | +0.029 |
Neg logit contributions | |
AAAA | -0.045 |
Raw | -0.044 |
Are | -0.043 |
Sorry | -0.041 |
oc | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
contain | +0.014 |
ier | +0.013 |
aney | +0.013 |
oll | +0.013 |
ver | +0.013 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Are | -0.012 |
Come | -0.012 |
We | -0.011 |
Token | hut |
Token ID | 40812 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
AAAA | +0.014 |
Raw | +0.013 |
Are | +0.013 |
Come | +0.012 |
Peter | +0.012 |
Neg logit contributions | |
ier | -0.029 |
oll | -0.028 |
he | -0.027 |
aney | -0.027 |
contain | -0.026 |
Token | together |
Token ID | 1978 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
oll | +0.059 |
ier | +0.056 |
aney | +0.054 |
contain | +0.051 |
ige | +0.050 |
Neg logit contributions | |
Are | -0.037 |
Fox | -0.036 |
We | -0.036 |
AAAA | -0.036 |
Raw | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
things | +0.058 |
Fox | +0.057 |
We | +0.056 |
Are | +0.053 |
cave | +0.052 |
Neg logit contributions | |
oll | -0.135 |
ier | -0.124 |
aney | -0.122 |
ige | -0.118 |
ax | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aney | +0.002 |
oll | +0.002 |
ier | +0.002 |
ver | +0.002 |
contain | +0.002 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
cave | -0.001 |
Fox | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Are | +0.006 |
Raw | +0.006 |
Fox | +0.006 |
situations | +0.006 |
Neg logit contributions | |
aney | -0.013 |
oll | -0.013 |
ier | -0.012 |
ver | -0.012 |
contain | -0.012 |
Token | The |
Token ID | 464 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Are | +0.008 |
Fox | +0.008 |
AAAA | +0.008 |
Raw | +0.008 |
cave | +0.008 |
Neg logit contributions | |
aney | -0.011 |
ier | -0.011 |
oll | -0.011 |
contain | -0.010 |
ver | -0.010 |
Token | compassionate |
Token ID | 32533 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
oll | +0.081 |
ier | +0.080 |
aney | +0.076 |
ver | +0.072 |
contain | +0.072 |
Neg logit contributions | |
AAAA | -0.043 |
Raw | -0.042 |
Are | -0.042 |
Fox | -0.039 |
We | -0.038 |
Token | lady |
Token ID | 10846 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
oll | +0.033 |
ier | +0.032 |
aney | +0.030 |
contain | +0.029 |
ver | +0.029 |
Neg logit contributions | |
AAAA | -0.016 |
Are | -0.016 |
Raw | -0.015 |
Fox | -0.015 |
We | -0.015 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
Are | +0.007 |
Fox | +0.007 |
AAAA | +0.007 |
Raw | +0.006 |
We | +0.006 |
Neg logit contributions | |
oll | -0.012 |
ier | -0.012 |
aney | -0.011 |
contain | -0.011 |
ige | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
Are | +0.002 |
Fox | +0.002 |
AAAA | +0.002 |
We | +0.002 |
Raw | +0.002 |
Neg logit contributions | |
oll | -0.003 |
aney | -0.003 |
ier | -0.003 |
contain | -0.003 |
ige | -0.003 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Are | +0.005 |
Raw | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.006 |
ier | -0.006 |
aney | -0.006 |
contain | -0.005 |
ver | -0.005 |
Token | them |
Token ID | 606 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
oll | +0.012 |
ier | +0.012 |
aney | +0.011 |
contain | +0.010 |
ver | +0.010 |
Neg logit contributions | |
AAAA | -0.009 |
Are | -0.009 |
Raw | -0.009 |
Fox | -0.008 |
We | -0.008 |
Token | better |
Token ID | 1365 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
AAAA | +0.018 |
Are | +0.018 |
Fox | +0.017 |
Raw | +0.017 |
We | +0.017 |
Neg logit contributions | |
oll | -0.027 |
ier | -0.027 |
aney | -0.026 |
contain | -0.025 |
ver | -0.024 |
Token | than |
Token ID | 621 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
AAAA | +0.060 |
Raw | +0.059 |
Look | +0.056 |
Are | +0.055 |
Peter | +0.053 |
Neg logit contributions | |
ier | -0.058 |
oll | -0.057 |
contain | -0.050 |
ver | -0.049 |
aney | -0.049 |
Token | greed |
Token ID | 25474 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Fox | +0.034 |
Are | +0.033 |
AAAA | +0.033 |
Raw | +0.033 |
things | +0.032 |
Neg logit contributions | |
oll | -0.063 |
ier | -0.059 |
aney | -0.058 |
ver | -0.055 |
contain | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Fox | +0.110 |
AAAA | +0.107 |
Are | +0.106 |
things | +0.105 |
Come | +0.104 |
Neg logit contributions | |
aney | -0.164 |
oll | -0.159 |
contain | -0.156 |
salon | -0.150 |
ige | -0.148 |
Token | child |
Token ID | 1200 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
oll | +0.010 |
ier | +0.010 |
aney | +0.009 |
contain | +0.009 |
ver | +0.009 |
Neg logit contributions | |
Are | -0.007 |
AAAA | -0.007 |
Raw | -0.007 |
We | -0.006 |
Fox | -0.006 |
Token | ." |
Token ID | 526 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Are | +0.026 |
We | +0.026 |
Fox | +0.026 |
AAAA | +0.025 |
Raw | +0.025 |
Neg logit contributions | |
oll | -0.043 |
ier | -0.041 |
aney | -0.040 |
contain | -0.039 |
ax | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
oll | +0.022 |
ier | +0.022 |
aney | +0.021 |
ax | +0.020 |
contain | +0.020 |
Neg logit contributions | |
AAAA | -0.020 |
Raw | -0.020 |
Ar | -0.019 |
Fox | -0.019 |
Are | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.005 |
Sorry | +0.005 |
Neg logit contributions | |
oll | -0.011 |
ier | -0.011 |
aney | -0.011 |
ax | -0.010 |
he | -0.010 |
Token | L |
Token ID | 43 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.006 |
Are | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.009 |
ier | -0.009 |
aney | -0.009 |
contain | -0.008 |
ax | -0.008 |
Token | illy |
Token ID | 6548 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
contain | +0.044 |
oll | +0.043 |
ier | +0.043 |
aney | +0.042 |
ver | +0.041 |
Neg logit contributions | |
AAAA | -0.081 |
Come | -0.077 |
Are | -0.075 |
Raw | -0.073 |
Look | -0.072 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.005 |
Are | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.007 |
ier | -0.007 |
aney | -0.007 |
contain | -0.006 |
ver | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
AAAA | +0.018 |
Raw | +0.018 |
Ar | +0.018 |
Peter | +0.017 |
oc | +0.017 |
Neg logit contributions | |
oll | -0.022 |
ier | -0.020 |
aney | -0.020 |
ver | -0.019 |
ill | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ier | +0.037 |
oll | +0.036 |
contain | +0.036 |
aney | +0.036 |
aces | +0.034 |
Neg logit contributions | |
AAAA | -0.016 |
Are | -0.015 |
Raw | -0.015 |
Look | -0.014 |
Fox | -0.014 |
Token | still |
Token ID | 991 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Look | +0.005 |
Are | +0.005 |
noise | +0.005 |
Help | +0.004 |
Neg logit contributions | |
oll | -0.010 |
aney | -0.010 |
iness | -0.010 |
contain | -0.010 |
ier | -0.010 |
Token | angry |
Token ID | 7954 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
AAAA | +0.009 |
Are | +0.009 |
Raw | +0.009 |
Fox | +0.008 |
We | +0.008 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.012 |
contain | -0.012 |
ver | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
oll | +0.030 |
aney | +0.029 |
ier | +0.028 |
contain | +0.028 |
ige | +0.027 |
Neg logit contributions | |
Are | -0.020 |
We | -0.019 |
Come | -0.019 |
AAAA | -0.019 |
Raw | -0.019 |
Token | but |
Token ID | 475 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
Are | +0.005 |
AAAA | +0.005 |
Raw | +0.005 |
Fox | +0.005 |
We | +0.005 |
Neg logit contributions | |
oll | -0.008 |
ier | -0.008 |
aney | -0.007 |
contain | -0.007 |
ver | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
oll | +0.002 |
ier | +0.002 |
aney | +0.002 |
contain | +0.002 |
ige | +0.002 |
Neg logit contributions | |
Are | -0.002 |
We | -0.002 |
AAAA | -0.002 |
Fox | -0.002 |
Raw | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ier | +0.004 |
oll | +0.003 |
aney | +0.003 |
contain | +0.003 |
aces | +0.003 |
Neg logit contributions | |
Are | -0.002 |
AAAA | -0.002 |
Raw | -0.002 |
Fox | -0.002 |
We | -0.002 |
Token | also |
Token ID | 635 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
things | +0.004 |
noise | +0.004 |
Are | +0.004 |
What | +0.004 |
Look | +0.004 |
Neg logit contributions | |
oll | -0.009 |
aney | -0.009 |
iness | -0.009 |
bars | -0.009 |
contain | -0.009 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
oll | +0.068 |
aney | +0.065 |
ier | +0.065 |
contain | +0.062 |
ill | +0.059 |
Neg logit contributions | |
Are | -0.043 |
AAAA | -0.041 |
We | -0.038 |
Raw | -0.037 |
Look | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
oll | +0.128 |
aney | +0.126 |
ier | +0.125 |
ige | +0.121 |
contain | +0.119 |
Neg logit contributions | |
Are | -0.084 |
We | -0.081 |
AAAA | -0.078 |
things | -0.078 |
Raw | -0.078 |
Token | Tim |
Token ID | 14967 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
AAAA | +0.005 |
Fox | +0.005 |
cave | +0.005 |
Are | +0.005 |
situations | +0.005 |
Neg logit contributions | |
aney | -0.007 |
ier | -0.007 |
ax | -0.007 |
oll | -0.007 |
ill | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
oll | +0.015 |
ier | +0.015 |
aney | +0.014 |
contain | +0.013 |
ver | +0.013 |
Neg logit contributions | |
AAAA | -0.014 |
Raw | -0.013 |
Are | -0.013 |
Fox | -0.012 |
Look | -0.012 |
Token | let |
Token ID | 1309 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
oll | +0.007 |
ier | +0.006 |
aney | +0.006 |
contain | +0.006 |
ax | +0.006 |
Neg logit contributions | |
AAAA | -0.004 |
Raw | -0.004 |
Ar | -0.004 |
Fox | -0.004 |
Are | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Raw | +0.019 |
AAAA | +0.019 |
Are | +0.019 |
Ar | +0.018 |
cave | +0.018 |
Neg logit contributions | |
oll | -0.016 |
ax | -0.015 |
ier | -0.015 |
aney | -0.014 |
ipp | -0.014 |
Token | try |
Token ID | 1949 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Are | +0.022 |
AAAA | +0.022 |
Raw | +0.022 |
Fox | +0.021 |
We | +0.020 |
Neg logit contributions | |
ier | -0.029 |
oll | -0.029 |
aney | -0.027 |
contain | -0.026 |
ver | -0.025 |
Token | something |
Token ID | 1223 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
AAAA | +0.042 |
Raw | +0.040 |
Are | +0.040 |
Fox | +0.037 |
Come | +0.037 |
Neg logit contributions | |
oll | -0.059 |
ier | -0.058 |
aney | -0.055 |
contain | -0.052 |
ax | -0.052 |
Token | new |
Token ID | 649 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
oll | +0.056 |
ier | +0.056 |
aney | +0.054 |
contain | +0.052 |
ige | +0.050 |
Neg logit contributions | |
AAAA | -0.039 |
Are | -0.039 |
Raw | -0.038 |
Fox | -0.037 |
We | -0.036 |
Token | today |
Token ID | 1909 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
AAAA | +0.021 |
Raw | +0.021 |
Are | +0.021 |
Fox | +0.020 |
We | +0.020 |
Neg logit contributions | |
oll | -0.032 |
ier | -0.032 |
aney | -0.030 |
contain | -0.029 |
ax | -0.028 |
Token | ." |
Token ID | 526 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
AAAA | +0.022 |
Raw | +0.021 |
Are | +0.021 |
Fox | +0.020 |
We | +0.020 |
Neg logit contributions | |
oll | -0.029 |
ier | -0.028 |
aney | -0.027 |
contain | -0.026 |
ver | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
aney | +0.027 |
oll | +0.026 |
ax | +0.025 |
ill | +0.025 |
ier | +0.024 |
Neg logit contributions | |
AAAA | -0.025 |
Ar | -0.024 |
Raw | -0.023 |
Fox | -0.022 |
Peter | -0.022 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ier | +0.037 |
oll | +0.037 |
aney | +0.035 |
contain | +0.034 |
ver | +0.032 |
Neg logit contributions | |
AAAA | -0.031 |
Raw | -0.030 |
Are | -0.030 |
Fox | -0.029 |
We | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
AAAA | +0.005 |
Raw | +0.004 |
Are | +0.004 |
Fox | +0.004 |
We | +0.004 |
Neg logit contributions | |
oll | -0.006 |
ier | -0.005 |
aney | -0.005 |
contain | -0.005 |
ver | -0.005 |
Token | one |
Token ID | 530 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
oll | +0.008 |
ier | +0.008 |
aney | +0.008 |
contain | +0.007 |
ver | +0.007 |
Neg logit contributions | |
Are | -0.005 |
AAAA | -0.005 |
Raw | -0.005 |
Fox | -0.005 |
We | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
oll | +0.099 |
ier | +0.095 |
ige | +0.092 |
ax | +0.089 |
aney | +0.088 |
Neg logit contributions | |
cave | -0.060 |
things | -0.058 |
Fox | -0.056 |
Are | -0.056 |
We | -0.054 |
Token | front |
Token ID | 2166 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
AAAA | +0.029 |
Are | +0.028 |
Raw | +0.028 |
Fox | +0.027 |
We | +0.026 |
Neg logit contributions | |
oll | -0.055 |
ier | -0.055 |
aney | -0.052 |
contain | -0.050 |
ax | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
cave | +0.019 |
things | +0.019 |
voices | +0.019 |
places | +0.018 |
houses | +0.018 |
Neg logit contributions | |
oll | -0.017 |
ier | -0.017 |
ver | -0.016 |
pper | -0.015 |
ige | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
oll | +0.092 |
ier | +0.092 |
aney | +0.085 |
ver | +0.083 |
contain | +0.082 |
Neg logit contributions | |
Fox | -0.043 |
Are | -0.041 |
AAAA | -0.040 |
Look | -0.039 |
Raw | -0.039 |
Token | other |
Token ID | 584 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
AAAA | +0.016 |
Raw | +0.015 |
Are | +0.015 |
We | +0.014 |
Come | +0.014 |
Neg logit contributions | |
ier | -0.026 |
oll | -0.026 |
aney | -0.024 |
contain | -0.024 |
ige | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
oll | +0.036 |
ier | +0.036 |
aney | +0.034 |
contain | +0.033 |
ax | +0.032 |
Neg logit contributions | |
AAAA | -0.024 |
Raw | -0.023 |
Are | -0.023 |
Fox | -0.021 |
We | -0.021 |
Token | Grand |
Token ID | 5675 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
oll | +0.008 |
aney | +0.008 |
ier | +0.007 |
ax | +0.007 |
ill | +0.007 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
cave | -0.005 |
situations | -0.005 |
Token | pa |
Token ID | 8957 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
AAAA | +0.076 |
Are | +0.075 |
Raw | +0.074 |
Fox | +0.073 |
We | +0.072 |
Neg logit contributions | |
oll | -0.082 |
ier | -0.081 |
aney | -0.076 |
contain | -0.075 |
ver | -0.071 |
Token | helps |
Token ID | 5419 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
AAAA | +0.052 |
Are | +0.051 |
Raw | +0.051 |
Fox | +0.050 |
We | +0.048 |
Neg logit contributions | |
oll | -0.105 |
ier | -0.105 |
aney | -0.100 |
contain | -0.098 |
ige | -0.093 |
Token | happen |
Token ID | 1645 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
oll | +0.011 |
aney | +0.010 |
ier | +0.010 |
ax | +0.010 |
ige | +0.010 |
Neg logit contributions | |
AAAA | -0.007 |
Are | -0.007 |
We | -0.007 |
Raw | -0.007 |
things | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.011 |
Fox | +0.011 |
We | +0.010 |
Neg logit contributions | |
oll | -0.014 |
ier | -0.014 |
aney | -0.013 |
contain | -0.012 |
ver | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
oll | +0.001 |
ier | +0.001 |
aney | +0.001 |
contain | +0.001 |
ver | +0.001 |
Neg logit contributions | |
AAAA | -0.001 |
Are | -0.001 |
Raw | -0.001 |
Fox | -0.001 |
We | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
oll | +0.006 |
ier | +0.006 |
aney | +0.006 |
contain | +0.006 |
ver | +0.005 |
Neg logit contributions | |
AAAA | -0.005 |
Raw | -0.005 |
Are | -0.005 |
Fox | -0.005 |
Come | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
AAAA | +0.027 |
Raw | +0.026 |
Are | +0.026 |
Fox | +0.024 |
Come | +0.024 |
Neg logit contributions | |
oll | -0.049 |
ier | -0.048 |
aney | -0.046 |
contain | -0.044 |
ver | -0.043 |
Token | important |
Token ID | 1593 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
things | +0.018 |
Fox | +0.018 |
AAAA | +0.017 |
Are | +0.017 |
We | +0.017 |
Neg logit contributions | |
aney | -0.027 |
contain | -0.026 |
oll | -0.026 |
ier | -0.025 |
ax | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
AAAA | +0.050 |
Are | +0.049 |
Raw | +0.049 |
Fox | +0.047 |
We | +0.047 |
Neg logit contributions | |
oll | -0.089 |
ier | -0.087 |
aney | -0.085 |
contain | -0.082 |
ax | -0.079 |
Token | stay |
Token ID | 2652 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
oll | +0.028 |
ier | +0.027 |
aney | +0.027 |
ver | +0.024 |
contain | +0.024 |
Neg logit contributions | |
Fox | -0.015 |
Are | -0.015 |
AAAA | -0.014 |
Raw | -0.014 |
We | -0.013 |
Token | positive |
Token ID | 3967 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ier | +0.033 |
oll | +0.032 |
contain | +0.029 |
aney | +0.029 |
ver | +0.028 |
Neg logit contributions | |
Raw | -0.031 |
AAAA | -0.030 |
Are | -0.029 |
Fox | -0.027 |
Look | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
AAAA | +0.038 |
Are | +0.037 |
Raw | +0.037 |
Fox | +0.036 |
We | +0.035 |
Neg logit contributions | |
oll | -0.048 |
ier | -0.047 |
aney | -0.045 |
contain | -0.043 |
ax | -0.042 |
Token | find |
Token ID | 1064 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
AAAA | +0.012 |
Raw | +0.012 |
Are | +0.011 |
Fox | +0.011 |
Look | +0.010 |
Neg logit contributions | |
ier | -0.013 |
oll | -0.013 |
contain | -0.012 |
aney | -0.011 |
ver | -0.011 |
Token | until |
Token ID | 1566 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
oll | +0.049 |
ier | +0.047 |
aney | +0.046 |
contain | +0.044 |
ver | +0.044 |
Neg logit contributions | |
AAAA | -0.026 |
Raw | -0.025 |
Are | -0.025 |
things | -0.025 |
Fox | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
oll | +0.004 |
ier | +0.004 |
aney | +0.004 |
contain | +0.003 |
ige | +0.003 |
Neg logit contributions | |
AAAA | -0.003 |
Are | -0.003 |
Raw | -0.003 |
Fox | -0.002 |
We | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Raw | +0.013 |
AAAA | +0.013 |
Look | +0.011 |
Are | +0.011 |
Ar | +0.010 |
Neg logit contributions | |
oll | -0.049 |
ier | -0.046 |
contain | -0.046 |
aney | -0.046 |
ige | -0.045 |
Token | time |
Token ID | 640 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
AAAA | +0.006 |
Raw | +0.005 |
Look | +0.005 |
Water | +0.005 |
noise | +0.005 |
Neg logit contributions | |
oll | -0.010 |
aney | -0.009 |
ier | -0.009 |
salon | -0.009 |
contain | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
oll | +0.056 |
aney | +0.051 |
ier | +0.051 |
pper | +0.049 |
vious | +0.048 |
Neg logit contributions | |
We | -0.023 |
Come | -0.022 |
things | -0.021 |
Are | -0.021 |
Help | -0.020 |
Token | go |
Token ID | 467 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
oll | +0.019 |
ier | +0.019 |
aney | +0.018 |
ver | +0.017 |
aces | +0.017 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
Are | -0.009 |
Fox | -0.009 |
Look | -0.009 |
Token | home |
Token ID | 1363 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
AAAA | +0.038 |
Raw | +0.037 |
Are | +0.036 |
Fox | +0.035 |
We | +0.034 |
Neg logit contributions | |
oll | -0.068 |
ier | -0.067 |
aney | -0.064 |
contain | -0.062 |
ver | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
We | +0.056 |
Are | +0.055 |
Fox | +0.055 |
cave | +0.053 |
things | +0.052 |
Neg logit contributions | |
oll | -0.103 |
aney | -0.095 |
ier | -0.095 |
ige | -0.091 |
ver | -0.087 |
Token | But |
Token ID | 887 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
oll | +0.006 |
aney | +0.006 |
ier | +0.005 |
ver | +0.005 |
ax | +0.005 |
Neg logit contributions | |
AAAA | -0.004 |
Raw | -0.004 |
Ar | -0.004 |
Are | -0.004 |
cave | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.021 |
aney | +0.021 |
contain | +0.019 |
ige | +0.019 |
Neg logit contributions | |
Are | -0.014 |
Fox | -0.014 |
AAAA | -0.014 |
We | -0.013 |
Raw | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ier | +0.007 |
oll | +0.007 |
aney | +0.006 |
contain | +0.006 |
aces | +0.006 |
Neg logit contributions | |
Are | -0.003 |
AAAA | -0.003 |
Fox | -0.003 |
Raw | -0.003 |
cave | -0.002 |
Token | share |
Token ID | 2648 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
oll | +0.022 |
ier | +0.022 |
aney | +0.021 |
ax | +0.019 |
contain | +0.019 |
Neg logit contributions | |
Are | -0.014 |
AAAA | -0.014 |
Fox | -0.013 |
Raw | -0.013 |
We | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
AAAA | +0.038 |
Raw | +0.038 |
Are | +0.037 |
Fox | +0.034 |
Come | +0.034 |
Neg logit contributions | |
ier | -0.056 |
oll | -0.056 |
aney | -0.053 |
contain | -0.051 |
ver | -0.049 |
Token | be |
Token ID | 307 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
AAAA | +0.003 |
Raw | +0.003 |
Are | +0.003 |
Fox | +0.003 |
Come | +0.003 |
Neg logit contributions | |
contain | -0.003 |
ier | -0.003 |
oll | -0.003 |
aney | -0.003 |
ver | -0.003 |
Token | kind |
Token ID | 1611 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
ier | +0.041 |
oll | +0.039 |
aney | +0.037 |
contain | +0.036 |
ver | +0.035 |
Neg logit contributions | |
AAAA | -0.035 |
Raw | -0.034 |
Are | -0.033 |
Fox | -0.031 |
Come | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
AAAA | +0.020 |
Are | +0.020 |
Raw | +0.020 |
Fox | +0.019 |
We | +0.019 |
Neg logit contributions | |
oll | -0.028 |
ier | -0.028 |
aney | -0.027 |
contain | -0.026 |
ax | -0.025 |
Token | instead |
Token ID | 2427 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oll | +0.006 |
ier | +0.005 |
aney | +0.005 |
contain | +0.005 |
ax | +0.005 |
Neg logit contributions | |
AAAA | -0.006 |
Are | -0.006 |
Raw | -0.006 |
Fox | -0.005 |
We | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
AAAA | +0.090 |
Are | +0.090 |
Raw | +0.089 |
We | +0.088 |
Fox | +0.088 |
Neg logit contributions | |
oll | -0.049 |
ier | -0.046 |
aney | -0.045 |
contain | -0.041 |
ax | -0.039 |
Token | being |
Token ID | 852 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
ier | +0.082 |
oll | +0.080 |
contain | +0.075 |
aney | +0.074 |
ver | +0.072 |
Neg logit contributions | |
AAAA | -0.064 |
Raw | -0.063 |
Are | -0.061 |
Come | -0.058 |
Look | -0.057 |
Token | nos |
Token ID | 43630 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
AAAA | +0.002 |
Are | +0.002 |
Raw | +0.002 |
Fox | +0.002 |
We | +0.002 |
Neg logit contributions | |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
contain | -0.002 |
ax | -0.002 |
Token | y |
Token ID | 88 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
Are | +0.056 |
We | +0.055 |
AAAA | +0.054 |
Come | +0.053 |
Fox | +0.053 |
Neg logit contributions | |
oll | -0.060 |
contain | -0.056 |
aney | -0.054 |
ier | -0.053 |
ige | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Are | +0.041 |
We | +0.040 |
AAAA | +0.040 |
Fox | +0.040 |
Raw | +0.038 |
Neg logit contributions | |
oll | -0.059 |
aney | -0.057 |
ier | -0.056 |
contain | -0.054 |
ax | -0.053 |
Token | They |
Token ID | 1119 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Raw | +0.008 |
AAAA | +0.008 |
cave | +0.007 |
Peter | +0.007 |
Fox | +0.007 |
Neg logit contributions | |
aney | -0.017 |
oll | -0.016 |
ier | -0.016 |
ver | -0.016 |
ill | -0.015 |
Token | climbed |
Token ID | 19952 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
AAAA | +0.017 |
Raw | +0.017 |
Fox | +0.017 |
Are | +0.017 |
Run | +0.015 |
Neg logit contributions | |
ier | -0.032 |
oll | -0.032 |
aney | -0.030 |
ax | -0.027 |
ipp | -0.027 |
Token | over |
Token ID | 625 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
ier | +0.152 |
oll | +0.143 |
aney | +0.138 |
contain | +0.135 |
ver | +0.134 |
Neg logit contributions | |
Are | -0.121 |
Raw | -0.121 |
AAAA | -0.120 |
Fox | -0.109 |
Sorry | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ier | +0.068 |
oll | +0.067 |
aney | +0.065 |
contain | +0.063 |
ver | +0.061 |
Neg logit contributions | |
AAAA | -0.052 |
Are | -0.051 |
Raw | -0.051 |
Fox | -0.047 |
Come | -0.046 |
Token | gate |
Token ID | 8946 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Raw | +0.021 |
AAAA | +0.021 |
Are | +0.021 |
Fox | +0.020 |
Peter | +0.020 |
Neg logit contributions | |
ier | -0.030 |
contain | -0.028 |
oll | -0.028 |
aney | -0.028 |
ige | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
oll | +0.050 |
ige | +0.045 |
wy | +0.045 |
ier | +0.044 |
aney | +0.044 |
Neg logit contributions | |
We | -0.014 |
cave | -0.012 |
Help | -0.012 |
things | -0.011 |
houses | -0.011 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
AAAA | +0.015 |
Raw | +0.015 |
Are | +0.015 |
Fox | +0.014 |
We | +0.014 |
Neg logit contributions | |
oll | -0.018 |
ier | -0.018 |
aney | -0.017 |
contain | -0.016 |
ver | -0.015 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
AAAA | +0.024 |
Raw | +0.023 |
Are | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
oll | -0.029 |
ier | -0.029 |
aney | -0.028 |
contain | -0.027 |
ver | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.021 |
aney | +0.020 |
contain | +0.019 |
ax | +0.018 |
Neg logit contributions | |
AAAA | -0.017 |
Are | -0.017 |
Raw | -0.017 |
Fox | -0.016 |
We | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
AAAA | +0.009 |
Raw | +0.009 |
situations | +0.009 |
cave | +0.008 |
oc | +0.008 |
Neg logit contributions | |
aney | -0.015 |
oll | -0.015 |
ver | -0.014 |
contain | -0.014 |
ill | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
AAAA | +0.015 |
Raw | +0.014 |
Are | +0.014 |
Fox | +0.014 |
situations | +0.013 |
Neg logit contributions | |
oll | -0.033 |
aney | -0.033 |
ier | -0.032 |
ver | -0.031 |
contain | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
AAAA | +0.011 |
Raw | +0.011 |
Are | +0.011 |
Fox | +0.010 |
Look | +0.010 |
Neg logit contributions | |
oll | -0.013 |
ier | -0.013 |
aney | -0.012 |
contain | -0.012 |
ver | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
oll | +0.019 |
ier | +0.018 |
aney | +0.017 |
contain | +0.016 |
ax | +0.015 |
Neg logit contributions | |
AAAA | -0.026 |
Are | -0.026 |
Raw | -0.025 |
Fox | -0.025 |
We | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
AAAA | +0.001 |
Raw | +0.001 |
Are | +0.001 |
Come | +0.001 |
Fox | +0.001 |
Neg logit contributions | |
oll | -0.002 |
ier | -0.002 |
aney | -0.002 |
contain | -0.002 |
ax | -0.002 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
AAAA | +0.017 |
Raw | +0.016 |
Are | +0.016 |
Fox | +0.015 |
Come | +0.015 |
Neg logit contributions | |
oll | -0.026 |
ier | -0.026 |
aney | -0.024 |
contain | -0.024 |
ax | -0.023 |
Token | in |
Token ID | 259 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
AAAA | +0.010 |
Raw | +0.010 |
Are | +0.010 |
Fox | +0.010 |
Peter | +0.010 |
Neg logit contributions | |
oll | -0.010 |
aney | -0.009 |
ier | -0.009 |
contain | -0.009 |
ige | -0.008 |
Token | oc |
Token ID | 420 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
oll | +0.009 |
ier | +0.008 |
aney | +0.008 |
contain | +0.008 |
ver | +0.008 |
Neg logit contributions | |
AAAA | -0.001 |
Raw | -0.001 |
Are | -0.001 |
Fox | -0.001 |
We | -0.001 |
Token | eros |
Token ID | 27498 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
AAAA | +0.153 |
Are | +0.146 |
Raw | +0.146 |
We | +0.130 |
Fox | +0.128 |
Neg logit contributions | |
oll | -0.293 |
ier | -0.293 |
aney | -0.271 |
contain | -0.259 |
ige | -0.258 |
Token | ! |
Token ID | 0 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Fox | +0.054 |
We | +0.052 |
Are | +0.051 |
AAAA | +0.048 |
Come | +0.048 |
Neg logit contributions | |
oll | -0.080 |
ier | -0.077 |
aney | -0.076 |
contain | -0.071 |
ige | -0.071 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
AAAA | +0.023 |
Raw | +0.023 |
Are | +0.020 |
situations | +0.019 |
things | +0.019 |
Neg logit contributions | |
oll | -0.049 |
aney | -0.047 |
ier | -0.046 |
ver | -0.045 |
ax | -0.045 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
oll | +0.026 |
he | +0.026 |
ier | +0.025 |
aney | +0.025 |
ill | +0.024 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.013 |
Sorry | -0.012 |
Are | -0.012 |
situations | -0.012 |
Token | there |
Token ID | 612 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
oll | +0.071 |
ier | +0.070 |
ige | +0.067 |
contain | +0.066 |
aces | +0.065 |
Neg logit contributions | |
We | -0.035 |
things | -0.034 |
Are | -0.034 |
cave | -0.034 |
Fox | -0.034 |
Token | loudly |
Token ID | 23112 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
AAAA | +0.075 |
Raw | +0.072 |
Are | +0.072 |
Fox | +0.068 |
We | +0.068 |
Neg logit contributions | |
oll | -0.076 |
ier | -0.076 |
aney | -0.069 |
contain | -0.068 |
ax | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
AAAA | +0.036 |
Raw | +0.035 |
Are | +0.035 |
Fox | +0.034 |
We | +0.033 |
Neg logit contributions | |
oll | -0.040 |
ier | -0.039 |
aney | -0.038 |
contain | -0.036 |
ver | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
oll | +0.016 |
ver | +0.015 |
about | +0.014 |
oured | +0.014 |
ax | +0.014 |
Neg logit contributions | |
AAAA | -0.013 |
situations | -0.012 |
keeping | -0.012 |
Raw | -0.011 |
Sorry | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
AAAA | +0.010 |
Raw | +0.009 |
Sorry | +0.009 |
situations | +0.009 |
Are | +0.009 |
Neg logit contributions | |
aney | -0.014 |
ver | -0.014 |
oll | -0.014 |
he | -0.014 |
ill | -0.013 |
Token | Near |
Token ID | 40640 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
Sorry | +0.009 |
situations | +0.009 |
AAAA | +0.009 |
keeping | +0.009 |
packages | +0.009 |
Neg logit contributions | |
oll | -0.012 |
aney | -0.012 |
ver | -0.012 |
ier | -0.012 |
contain | -0.011 |
Token | by |
Token ID | 1525 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
oll | +0.006 |
ier | +0.006 |
aney | +0.005 |
contain | +0.005 |
ax | +0.005 |
Neg logit contributions | |
AAAA | -0.004 |
Raw | -0.004 |
Are | -0.004 |
Fox | -0.004 |
We | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
Raw | +0.227 |
AAAA | +0.223 |
Are | +0.220 |
Look | +0.217 |
Sorry | +0.216 |
Neg logit contributions | |
oll | -0.182 |
aney | -0.159 |
ier | -0.157 |
ver | -0.147 |
ill | -0.140 |
Token | he |
Token ID | 339 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ier | +0.006 |
ver | +0.006 |
oll | +0.006 |
contain | +0.006 |
aney | +0.005 |
Neg logit contributions | |
Raw | -0.006 |
AAAA | -0.006 |
situations | -0.006 |
keeping | -0.006 |
We | -0.006 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
oll | +0.018 |
ier | +0.017 |
aney | +0.017 |
contain | +0.016 |
ver | +0.015 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Are | -0.012 |
Fox | -0.012 |
We | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
AAAA | +0.023 |
Raw | +0.022 |
Are | +0.022 |
We | +0.021 |
Fox | +0.021 |
Neg logit contributions | |
oll | -0.031 |
ier | -0.030 |
aney | -0.028 |
contain | -0.027 |
ax | -0.026 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
keeping | +0.004 |
ASH | +0.003 |
Come | +0.003 |
situations | +0.003 |
AAAA | +0.003 |
Neg logit contributions | |
contain | -0.003 |
isy | -0.003 |
oll | -0.003 |
ier | -0.003 |
aney | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
oll | +0.021 |
ier | +0.020 |
aney | +0.020 |
contain | +0.019 |
ax | +0.019 |
Neg logit contributions | |
AAAA | -0.012 |
Raw | -0.012 |
Are | -0.011 |
Fox | -0.010 |
situations | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Look | +0.023 |
Are | +0.023 |
Fox | +0.023 |
AAAA | +0.022 |
cave | +0.022 |
Neg logit contributions | |
oll | -0.043 |
ier | -0.042 |
contain | -0.040 |
aney | -0.040 |
ilies | -0.039 |
Token | who |
Token ID | 508 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
AAAA | +0.019 |
Are | +0.019 |
Raw | +0.018 |
Fox | +0.018 |
We | +0.017 |
Neg logit contributions | |
oll | -0.023 |
ier | -0.023 |
aney | -0.022 |
contain | -0.021 |
ver | -0.020 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
AAAA | +0.081 |
Raw | +0.078 |
Are | +0.075 |
Fox | +0.074 |
Come | +0.074 |
Neg logit contributions | |
oll | -0.056 |
ier | -0.051 |
aney | -0.045 |
he | -0.045 |
ver | -0.044 |
Token | sa |
Token ID | 473 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
oll | +0.002 |
salon | +0.002 |
ier | +0.002 |
contain | +0.002 |
ax | +0.002 |
Neg logit contributions | |
AAAA | -0.004 |
Are | -0.004 |
Raw | -0.003 |
inct | -0.003 |
oc | -0.003 |
Token | us |
Token ID | 385 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
AAAA | +0.044 |
Raw | +0.042 |
Are | +0.042 |
Fox | +0.039 |
We | +0.038 |
Neg logit contributions | |
oll | -0.074 |
ier | -0.074 |
aney | -0.070 |
contain | -0.067 |
ver | -0.065 |
Token | ages |
Token ID | 1095 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
AAAA | +0.152 |
Raw | +0.145 |
Are | +0.142 |
Look | +0.129 |
Fox | +0.125 |
Neg logit contributions | |
oll | -0.274 |
ier | -0.268 |
aney | -0.255 |
contain | -0.247 |
ax | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
things | +0.049 |
Fox | +0.044 |
cave | +0.040 |
We | +0.040 |
packages | +0.039 |
Neg logit contributions | |
aney | -0.119 |
oll | -0.108 |
ill | -0.107 |
ige | -0.105 |
ier | -0.105 |
Token | He |
Token ID | 679 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
oll | +0.021 |
aney | +0.020 |
ier | +0.020 |
contain | +0.019 |
ax | +0.019 |
Neg logit contributions | |
AAAA | -0.010 |
Raw | -0.009 |
Are | -0.008 |
Peter | -0.008 |
Fox | -0.008 |
Token | always |
Token ID | 1464 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ier | +0.005 |
oll | +0.005 |
aney | +0.004 |
contain | +0.004 |
ax | +0.004 |
Neg logit contributions | |
AAAA | -0.004 |
Raw | -0.004 |
Are | -0.004 |
Fox | -0.004 |
We | -0.004 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
AAAA | +0.021 |
Raw | +0.020 |
Are | +0.020 |
Fox | +0.019 |
We | +0.019 |
Neg logit contributions | |
oll | -0.020 |
ier | -0.020 |
aney | -0.019 |
contain | -0.018 |
ver | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Are | +0.017 |
AAAA | +0.017 |
Raw | +0.016 |
Fox | +0.016 |
We | +0.016 |
Neg logit contributions | |
ier | -0.028 |
oll | -0.028 |
aney | -0.026 |
contain | -0.025 |
aces | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ier | +0.030 |
oll | +0.030 |
aney | +0.028 |
contain | +0.027 |
ax | +0.026 |
Neg logit contributions | |
AAAA | -0.031 |
Raw | -0.031 |
Are | -0.030 |
Ar | -0.028 |
Fox | -0.028 |
Token | have |
Token ID | 423 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
oll | +0.018 |
ier | +0.018 |
aney | +0.017 |
contain | +0.016 |
ver | +0.016 |
Neg logit contributions | |
AAAA | -0.011 |
Are | -0.010 |
Raw | -0.010 |
Fox | -0.010 |
We | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
AAAA | +0.023 |
Raw | +0.023 |
Are | +0.023 |
Fox | +0.022 |
We | +0.021 |
Neg logit contributions | |
oll | -0.028 |
ier | -0.028 |
aney | -0.026 |
contain | -0.025 |
ax | -0.024 |
Token | av |
Token ID | 1196 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
things | +0.004 |
Fox | +0.004 |
We | +0.004 |
Are | +0.004 |
AAAA | +0.004 |
Neg logit contributions | |
oll | -0.006 |
ier | -0.006 |
aney | -0.006 |
contain | -0.006 |
ax | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
oll | +0.138 |
ier | +0.137 |
aney | +0.133 |
contain | +0.129 |
ver | +0.126 |
Neg logit contributions | |
AAAA | -0.016 |
Raw | -0.014 |
Are | -0.014 |
Fox | -0.011 |
We | -0.009 |
Token | ados |
Token ID | 22484 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
AAAA | +0.149 |
Are | +0.142 |
Raw | +0.142 |
We | +0.127 |
Fox | +0.127 |
Neg logit contributions | |
oll | -0.290 |
ier | -0.289 |
aney | -0.270 |
contain | -0.258 |
ige | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
things | +0.010 |
Fox | +0.010 |
cave | +0.009 |
places | +0.008 |
packages | +0.008 |
Neg logit contributions | |
aney | -0.030 |
oll | -0.029 |
lated | -0.028 |
obb | -0.028 |
fourteen | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
oll | +0.008 |
ier | +0.008 |
aney | +0.008 |
contain | +0.007 |
ax | +0.007 |
Neg logit contributions | |
AAAA | -0.006 |
Raw | -0.005 |
Are | -0.005 |
Fox | -0.005 |
Peter | -0.005 |
Token | thanked |
Token ID | 26280 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ier | +0.035 |
oll | +0.034 |
aney | +0.032 |
contain | +0.031 |
ver | +0.030 |
Neg logit contributions | |
AAAA | -0.030 |
Raw | -0.029 |
Are | -0.029 |
Fox | -0.028 |
We | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
oll | +0.022 |
ier | +0.022 |
aney | +0.021 |
contain | +0.020 |
ver | +0.019 |
Neg logit contributions | |
AAAA | -0.016 |
Raw | -0.016 |
Are | -0.016 |
Fox | -0.015 |
We | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
oll | +0.147 |
ier | +0.146 |
aney | +0.141 |
contain | +0.137 |
ax | +0.132 |
Neg logit contributions | |
Are | -0.067 |
AAAA | -0.064 |
Fox | -0.064 |
Raw | -0.064 |
We | -0.062 |
Token | would |
Token ID | 561 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
AAAA | +0.019 |
Fox | +0.019 |
Raw | +0.019 |
Are | +0.019 |
We | +0.018 |
Neg logit contributions | |
oll | -0.041 |
aney | -0.041 |
ier | -0.040 |
contain | -0.038 |
ax | -0.038 |
Token | spark |
Token ID | 9009 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
oll | +0.069 |
ier | +0.064 |
aney | +0.063 |
ax | +0.059 |
ver | +0.059 |
Neg logit contributions | |
Raw | -0.033 |
Are | -0.033 |
Fox | -0.032 |
We | -0.032 |
AAAA | -0.031 |
Token | le |
Token ID | 293 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
oll | +0.042 |
aney | +0.040 |
contain | +0.038 |
ier | +0.038 |
ver | +0.035 |
Neg logit contributions | |
AAAA | -0.057 |
Are | -0.056 |
things | -0.055 |
Fox | -0.054 |
We | -0.054 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Fox | +0.045 |
We | +0.045 |
Are | +0.044 |
things | +0.044 |
AAAA | +0.044 |
Neg logit contributions | |
oll | -0.080 |
ier | -0.075 |
aney | -0.074 |
ige | -0.070 |
ax | -0.070 |
Token | more |
Token ID | 3549 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
We | +0.092 |
Are | +0.091 |
Fox | +0.091 |
AAAA | +0.089 |
things | +0.088 |
Neg logit contributions | |
oll | -0.169 |
aney | -0.157 |
ier | -0.154 |
contain | -0.146 |
ver | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
We | +0.149 |
Fox | +0.145 |
AAAA | +0.144 |
Are | +0.143 |
things | +0.141 |
Neg logit contributions | |
oll | -0.267 |
ier | -0.248 |
aney | -0.245 |
contain | -0.238 |
ax | -0.233 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
oll | +0.019 |
aney | +0.018 |
ier | +0.018 |
contain | +0.017 |
ver | +0.017 |
Neg logit contributions | |
AAAA | -0.009 |
Raw | -0.009 |
Are | -0.008 |
Fox | -0.008 |
Ar | -0.008 |
Token | Michael |
Token ID | 13256 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
oll | +0.025 |
he | +0.024 |
ier | +0.024 |
aney | +0.024 |
ver | +0.023 |
Neg logit contributions | |
AAAA | -0.013 |
Raw | -0.012 |
Are | -0.012 |
Sorry | -0.012 |
situations | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ier | +0.023 |
oll | +0.023 |
aney | +0.022 |
contain | +0.021 |
ver | +0.020 |
Neg logit contributions | |
AAAA | -0.014 |
Are | -0.014 |
Raw | -0.013 |
Fox | -0.013 |
We | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
Are | +0.005 |
AAAA | +0.005 |
Raw | +0.005 |
Fox | +0.005 |
Look | +0.004 |
Neg logit contributions | |
ier | -0.009 |
oll | -0.009 |
aney | -0.009 |
contain | -0.008 |
ver | -0.008 |