Token | came |
Token ID | 1625 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
P | +0.012 |
best | +0.011 |
joy | +0.011 |
rob | +0.011 |
robat | +0.011 |
Neg logit contributions | |
plets | -0.012 |
runway | -0.012 |
ramids | -0.012 |
ifying | -0.012 |
umes | -0.011 |
Token | back |
Token ID | 736 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
P | +0.022 |
best | +0.021 |
joy | +0.019 |
my | +0.019 |
seeker | +0.018 |
Neg logit contributions | |
plets | -0.030 |
runway | -0.029 |
ramids | -0.028 |
mic | -0.028 |
umes | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
P | +0.018 |
best | +0.015 |
joy | +0.015 |
rob | +0.015 |
robat | +0.015 |
Neg logit contributions | |
plets | -0.023 |
runway | -0.023 |
ramids | -0.023 |
ifying | -0.022 |
umes | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
plets | +0.006 |
runway | +0.006 |
ramids | +0.006 |
ifying | +0.006 |
umes | +0.005 |
Neg logit contributions | |
P | -0.004 |
joy | -0.003 |
best | -0.003 |
rob | -0.003 |
seeker | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
P | +0.005 |
best | +0.005 |
rob | +0.005 |
robat | +0.005 |
joy | +0.005 |
Neg logit contributions | |
plets | -0.005 |
ramids | -0.005 |
runway | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | THE |
Token ID | 10970 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
joy | +0.002 |
rob | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.002 |
runway | -0.002 |
ramids | -0.002 |
ifying | -0.002 |
umes | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
ifying | +0.225 |
plets | +0.225 |
runway | +0.219 |
umes | +0.219 |
ramids | +0.218 |
Neg logit contributions | |
P | -0.083 |
best | -0.075 |
rob | -0.072 |
seeker | -0.070 |
joy | -0.068 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
P | +0.008 |
Deal | +0.008 |
best | +0.008 |
seeker | +0.008 |
moderation | +0.008 |
Neg logit contributions | |
plets | -0.012 |
ifying | -0.011 |
ramids | -0.011 |
runway | -0.010 |
umes | -0.010 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
plets | +0.019 |
ramids | +0.019 |
runway | +0.019 |
ifying | +0.019 |
umes | +0.018 |
Neg logit contributions | |
P | -0.013 |
rob | -0.012 |
robat | -0.011 |
seeker | -0.011 |
best | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
plets | +0.040 |
runway | +0.039 |
ramids | +0.039 |
ifying | +0.038 |
umes | +0.037 |
Neg logit contributions | |
P | -0.035 |
rob | -0.030 |
best | -0.030 |
joy | -0.030 |
robat | -0.030 |
Token | time |
Token ID | 640 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
rob | +0.011 |
robat | +0.010 |
joy | +0.010 |
ests | +0.010 |
seeker | +0.010 |
Neg logit contributions | |
runway | -0.011 |
ifying | -0.010 |
plets | -0.010 |
cum | -0.010 |
inated | -0.010 |
Token | again |
Token ID | 757 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
P | +0.023 |
moderation | +0.021 |
Deal | +0.021 |
rob | +0.020 |
joy | +0.020 |
Neg logit contributions | |
runway | -0.019 |
uring | -0.019 |
plets | -0.019 |
ured | -0.019 |
ramids | -0.018 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +4.54e-03 |
Pos logit contributions | |
P | +0.022 |
rob | +0.019 |
robat | +0.019 |
Deal | +0.018 |
joy | +0.018 |
Neg logit contributions | |
runway | -0.022 |
plets | -0.021 |
ifying | -0.021 |
ramids | -0.021 |
uring | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -4.58e-04 |
Pos logit contributions | |
plets | +0.008 |
runway | +0.008 |
ramids | +0.008 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.006 |
rob | -0.005 |
best | -0.005 |
robat | -0.005 |
joy | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -5.16e-04 |
Pos logit contributions | |
P | +0.001 |
joy | +0.000 |
best | +0.000 |
rob | +0.000 |
robat | +0.000 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
umes | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e-04 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
rob | +0.001 |
joy | +0.001 |
robat | +0.001 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
umes | -0.001 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
P | +0.000 |
best | +0.000 |
robat | +0.000 |
joy | +0.000 |
rob | +0.000 |
Neg logit contributions | |
plets | -0.000 |
ramids | -0.000 |
runway | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.57e-03 |
Pos logit contributions | |
plets | +0.210 |
ifying | +0.210 |
runway | +0.205 |
ramids | +0.204 |
umes | +0.204 |
Neg logit contributions | |
P | -0.097 |
best | -0.087 |
rob | -0.087 |
robat | -0.083 |
seeker | -0.080 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
P | +0.008 |
Deal | +0.008 |
best | +0.008 |
seeker | +0.008 |
moderation | +0.008 |
Neg logit contributions | |
plets | -0.011 |
ifying | -0.011 |
ramids | -0.010 |
runway | -0.010 |
umes | -0.009 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ramids | +0.017 |
plets | +0.017 |
runway | +0.017 |
ifying | +0.017 |
umes | +0.016 |
Neg logit contributions | |
P | -0.014 |
rob | -0.012 |
robat | -0.012 |
Deal | -0.012 |
moderation | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
plets | +0.038 |
runway | +0.037 |
ramids | +0.037 |
ifying | +0.036 |
umes | +0.035 |
Neg logit contributions | |
P | -0.033 |
best | -0.028 |
rob | -0.028 |
joy | -0.028 |
robat | -0.028 |
Token | time |
Token ID | 640 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
rob | +0.012 |
robat | +0.011 |
ests | +0.011 |
joy | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
ifying | -0.011 |
runway | -0.011 |
plets | -0.011 |
cum | -0.011 |
inated | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
plets | +0.018 |
ramids | +0.017 |
runway | +0.017 |
ifying | +0.017 |
umes | +0.016 |
Neg logit contributions | |
P | -0.014 |
best | -0.014 |
joy | -0.013 |
my | -0.013 |
seeker | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
plets | +0.028 |
ramids | +0.028 |
runway | +0.028 |
ifying | +0.026 |
umes | +0.026 |
Neg logit contributions | |
P | -0.019 |
best | -0.018 |
joy | -0.016 |
my | -0.015 |
moderation | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
plets | +0.025 |
ramids | +0.024 |
runway | +0.024 |
ifying | +0.024 |
umes | +0.023 |
Neg logit contributions | |
P | -0.020 |
best | -0.018 |
joy | -0.018 |
rob | -0.017 |
robat | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
P | +0.002 |
best | +0.001 |
joy | +0.001 |
rob | +0.001 |
robat | +0.001 |
Neg logit contributions | |
plets | -0.002 |
runway | -0.002 |
ramids | -0.002 |
ifying | -0.002 |
umes | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
plets | +0.007 |
runway | +0.007 |
ramids | +0.007 |
ifying | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.006 |
best | -0.005 |
joy | -0.005 |
rob | -0.005 |
robat | -0.005 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.005 |
runway | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.006 |
best | -0.005 |
rob | -0.005 |
robat | -0.005 |
joy | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.88e-04 |
Pos logit contributions | |
plets | +0.230 |
ifying | +0.227 |
umes | +0.218 |
ramids | +0.215 |
lights | +0.214 |
Neg logit contributions | |
P | -0.079 |
best | -0.072 |
rob | -0.069 |
joy | -0.064 |
robat | -0.064 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
P | +0.001 |
Deal | +0.001 |
best | +0.001 |
moderation | +0.001 |
seeker | +0.001 |
Neg logit contributions | |
plets | -0.001 |
ifying | -0.001 |
ramids | -0.001 |
runway | -0.001 |
umes | -0.001 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
runway | +0.014 |
ramids | +0.014 |
plets | +0.014 |
ifying | +0.014 |
umes | +0.013 |
Neg logit contributions | |
P | -0.012 |
rob | -0.011 |
robat | -0.010 |
Deal | -0.010 |
moderation | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
plets | +0.037 |
runway | +0.037 |
ramids | +0.036 |
ifying | +0.035 |
umes | +0.035 |
Neg logit contributions | |
P | -0.031 |
best | -0.026 |
rob | -0.026 |
joy | -0.026 |
robat | -0.026 |
Token | time |
Token ID | 640 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
rob | +0.019 |
robat | +0.018 |
ests | +0.017 |
P | +0.017 |
seeker | +0.016 |
Neg logit contributions | |
ifying | -0.019 |
runway | -0.019 |
inated | -0.018 |
cum | -0.018 |
mic | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
P | +0.046 |
rob | +0.040 |
joy | +0.040 |
best | +0.040 |
robat | +0.040 |
Neg logit contributions | |
plets | -0.042 |
runway | -0.041 |
ramids | -0.041 |
ifying | -0.040 |
umes | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
ramids | +0.011 |
plets | +0.011 |
runway | +0.010 |
ifying | +0.010 |
umes | +0.010 |
Neg logit contributions | |
P | -0.006 |
best | -0.006 |
my | -0.005 |
joy | -0.005 |
moderation | -0.005 |
Token | |
Token ID | 220 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
P | +0.011 |
rob | +0.009 |
robat | +0.009 |
seeker | +0.009 |
best | +0.009 |
Neg logit contributions | |
ramids | -0.016 |
plets | -0.016 |
ifying | -0.015 |
runway | -0.015 |
umes | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
P | +0.004 |
best | +0.003 |
joy | +0.003 |
rob | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.008 |
runway | -0.008 |
ramids | -0.008 |
ifying | -0.008 |
umes | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +8.70e-04 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
seeker | +0.002 |
rob | +0.002 |
joy | +0.002 |
Neg logit contributions | |
plets | -0.002 |
ramids | -0.002 |
runway | -0.002 |
ifying | -0.002 |
umes | -0.002 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
plets | +0.001 |
runway | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.002 |
best | -0.001 |
joy | -0.001 |
rob | -0.001 |
robat | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
plets | +0.215 |
ifying | +0.210 |
runway | +0.208 |
ramids | +0.207 |
umes | +0.206 |
Neg logit contributions | |
P | -0.091 |
best | -0.079 |
rob | -0.078 |
joy | -0.076 |
robat | -0.075 |
Token | T |
Token ID | 51 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
P | +0.004 |
Deal | +0.004 |
best | +0.004 |
seeker | +0.004 |
moderation | +0.003 |
Neg logit contributions | |
plets | -0.005 |
ifying | -0.005 |
ramids | -0.005 |
runway | -0.005 |
umes | -0.004 |
Token | ina |
Token ID | 1437 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ramids | +0.025 |
plets | +0.025 |
runway | +0.025 |
ifying | +0.024 |
umes | +0.023 |
Neg logit contributions | |
P | -0.021 |
best | -0.018 |
seeker | -0.018 |
joy | -0.018 |
rob | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
plets | +0.049 |
ramids | +0.048 |
ifying | +0.047 |
runway | +0.047 |
umes | +0.047 |
Neg logit contributions | |
P | -0.034 |
best | -0.029 |
my | -0.028 |
joy | -0.028 |
rob | -0.028 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
runway | +0.005 |
plets | +0.005 |
ramids | +0.005 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.005 |
rob | -0.004 |
robat | -0.004 |
joy | -0.004 |
Deal | -0.004 |
Token | arm |
Token ID | 3211 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
joy | +0.005 |
robat | +0.005 |
seeker | +0.005 |
Neg logit contributions | |
plets | -0.009 |
ramids | -0.008 |
runway | -0.008 |
ifying | -0.008 |
umes | -0.008 |
Token | chair |
Token ID | 16337 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ramids | +0.040 |
plets | +0.039 |
runway | +0.038 |
ifying | +0.038 |
umes | +0.038 |
Neg logit contributions | |
P | -0.027 |
best | -0.026 |
my | -0.025 |
rob | -0.024 |
robat | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
plets | +0.055 |
ramids | +0.054 |
runway | +0.054 |
ifying | +0.052 |
umes | +0.051 |
Neg logit contributions | |
P | -0.041 |
best | -0.036 |
rob | -0.035 |
joy | -0.035 |
robat | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
P | +0.005 |
joy | +0.004 |
best | +0.004 |
moderation | +0.004 |
my | +0.004 |
Neg logit contributions | |
plets | -0.007 |
runway | -0.007 |
ramids | -0.007 |
ifying | -0.007 |
umes | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
P | +0.008 |
best | +0.007 |
rob | +0.007 |
robat | +0.007 |
joy | +0.007 |
Neg logit contributions | |
plets | -0.012 |
runway | -0.012 |
ramids | -0.012 |
ifying | -0.011 |
umes | -0.011 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
P | +0.005 |
moderation | +0.004 |
joy | +0.004 |
robat | +0.004 |
best | +0.004 |
Neg logit contributions | |
plets | -0.006 |
ramids | -0.005 |
runway | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
plets | +0.199 |
ifying | +0.198 |
ramids | +0.194 |
runway | +0.194 |
umes | +0.193 |
Neg logit contributions | |
P | -0.103 |
best | -0.093 |
rob | -0.092 |
robat | -0.089 |
seeker | -0.088 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
P | +0.008 |
Deal | +0.008 |
best | +0.008 |
seeker | +0.008 |
moderation | +0.007 |
Neg logit contributions | |
plets | -0.011 |
ifying | -0.010 |
ramids | -0.010 |
runway | -0.010 |
umes | -0.009 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
plets | +0.017 |
ramids | +0.017 |
runway | +0.017 |
ifying | +0.017 |
umes | +0.016 |
Neg logit contributions | |
P | -0.012 |
rob | -0.011 |
robat | -0.010 |
best | -0.010 |
joy | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
plets | +0.036 |
runway | +0.035 |
ramids | +0.035 |
ifying | +0.034 |
umes | +0.033 |
Neg logit contributions | |
P | -0.033 |
rob | -0.029 |
joy | -0.029 |
robat | -0.029 |
best | -0.028 |
Token | time |
Token ID | 640 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
rob | +0.009 |
robat | +0.009 |
ests | +0.008 |
joy | +0.008 |
seeker | +0.008 |
Neg logit contributions | |
runway | -0.009 |
ifying | -0.009 |
plets | -0.009 |
cum | -0.008 |
keys | -0.008 |
Token | available |
Token ID | 1695 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
P | +0.043 |
best | +0.042 |
joy | +0.039 |
seeker | +0.037 |
my | +0.037 |
Neg logit contributions | |
plets | -0.056 |
ramids | -0.054 |
runway | -0.053 |
ifying | -0.051 |
umes | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
P | +0.019 |
best | +0.016 |
joy | +0.016 |
rob | +0.016 |
robat | +0.015 |
Neg logit contributions | |
plets | -0.025 |
runway | -0.024 |
ramids | -0.024 |
ifying | -0.023 |
umes | -0.023 |
Token | |
Token ID | 220 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
P | +0.007 |
best | +0.006 |
joy | +0.006 |
rob | +0.006 |
robat | +0.006 |
Neg logit contributions | |
plets | -0.012 |
runway | -0.012 |
ramids | -0.012 |
ifying | -0.011 |
umes | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.002 |
joy | +0.002 |
rob | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.006 |
ramids | -0.006 |
ifying | -0.006 |
ured | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.22e-05 |
Pos logit contributions | |
P | +0.004 |
seeker | +0.004 |
best | +0.004 |
joy | +0.004 |
rob | +0.004 |
Neg logit contributions | |
ramids | -0.005 |
plets | -0.005 |
runway | -0.005 |
umes | -0.005 |
uring | -0.005 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
P | +0.000 |
best | +0.000 |
joy | +0.000 |
robat | +0.000 |
rob | +0.000 |
Neg logit contributions | |
plets | -0.000 |
ramids | -0.000 |
runway | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.80e-03 |
Pos logit contributions | |
plets | +0.220 |
ifying | +0.218 |
runway | +0.214 |
ramids | +0.212 |
umes | +0.211 |
Neg logit contributions | |
P | -0.080 |
best | -0.071 |
rob | -0.069 |
robat | -0.066 |
seeker | -0.065 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
P | +0.006 |
Deal | +0.006 |
best | +0.006 |
seeker | +0.006 |
moderation | +0.006 |
Neg logit contributions | |
plets | -0.008 |
ifying | -0.008 |
ramids | -0.008 |
runway | -0.007 |
umes | -0.007 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
plets | +0.014 |
ramids | +0.014 |
runway | +0.014 |
ifying | +0.014 |
umes | +0.013 |
Neg logit contributions | |
P | -0.010 |
rob | -0.009 |
robat | -0.008 |
joy | -0.008 |
seeker | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -9.50e-03 |
Pos logit contributions | |
plets | +0.035 |
runway | +0.035 |
ramids | +0.034 |
ifying | +0.034 |
umes | +0.032 |
Neg logit contributions | |
P | -0.033 |
rob | -0.029 |
robat | -0.029 |
joy | -0.029 |
best | -0.029 |
Token | time |
Token ID | 640 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
rob | +0.015 |
robat | +0.014 |
ests | +0.013 |
seeker | +0.013 |
joy | +0.013 |
Neg logit contributions | |
ifying | -0.012 |
cum | -0.012 |
inated | -0.012 |
runway | -0.012 |
plets | -0.012 |
Token | delicious |
Token ID | 12625 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.003 |
moderation | +0.003 |
joy | +0.003 |
my | +0.003 |
Neg logit contributions | |
runway | -0.004 |
plets | -0.004 |
ramids | -0.004 |
umes | -0.004 |
mic | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.005 |
ifying | +0.005 |
runway | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.005 |
rob | -0.004 |
seeker | -0.004 |
robat | -0.004 |
joy | -0.004 |
Token | |
Token ID | 220 |
Feature activation | -7.95e-04 |
Pos logit contributions | |
P | +0.002 |
my | +0.002 |
joy | +0.002 |
best | +0.002 |
ossible | +0.002 |
Neg logit contributions | |
runway | -0.004 |
plets | -0.003 |
mic | -0.003 |
ured | -0.003 |
uring | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
joy | +0.000 |
my | +0.000 |
rob | +0.000 |
Neg logit contributions | |
runway | -0.002 |
plets | -0.002 |
ramids | -0.002 |
ifying | -0.002 |
ured | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
runway | +0.009 |
plets | +0.009 |
ramids | +0.009 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.003 |
rob | -0.002 |
best | -0.002 |
robat | -0.002 |
my | -0.002 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.009 |
runway | +0.009 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.008 |
Deal | -0.006 |
my | -0.006 |
robat | -0.005 |
best | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.04e-03 |
Pos logit contributions | |
ifying | +0.231 |
plets | +0.229 |
runway | +0.225 |
umes | +0.221 |
ramids | +0.220 |
Neg logit contributions | |
P | -0.061 |
best | -0.055 |
rob | -0.052 |
joy | -0.052 |
Deal | -0.051 |
Token | Elsa |
Token ID | 49050 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
P | +0.001 |
Deal | +0.001 |
moderation | +0.001 |
best | +0.001 |
seeker | +0.001 |
Neg logit contributions | |
plets | -0.002 |
ifying | -0.002 |
ramids | -0.002 |
runway | -0.001 |
umes | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
plets | +0.030 |
runway | +0.029 |
ramids | +0.029 |
ifying | +0.029 |
umes | +0.028 |
Neg logit contributions | |
P | -0.020 |
best | -0.016 |
joy | -0.016 |
rob | -0.016 |
robat | -0.016 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
plets | +0.006 |
runway | +0.006 |
ramids | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.005 |
rob | -0.004 |
robat | -0.004 |
joy | -0.004 |
best | -0.004 |
Token | chess |
Token ID | 19780 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
rob | +0.019 |
P | +0.019 |
joy | +0.019 |
robat | +0.019 |
moderation | +0.018 |
Neg logit contributions | |
runway | -0.012 |
uring | -0.011 |
ured | -0.011 |
inated | -0.011 |
plets | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
plets | +0.010 |
runway | +0.010 |
ramids | +0.010 |
ifying | +0.010 |
umes | +0.009 |
Neg logit contributions | |
P | -0.010 |
robat | -0.009 |
rob | -0.009 |
joy | -0.009 |
best | -0.009 |
Token | brave |
Token ID | 14802 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
runway | +0.006 |
plets | +0.006 |
ramids | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.006 |
rob | -0.006 |
robat | -0.006 |
joy | -0.005 |
moderation | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
P | +0.005 |
rob | +0.004 |
moderation | +0.004 |
robat | +0.004 |
best | +0.004 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.006 |
ramids | -0.006 |
ifying | -0.005 |
umes | -0.005 |
Token | named |
Token ID | 3706 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
plets | +0.014 |
ramids | +0.013 |
runway | +0.013 |
ifying | +0.013 |
mic | +0.013 |
Neg logit contributions | |
P | -0.012 |
best | -0.010 |
my | -0.010 |
seeker | -0.010 |
joy | -0.010 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
plets | +0.031 |
runway | +0.030 |
ramids | +0.030 |
ifying | +0.029 |
umes | +0.029 |
Neg logit contributions | |
P | -0.025 |
best | -0.021 |
joy | -0.021 |
rob | -0.021 |
seeker | -0.020 |
Token | icia |
Token ID | 33577 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
P | +0.015 |
best | +0.013 |
my | +0.012 |
rob | +0.012 |
robat | +0.011 |
Neg logit contributions | |
plets | -0.024 |
ifying | -0.024 |
ramids | -0.024 |
runway | -0.023 |
umes | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
plets | +0.219 |
ramids | +0.203 |
runway | +0.198 |
ifying | +0.197 |
umes | +0.194 |
Neg logit contributions | |
P | -0.098 |
best | -0.089 |
my | -0.080 |
seeker | -0.078 |
ossible | -0.076 |
Token | She |
Token ID | 1375 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
plets | +0.020 |
runway | +0.020 |
ramids | +0.020 |
ifying | +0.019 |
umes | +0.019 |
Neg logit contributions | |
P | -0.016 |
best | -0.014 |
joy | -0.014 |
seeker | -0.013 |
rob | -0.013 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
plets | +0.045 |
ifying | +0.044 |
ramids | +0.044 |
umes | +0.043 |
runway | +0.042 |
Neg logit contributions | |
P | -0.036 |
best | -0.031 |
rob | -0.029 |
seeker | -0.029 |
my | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
uring | +0.018 |
umes | +0.018 |
runway | +0.018 |
capt | +0.017 |
through | +0.017 |
Neg logit contributions | |
rob | -0.047 |
robat | -0.046 |
ah | -0.044 |
moderation | -0.042 |
P | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
plets | +0.046 |
ramids | +0.045 |
ifying | +0.044 |
runway | +0.044 |
umes | +0.044 |
Neg logit contributions | |
P | -0.029 |
best | -0.025 |
rob | -0.024 |
seeker | -0.023 |
moderation | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
P | +0.000 |
best | +0.000 |
joy | +0.000 |
moderation | +0.000 |
rob | +0.000 |
Neg logit contributions | |
plets | -0.000 |
ramids | -0.000 |
runway | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
plets | +0.040 |
ramids | +0.039 |
runway | +0.039 |
ifying | +0.038 |
umes | +0.038 |
Neg logit contributions | |
P | -0.025 |
best | -0.022 |
joy | -0.022 |
robat | -0.020 |
rob | -0.020 |
Token | |
Token ID | 220 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
P | +0.007 |
best | +0.006 |
joy | +0.006 |
rob | +0.006 |
robat | +0.006 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.012 |
umes | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-04 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
joy | +0.001 |
rob | +0.001 |
robat | +0.001 |
Neg logit contributions | |
plets | -0.003 |
runway | -0.003 |
ramids | -0.003 |
ifying | -0.003 |
umes | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
plets | +0.000 |
runway | +0.000 |
ramids | +0.000 |
umes | +0.000 |
ifying | +0.000 |
Neg logit contributions | |
P | -0.000 |
seeker | -0.000 |
joy | -0.000 |
best | -0.000 |
robat | -0.000 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
plets | +0.002 |
ramids | +0.002 |
runway | +0.002 |
ifying | +0.002 |
umes | +0.002 |
Neg logit contributions | |
P | -0.003 |
best | -0.003 |
rob | -0.003 |
robat | -0.003 |
joy | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
plets | +0.224 |
ifying | +0.221 |
umes | +0.216 |
ramids | +0.215 |
runway | +0.214 |
Neg logit contributions | |
P | -0.067 |
best | -0.065 |
rob | -0.059 |
joy | -0.058 |
Deal | -0.056 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.86e-03 |
Pos logit contributions | |
P | +0.006 |
Deal | +0.006 |
seeker | +0.005 |
best | +0.005 |
moderation | +0.005 |
Neg logit contributions | |
plets | -0.006 |
ifying | -0.006 |
ramids | -0.006 |
runway | -0.006 |
umes | -0.005 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ramids | +0.010 |
runway | +0.010 |
plets | +0.010 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.009 |
rob | -0.008 |
robat | -0.007 |
Deal | -0.007 |
moderation | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
plets | +0.035 |
runway | +0.034 |
ramids | +0.034 |
ifying | +0.033 |
umes | +0.033 |
Neg logit contributions | |
P | -0.031 |
rob | -0.027 |
robat | -0.027 |
joy | -0.027 |
best | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
rob | +0.021 |
robat | +0.019 |
ests | +0.018 |
P | +0.018 |
seeker | +0.018 |
Neg logit contributions | |
ifying | -0.019 |
runway | -0.019 |
inated | -0.018 |
cum | -0.018 |
mic | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
P | +0.011 |
best | +0.010 |
joy | +0.009 |
robat | +0.009 |
my | +0.009 |
Neg logit contributions | |
plets | -0.019 |
runway | -0.018 |
ramids | -0.018 |
ifying | -0.018 |
umes | -0.017 |
Token | One |
Token ID | 1881 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
plets | +0.007 |
runway | +0.007 |
ifying | +0.007 |
ramids | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.007 |
joy | -0.006 |
best | -0.006 |
moderation | -0.006 |
seeker | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
P | +0.031 |
best | +0.023 |
rob | +0.021 |
joy | +0.021 |
robat | +0.021 |
Neg logit contributions | |
plets | -0.106 |
ramids | -0.104 |
runway | -0.104 |
ifying | -0.102 |
umes | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -9.07e-04 |
Pos logit contributions | |
runway | +0.048 |
plets | +0.046 |
mic | +0.046 |
ramids | +0.045 |
uring | +0.045 |
Neg logit contributions | |
P | -0.012 |
best | -0.009 |
seeker | -0.008 |
joy | -0.007 |
my | -0.006 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.64e-04 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
seeker | +0.001 |
joy | +0.001 |
boy | +0.001 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
mic | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
Token | icia |
Token ID | 33577 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
plets | +0.000 |
ifying | +0.000 |
runway | +0.000 |
ramids | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
best | -0.000 |
my | -0.000 |
rob | -0.000 |
moderation | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
plets | +0.190 |
runway | +0.182 |
ramids | +0.179 |
lights | +0.178 |
ifying | +0.175 |
Neg logit contributions | |
P | -0.111 |
best | -0.105 |
seeker | -0.098 |
my | -0.097 |
idea | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
plets | +0.058 |
ramids | +0.056 |
runway | +0.055 |
ifying | +0.054 |
umes | +0.054 |
Neg logit contributions | |
P | -0.034 |
best | -0.029 |
joy | -0.027 |
moderation | -0.026 |
seeker | -0.026 |
Token | big |
Token ID | 1263 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
P | +0.004 |
rob | +0.004 |
robat | +0.004 |
joy | +0.004 |
moderation | +0.003 |
Neg logit contributions | |
runway | -0.005 |
plets | -0.005 |
ramids | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | idea |
Token ID | 2126 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
runway | +0.008 |
cum | +0.007 |
ramids | +0.006 |
mic | +0.006 |
inated | +0.006 |
Neg logit contributions | |
P | -0.008 |
rob | -0.007 |
ests | -0.007 |
joy | -0.007 |
robat | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
robat | +0.005 |
joy | +0.005 |
rob | +0.005 |
Neg logit contributions | |
plets | -0.011 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
umes | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-04 |
Pos logit contributions | |
P | +0.031 |
best | +0.026 |
rob | +0.026 |
joy | +0.026 |
robat | +0.026 |
Neg logit contributions | |
plets | -0.040 |
runway | -0.040 |
ramids | -0.040 |
ifying | -0.039 |
umes | -0.038 |
Token | |
Token ID | 220 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
P | +0.001 |
rob | +0.001 |
robat | +0.001 |
seeker | +0.001 |
best | +0.001 |
Neg logit contributions | |
plets | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
runway | -0.001 |
umes | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.004 |
runway | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.003 |
rob | -0.002 |
best | -0.002 |
robat | -0.002 |
joy | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.004 |
runway | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.005 |
seeker | -0.005 |
joy | -0.005 |
rob | -0.005 |
robat | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
plets | +0.008 |
ramids | +0.007 |
runway | +0.007 |
ifying | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.005 |
rob | -0.004 |
robat | -0.004 |
best | -0.004 |
joy | -0.004 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
plets | +0.008 |
runway | +0.008 |
ramids | +0.008 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.007 |
seeker | -0.007 |
joy | -0.007 |
rob | -0.007 |
robat | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
plets | +0.187 |
runway | +0.184 |
ramids | +0.183 |
ifying | +0.180 |
umes | +0.177 |
Neg logit contributions | |
P | -0.105 |
best | -0.089 |
joy | -0.087 |
rob | -0.087 |
robat | -0.086 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
plets | +0.002 |
ifying | +0.002 |
ramids | +0.002 |
runway | +0.001 |
umes | +0.001 |
Neg logit contributions | |
Deal | -0.002 |
P | -0.001 |
seeker | -0.001 |
moderation | -0.001 |
best | -0.001 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
ramids | +0.017 |
runway | +0.017 |
plets | +0.017 |
ifying | +0.017 |
lights | +0.016 |
Neg logit contributions | |
P | -0.016 |
rob | -0.014 |
robat | -0.014 |
Deal | -0.013 |
seeker | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
plets | +0.036 |
runway | +0.036 |
ramids | +0.035 |
ifying | +0.035 |
umes | +0.034 |
Neg logit contributions | |
P | -0.035 |
rob | -0.031 |
robat | -0.031 |
joy | -0.031 |
best | -0.030 |
Token | time |
Token ID | 640 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
rob | +0.022 |
robat | +0.021 |
P | +0.020 |
seeker | +0.020 |
ests | +0.020 |
Neg logit contributions | |
inated | -0.020 |
ifying | -0.020 |
runway | -0.020 |
cum | -0.020 |
mic | -0.019 |
Token | collecting |
Token ID | 13157 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
runway | +0.001 |
plets | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
rob | -0.001 |
robat | -0.001 |
joy | -0.000 |
seeker | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
P | +0.020 |
rob | +0.018 |
seeker | +0.018 |
robat | +0.018 |
joy | +0.017 |
Neg logit contributions | |
plets | -0.022 |
runway | -0.022 |
ifying | -0.022 |
ramids | -0.022 |
umes | -0.021 |
Token | |
Token ID | 220 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
P | +0.016 |
rob | +0.015 |
robat | +0.014 |
seeker | +0.014 |
best | +0.014 |
Neg logit contributions | |
plets | -0.019 |
ramids | -0.019 |
ifying | -0.019 |
runway | -0.018 |
umes | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
P | +0.005 |
best | +0.004 |
rob | +0.004 |
joy | +0.004 |
robat | +0.004 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
runway | -0.010 |
ifying | -0.009 |
umes | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -9.10e-04 |
Pos logit contributions | |
P | +0.003 |
seeker | +0.003 |
best | +0.003 |
rob | +0.003 |
joy | +0.003 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
umes | -0.004 |
ifying | -0.004 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
P | +0.002 |
best | +0.001 |
rob | +0.001 |
joy | +0.001 |
seeker | +0.001 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
umes | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
plets | +0.204 |
ifying | +0.199 |
runway | +0.198 |
ramids | +0.198 |
umes | +0.194 |
Neg logit contributions | |
P | -0.087 |
best | -0.074 |
joy | -0.071 |
rob | -0.071 |
robat | -0.070 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
Deal | +0.003 |
P | +0.003 |
seeker | +0.003 |
moderation | +0.003 |
best | +0.003 |
Neg logit contributions | |
plets | -0.003 |
ifying | -0.003 |
ramids | -0.003 |
runway | -0.003 |
umes | -0.002 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ramids | +0.014 |
runway | +0.014 |
plets | +0.014 |
ifying | +0.014 |
umes | +0.013 |
Neg logit contributions | |
P | -0.013 |
rob | -0.012 |
robat | -0.012 |
Deal | -0.011 |
moderation | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
plets | +0.036 |
runway | +0.036 |
ramids | +0.035 |
ifying | +0.035 |
umes | +0.034 |
Neg logit contributions | |
P | -0.035 |
rob | -0.031 |
robat | -0.030 |
joy | -0.030 |
best | -0.030 |
Token | time |
Token ID | 640 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
rob | +0.022 |
robat | +0.020 |
ests | +0.019 |
P | +0.019 |
seeker | +0.019 |
Neg logit contributions | |
ifying | -0.017 |
inated | -0.017 |
cum | -0.017 |
mic | -0.016 |
ln | -0.016 |
Token | restless |
Token ID | 42537 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
plets | +0.004 |
runway | +0.004 |
ramids | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.004 |
rob | -0.004 |
best | -0.003 |
joy | -0.003 |
robat | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-04 |
Pos logit contributions | |
plets | +0.064 |
ramids | +0.064 |
runway | +0.062 |
umes | +0.061 |
ifying | +0.060 |
Neg logit contributions | |
P | -0.047 |
joy | -0.044 |
best | -0.044 |
seeker | -0.040 |
robat | -0.040 |
Token | |
Token ID | 220 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
plets | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
runway | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.000 |
seeker | -0.000 |
robat | -0.000 |
rob | -0.000 |
best | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
runway | +0.009 |
plets | +0.009 |
ramids | +0.009 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.004 |
best | -0.003 |
joy | -0.003 |
rob | -0.003 |
robat | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
plets | +0.008 |
ramids | +0.008 |
runway | +0.008 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.006 |
seeker | -0.005 |
joy | -0.005 |
best | -0.005 |
robat | -0.005 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
plets | +0.007 |
runway | +0.007 |
ramids | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.011 |
joy | -0.011 |
seeker | -0.011 |
best | -0.011 |
rob | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
plets | +0.191 |
runway | +0.187 |
ramids | +0.187 |
ifying | +0.184 |
umes | +0.181 |
Neg logit contributions | |
P | -0.099 |
best | -0.083 |
rob | -0.083 |
joy | -0.082 |
robat | -0.081 |
Token | Dad |
Token ID | 46270 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
plets | +0.006 |
ifying | +0.006 |
ramids | +0.006 |
runway | +0.005 |
umes | +0.005 |
Neg logit contributions | |
Deal | -0.005 |
P | -0.005 |
moderation | -0.005 |
seeker | -0.005 |
best | -0.005 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
P | +0.035 |
best | +0.030 |
joy | +0.029 |
rob | +0.029 |
robat | +0.029 |
Neg logit contributions | |
plets | -0.056 |
runway | -0.056 |
ramids | -0.055 |
ifying | -0.054 |
umes | -0.053 |
Token | at |
Token ID | 379 |
Feature activation | -4.16e-04 |
Pos logit contributions | |
P | +0.005 |
best | +0.004 |
joy | +0.004 |
rob | +0.004 |
robat | +0.004 |
Neg logit contributions | |
plets | -0.007 |
runway | -0.007 |
ramids | -0.007 |
ifying | -0.007 |
umes | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
joy | +0.001 |
rob | +0.001 |
robat | +0.001 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
umes | -0.001 |
Token | cloth |
Token ID | 16270 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
plets | +0.015 |
runway | +0.015 |
ramids | +0.014 |
ifying | +0.014 |
umes | +0.014 |
Neg logit contributions | |
P | -0.011 |
rob | -0.010 |
joy | -0.010 |
best | -0.009 |
robat | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
P | +0.004 |
best | +0.003 |
joy | +0.003 |
rob | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.005 |
ramids | -0.005 |
runway | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | wiped |
Token ID | 21122 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ramids | +0.019 |
runway | +0.019 |
plets | +0.019 |
ifying | +0.019 |
uring | +0.018 |
Neg logit contributions | |
P | -0.017 |
best | -0.014 |
my | -0.014 |
rob | -0.014 |
vest | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
plets | +0.020 |
ramids | +0.019 |
runway | +0.019 |
ifying | +0.019 |
umes | +0.018 |
Neg logit contributions | |
P | -0.028 |
best | -0.025 |
joy | -0.025 |
rob | -0.025 |
robat | -0.025 |
Token | dirt |
Token ID | 13647 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
plets | +0.063 |
ramids | +0.062 |
runway | +0.062 |
ifying | +0.060 |
umes | +0.059 |
Neg logit contributions | |
P | -0.053 |
best | -0.046 |
rob | -0.045 |
joy | -0.045 |
robat | -0.045 |
Token | off |
Token ID | 572 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
ramids | +0.063 |
plets | +0.063 |
runway | +0.061 |
ifying | +0.059 |
umes | +0.058 |
Neg logit contributions | |
P | -0.111 |
best | -0.102 |
robat | -0.096 |
rob | -0.095 |
my | -0.095 |
Token | of |
Token ID | 286 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
plets | +0.177 |
ramids | +0.176 |
runway | +0.176 |
keys | +0.174 |
mic | +0.172 |
Neg logit contributions | |
P | -0.107 |
best | -0.099 |
my | -0.091 |
right | -0.088 |
gum | -0.082 |
Token | her |
Token ID | 607 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
plets | +0.087 |
runway | +0.085 |
ramids | +0.085 |
ifying | +0.082 |
umes | +0.081 |
Neg logit contributions | |
P | -0.087 |
best | -0.077 |
moderation | -0.076 |
joy | -0.075 |
rob | -0.075 |
Token | knee |
Token ID | 10329 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
runway | +0.037 |
plets | +0.037 |
ramids | +0.036 |
ifying | +0.035 |
umes | +0.035 |
Neg logit contributions | |
P | -0.031 |
rob | -0.026 |
joy | -0.026 |
robat | -0.026 |
seeker | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
P | +0.005 |
joy | +0.005 |
rob | +0.005 |
robat | +0.004 |
best | +0.004 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.006 |
ramids | -0.006 |
ifying | -0.006 |
umes | -0.006 |
Token | But |
Token ID | 887 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
keys | +0.013 |
runway | +0.012 |
plets | +0.012 |
ifying | +0.012 |
aro | +0.012 |
Neg logit contributions | |
joy | -0.006 |
P | -0.005 |
my | -0.005 |
best | -0.005 |
right | -0.005 |
Token | special |
Token ID | 2041 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
plets | +0.020 |
ramids | +0.020 |
runway | +0.020 |
ifying | +0.019 |
umes | +0.019 |
Neg logit contributions | |
P | -0.014 |
best | -0.012 |
joy | -0.012 |
robat | -0.011 |
rob | -0.011 |
Token | talent |
Token ID | 7401 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
P | +0.018 |
rob | +0.015 |
seeker | +0.015 |
robat | +0.014 |
Deal | +0.014 |
Neg logit contributions | |
runway | -0.020 |
plets | -0.019 |
ramids | -0.019 |
ifying | -0.019 |
mic | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -8.23e-03 |
Pos logit contributions | |
P | +0.031 |
rob | +0.026 |
best | +0.026 |
joy | +0.026 |
robat | +0.026 |
Neg logit contributions | |
plets | -0.041 |
runway | -0.041 |
ramids | -0.041 |
ifying | -0.040 |
umes | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +5.42e-04 |
Pos logit contributions | |
P | +0.008 |
best | +0.007 |
joy | +0.007 |
rob | +0.007 |
robat | +0.006 |
Neg logit contributions | |
plets | -0.018 |
runway | -0.017 |
ramids | -0.017 |
ifying | -0.017 |
umes | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
plets | +0.001 |
runway | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.001 |
rob | -0.001 |
joy | -0.001 |
robat | -0.001 |
Token | THE |
Token ID | 10970 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
plets | +0.006 |
ramids | +0.006 |
runway | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.006 |
best | -0.005 |
robat | -0.005 |
rob | -0.005 |
Deal | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.39e-04 |
Pos logit contributions | |
plets | +0.213 |
ifying | +0.208 |
runway | +0.203 |
ramids | +0.203 |
umes | +0.202 |
Neg logit contributions | |
P | -0.071 |
best | -0.065 |
rob | -0.061 |
joy | -0.061 |
Deal | -0.060 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
Deal | +0.001 |
P | +0.001 |
moderation | +0.001 |
seeker | +0.001 |
best | +0.001 |
Neg logit contributions | |
plets | -0.001 |
ifying | -0.001 |
ramids | -0.001 |
runway | -0.001 |
cum | -0.001 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ramids | +0.018 |
runway | +0.018 |
plets | +0.018 |
ifying | +0.018 |
umes | +0.017 |
Neg logit contributions | |
P | -0.016 |
rob | -0.014 |
robat | -0.014 |
Deal | -0.013 |
moderation | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
plets | +0.040 |
runway | +0.040 |
ramids | +0.039 |
ifying | +0.038 |
umes | +0.037 |
Neg logit contributions | |
P | -0.037 |
rob | -0.032 |
robat | -0.032 |
joy | -0.032 |
best | -0.031 |
Token | time |
Token ID | 640 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
rob | +0.022 |
robat | +0.021 |
P | +0.020 |
ests | +0.019 |
seeker | +0.019 |
Neg logit contributions | |
ifying | -0.018 |
inated | -0.018 |
cum | -0.018 |
mic | -0.018 |
runway | -0.018 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
P | +0.005 |
best | +0.005 |
joy | +0.005 |
rob | +0.004 |
seeker | +0.004 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
best | +0.003 |
P | +0.003 |
my | +0.003 |
robat | +0.002 |
joy | +0.002 |
Neg logit contributions | |
plets | -0.004 |
ifying | -0.004 |
ramids | -0.004 |
runway | -0.004 |
umes | -0.004 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
runway | +0.005 |
ramids | +0.004 |
plets | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.004 |
rob | -0.003 |
robat | -0.003 |
seeker | -0.003 |
moderation | -0.003 |
Token | gesture |
Token ID | 18342 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
P | +0.004 |
rob | +0.003 |
robat | +0.003 |
seeker | +0.003 |
best | +0.003 |
Neg logit contributions | |
plets | -0.004 |
runway | -0.004 |
ramids | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
plets | +0.003 |
ramids | +0.003 |
runway | +0.003 |
umes | +0.002 |
ifying | +0.002 |
Neg logit contributions | |
P | -0.002 |
best | -0.001 |
joy | -0.001 |
robat | -0.001 |
rob | -0.001 |
Token | Ms |
Token ID | 6997 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
plets | +0.014 |
ramids | +0.014 |
runway | +0.014 |
umes | +0.014 |
ifying | +0.014 |
Neg logit contributions | |
P | -0.018 |
seeker | -0.016 |
rob | -0.016 |
robat | -0.016 |
joy | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
plets | +0.158 |
ramids | +0.157 |
runway | +0.156 |
ifying | +0.152 |
umes | +0.150 |
Neg logit contributions | |
P | -0.127 |
rob | -0.107 |
robat | -0.106 |
best | -0.105 |
joy | -0.105 |
Token | Smith |
Token ID | 4176 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ramids | +0.020 |
plets | +0.019 |
runway | +0.018 |
ifying | +0.018 |
umes | +0.018 |
Neg logit contributions | |
P | -0.018 |
best | -0.015 |
rob | -0.015 |
robat | -0.015 |
Deal | -0.015 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
plets | +0.035 |
ramids | +0.034 |
runway | +0.033 |
ifying | +0.032 |
umes | +0.031 |
Neg logit contributions | |
best | -0.019 |
my | -0.018 |
P | -0.016 |
idea | -0.016 |
joy | -0.016 |
Token | much |
Token ID | 881 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
ramids | +0.048 |
runway | +0.047 |
plets | +0.046 |
umes | +0.044 |
ants | +0.043 |
Neg logit contributions | |
P | -0.030 |
best | -0.029 |
joy | -0.025 |
moderation | -0.025 |
right | -0.023 |
Token | better |
Token ID | 1365 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
plets | +0.040 |
runway | +0.038 |
ifying | +0.037 |
ured | +0.037 |
mic | +0.036 |
Neg logit contributions | |
P | -0.046 |
rob | -0.042 |
robat | -0.042 |
seeker | -0.040 |
icer | -0.037 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
P | +0.007 |
best | +0.006 |
rob | +0.006 |
joy | +0.006 |
robat | +0.006 |
Neg logit contributions | |
plets | -0.007 |
ramids | -0.007 |
runway | -0.007 |
ifying | -0.007 |
umes | -0.007 |
Token | better |
Token ID | 1365 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
ramids | +0.052 |
plets | +0.051 |
runway | +0.050 |
umes | +0.048 |
ifying | +0.048 |
Neg logit contributions | |
best | -0.023 |
P | -0.023 |
moderation | -0.020 |
joy | -0.019 |
idea | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
plets | +0.016 |
runway | +0.016 |
ifying | +0.015 |
ramids | +0.015 |
ured | +0.015 |
Neg logit contributions | |
P | -0.015 |
rob | -0.013 |
robat | -0.012 |
joy | -0.012 |
seeker | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-04 |
Pos logit contributions | |
P | +0.014 |
rob | +0.012 |
robat | +0.011 |
best | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
plets | -0.021 |
ramids | -0.021 |
runway | -0.021 |
ifying | -0.020 |
umes | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
plets | +0.001 |
runway | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.001 |
joy | -0.001 |
rob | -0.001 |
robat | -0.001 |
Token | THE |
Token ID | 10970 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
plets | +0.004 |
runway | +0.004 |
ramids | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.003 |
best | -0.002 |
rob | -0.002 |
joy | -0.002 |
robat | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.26e-04 |
Pos logit contributions | |
plets | +0.203 |
ifying | +0.199 |
runway | +0.194 |
ramids | +0.194 |
umes | +0.190 |
Neg logit contributions | |
P | -0.076 |
best | -0.070 |
joy | -0.065 |
Deal | -0.064 |
rob | -0.062 |
Token | John |
Token ID | 7554 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
Deal | +0.001 |
P | +0.001 |
seeker | +0.001 |
moderation | +0.001 |
best | +0.001 |
Neg logit contributions | |
plets | -0.001 |
ifying | -0.001 |
ramids | -0.001 |
runway | -0.001 |
cum | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
P | +0.031 |
best | +0.027 |
joy | +0.026 |
rob | +0.026 |
robat | +0.026 |
Neg logit contributions | |
plets | -0.041 |
runway | -0.041 |
ramids | -0.040 |
ifying | -0.039 |
umes | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +6.67e-04 |
Pos logit contributions | |
P | +0.006 |
rob | +0.004 |
robat | +0.004 |
joy | +0.004 |
best | +0.004 |
Neg logit contributions | |
runway | -0.011 |
plets | -0.011 |
ramids | -0.011 |
ifying | -0.011 |
umes | -0.011 |
Token | mother |
Token ID | 2802 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
plets | +0.001 |
ramids | +0.001 |
runway | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.001 |
joy | -0.001 |
rob | -0.001 |
robat | -0.001 |
Token | out |
Token ID | 503 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
P | +0.010 |
rob | +0.009 |
robat | +0.009 |
joy | +0.009 |
Deal | +0.008 |
Neg logit contributions | |
ramids | -0.007 |
plets | -0.007 |
runway | -0.007 |
ifying | -0.007 |
ured | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
plets | +0.044 |
runway | +0.043 |
ramids | +0.043 |
ifying | +0.041 |
umes | +0.040 |
Neg logit contributions | |
P | -0.036 |
best | -0.032 |
joy | -0.031 |
rob | -0.030 |
moderation | -0.030 |
Token | cloth |
Token ID | 16270 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
P | +0.013 |
rob | +0.012 |
robat | +0.012 |
moderation | +0.012 |
Deal | +0.011 |
Neg logit contributions | |
runway | -0.016 |
plets | -0.016 |
ifying | -0.015 |
umes | -0.015 |
ramids | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +9.62e-03 |
Pos logit contributions | |
P | +0.019 |
rob | +0.017 |
joy | +0.016 |
best | +0.016 |
robat | +0.016 |
Neg logit contributions | |
plets | -0.024 |
runway | -0.024 |
ramids | -0.024 |
ifying | -0.023 |
umes | -0.023 |
Token | wiped |
Token ID | 21122 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ramids | +0.017 |
plets | +0.017 |
runway | +0.017 |
ifying | +0.016 |
umes | +0.015 |
Neg logit contributions | |
P | -0.014 |
best | -0.012 |
my | -0.011 |
vest | -0.011 |
seeker | -0.011 |
Token | off |
Token ID | 572 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
plets | +0.017 |
ramids | +0.017 |
runway | +0.017 |
ifying | +0.016 |
umes | +0.016 |
Neg logit contributions | |
P | -0.025 |
joy | -0.022 |
rob | -0.022 |
best | -0.022 |
robat | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
plets | +0.154 |
runway | +0.153 |
ramids | +0.149 |
ifying | +0.142 |
umes | +0.141 |
Neg logit contributions | |
P | -0.123 |
best | -0.115 |
joy | -0.103 |
my | -0.102 |
right | -0.098 |
Token | dirt |
Token ID | 13647 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
plets | +0.039 |
ramids | +0.039 |
runway | +0.038 |
ifying | +0.038 |
umes | +0.037 |
Neg logit contributions | |
P | -0.028 |
best | -0.025 |
joy | -0.024 |
robat | -0.023 |
rob | -0.023 |
Token | from |
Token ID | 422 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
plets | +0.064 |
ramids | +0.063 |
runway | +0.063 |
ifying | +0.061 |
umes | +0.060 |
Neg logit contributions | |
P | -0.062 |
best | -0.056 |
robat | -0.053 |
rob | -0.053 |
joy | -0.053 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
plets | +0.059 |
ramids | +0.057 |
runway | +0.056 |
ifying | +0.055 |
umes | +0.054 |
Neg logit contributions | |
P | -0.067 |
best | -0.060 |
joy | -0.059 |
rob | -0.059 |
seeker | -0.059 |
Token | 's |
Token ID | 338 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
P | +0.019 |
best | +0.017 |
joy | +0.016 |
my | +0.016 |
robat | +0.015 |
Neg logit contributions | |
plets | -0.028 |
ramids | -0.028 |
runway | -0.028 |
ifying | -0.027 |
umes | -0.026 |
Token | face |
Token ID | 1986 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
P | +0.021 |
best | +0.020 |
joy | +0.019 |
vest | +0.018 |
robat | +0.017 |
Neg logit contributions | |
plets | -0.029 |
ramids | -0.029 |
umes | -0.028 |
runway | -0.028 |
ifying | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
P | +0.041 |
best | +0.036 |
joy | +0.035 |
robat | +0.033 |
rob | +0.033 |
Neg logit contributions | |
plets | -0.068 |
runway | -0.068 |
ramids | -0.068 |
ifying | -0.065 |
umes | -0.065 |
Token | |
Token ID | 220 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
P | +0.007 |
robat | +0.006 |
rob | +0.006 |
seeker | +0.006 |
best | +0.006 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
runway | -0.009 |
inated | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.98e-05 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
rob | +0.005 |
joy | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.012 |
ramids | -0.012 |
runway | -0.012 |
ifying | -0.011 |
umes | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
plets | +0.000 |
ramids | +0.000 |
runway | +0.000 |
ifying | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
seeker | -0.000 |
joy | -0.000 |
best | -0.000 |
robat | -0.000 |
Token | THE |
Token ID | 10970 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
plets | +0.003 |
ramids | +0.003 |
runway | +0.003 |
ifying | +0.003 |
ured | +0.003 |
Neg logit contributions | |
P | -0.005 |
joy | -0.005 |
seeker | -0.005 |
best | -0.005 |
robat | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
plets | +0.185 |
runway | +0.181 |
ifying | +0.180 |
ramids | +0.180 |
umes | +0.178 |
Neg logit contributions | |
P | -0.092 |
best | -0.080 |
joy | -0.077 |
rob | -0.077 |
robat | -0.073 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
Deal | +0.005 |
P | +0.005 |
moderation | +0.005 |
seeker | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.005 |
ifying | -0.005 |
ramids | -0.005 |
runway | -0.004 |
through | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ramids | +0.012 |
runway | +0.012 |
ifying | +0.012 |
plets | +0.012 |
lights | +0.012 |
Neg logit contributions | |
P | -0.012 |
rob | -0.012 |
robat | -0.011 |
Deal | -0.011 |
moderation | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
plets | +0.030 |
runway | +0.030 |
ifying | +0.029 |
ramids | +0.029 |
umes | +0.028 |
Neg logit contributions | |
P | -0.031 |
rob | -0.028 |
robat | -0.028 |
joy | -0.027 |
best | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
rob | +0.022 |
robat | +0.021 |
ests | +0.020 |
seeker | +0.019 |
P | +0.019 |
Neg logit contributions | |
ifying | -0.017 |
inated | -0.017 |
cum | -0.016 |
ln | -0.016 |
mic | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
plets | +0.045 |
runway | +0.045 |
ramids | +0.045 |
ifying | +0.043 |
umes | +0.042 |
Neg logit contributions | |
P | -0.038 |
best | -0.033 |
rob | -0.033 |
joy | -0.033 |
robat | -0.032 |
Token | big |
Token ID | 1263 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
rob | +0.012 |
P | +0.012 |
Deal | +0.011 |
seeker | +0.011 |
robat | +0.011 |
Neg logit contributions | |
runway | -0.014 |
plets | -0.014 |
ifying | -0.013 |
umes | -0.013 |
mic | -0.013 |
Token | cloth |
Token ID | 16270 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
Deal | +0.003 |
rob | +0.003 |
P | +0.003 |
ests | +0.003 |
best | +0.002 |
Neg logit contributions | |
runway | -0.003 |
plets | -0.003 |
rubble | -0.002 |
mic | -0.002 |
cum | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
P | +0.023 |
rob | +0.020 |
joy | +0.020 |
best | +0.019 |
robat | +0.019 |
Neg logit contributions | |
plets | -0.030 |
runway | -0.029 |
ramids | -0.029 |
ifying | -0.028 |
umes | -0.028 |
Token | wiped |
Token ID | 21122 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ramids | +0.006 |
runway | +0.006 |
plets | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.006 |
best | -0.005 |
rob | -0.005 |
my | -0.005 |
joy | -0.005 |
Token | off |
Token ID | 572 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
plets | +0.016 |
runway | +0.016 |
ramids | +0.016 |
ifying | +0.015 |
umes | +0.015 |
Neg logit contributions | |
P | -0.023 |
best | -0.020 |
joy | -0.020 |
rob | -0.020 |
robat | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
runway | +0.160 |
plets | +0.159 |
ramids | +0.156 |
keys | +0.149 |
mic | +0.147 |
Neg logit contributions | |
P | -0.111 |
best | -0.101 |
my | -0.092 |
joy | -0.092 |
right | -0.091 |
Token | mud |
Token ID | 17492 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
plets | +0.031 |
runway | +0.031 |
ramids | +0.030 |
ifying | +0.029 |
umes | +0.029 |
Neg logit contributions | |
P | -0.037 |
rob | -0.033 |
robat | -0.033 |
joy | -0.033 |
best | -0.033 |
Token | from |
Token ID | 422 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
plets | +0.060 |
runway | +0.059 |
ramids | +0.059 |
ifying | +0.057 |
umes | +0.056 |
Neg logit contributions | |
P | -0.054 |
best | -0.047 |
joy | -0.047 |
rob | -0.047 |
robat | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
plets | +0.056 |
ramids | +0.054 |
runway | +0.054 |
ifying | +0.052 |
umes | +0.051 |
Neg logit contributions | |
P | -0.062 |
best | -0.055 |
joy | -0.055 |
rob | -0.054 |
robat | -0.054 |
Token | child |
Token ID | 1200 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
P | +0.009 |
rob | +0.008 |
best | +0.008 |
robat | +0.008 |
joy | +0.008 |
Neg logit contributions | |
plets | -0.009 |
runway | -0.009 |
ramids | -0.008 |
ifying | -0.008 |
umes | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
plets | +0.013 |
runway | +0.012 |
ramids | +0.012 |
ifying | +0.012 |
umes | +0.011 |
Neg logit contributions | |
P | -0.020 |
best | -0.018 |
joy | -0.018 |
rob | -0.018 |
robat | -0.018 |
Token | away |
Token ID | 1497 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
plets | +0.052 |
ramids | +0.051 |
runway | +0.051 |
ifying | +0.049 |
umes | +0.048 |
Neg logit contributions | |
P | -0.048 |
best | -0.042 |
joy | -0.041 |
robat | -0.041 |
rob | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
plets | +0.074 |
ramids | +0.072 |
runway | +0.072 |
ifying | +0.069 |
umes | +0.069 |
Neg logit contributions | |
P | -0.046 |
best | -0.042 |
joy | -0.040 |
seeker | -0.038 |
robat | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
P | +0.007 |
rob | +0.007 |
Deal | +0.007 |
robat | +0.007 |
seeker | +0.006 |
Neg logit contributions | |
runway | -0.004 |
ifying | -0.004 |
ramids | -0.004 |
plets | -0.004 |
sealed | -0.004 |
Token | wheel |
Token ID | 7825 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
P | +0.046 |
rob | +0.041 |
robat | +0.040 |
best | +0.040 |
joy | +0.039 |
Neg logit contributions | |
plets | -0.055 |
runway | -0.054 |
ramids | -0.053 |
ifying | -0.053 |
umes | -0.051 |
Token | bar |
Token ID | 5657 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
P | +0.055 |
joy | +0.047 |
rob | +0.047 |
moderation | +0.046 |
best | +0.045 |
Neg logit contributions | |
plets | -0.059 |
runway | -0.058 |
ramids | -0.057 |
ifying | -0.056 |
umes | -0.054 |
Token | row |
Token ID | 808 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
joy | +0.243 |
P | +0.231 |
seeker | +0.221 |
rob | +0.221 |
Deal | +0.218 |
Neg logit contributions | |
plets | -0.089 |
oves | -0.087 |
lights | -0.085 |
ric | -0.082 |
runway | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
P | +0.021 |
rob | +0.018 |
robat | +0.018 |
moderation | +0.017 |
joy | +0.017 |
Neg logit contributions | |
plets | -0.022 |
runway | -0.021 |
ramids | -0.021 |
ifying | -0.021 |
ured | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -7.29e-04 |
Pos logit contributions | |
P | +0.022 |
seeker | +0.019 |
robat | +0.019 |
rob | +0.018 |
best | +0.018 |
Neg logit contributions | |
ramids | -0.024 |
plets | -0.023 |
runway | -0.022 |
inated | -0.022 |
ifying | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
P | +0.001 |
seeker | +0.001 |
joy | +0.001 |
best | +0.001 |
rob | +0.001 |
Neg logit contributions | |
ramids | -0.001 |
runway | -0.001 |
plets | -0.001 |
uring | -0.001 |
inated | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
plets | +0.002 |
ramids | +0.002 |
runway | +0.002 |
ifying | +0.002 |
umes | +0.002 |
Neg logit contributions | |
P | -0.003 |
robat | -0.003 |
best | -0.003 |
moderation | -0.003 |
Deal | -0.002 |
Token | dolls |
Token ID | 36062 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
plets | +0.053 |
ramids | +0.052 |
runway | +0.051 |
ifying | +0.050 |
umes | +0.049 |
Neg logit contributions | |
P | -0.041 |
best | -0.038 |
robat | -0.035 |
seeker | -0.035 |
joy | -0.035 |
Token | around |
Token ID | 1088 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
runway | +0.026 |
plets | +0.025 |
ramids | +0.025 |
uring | +0.024 |
ifying | +0.024 |
Neg logit contributions | |
P | -0.027 |
rob | -0.024 |
joy | -0.024 |
moderation | -0.023 |
Deal | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
runway | +0.013 |
ramids | +0.013 |
uring | +0.012 |
plets | +0.012 |
ured | +0.012 |
Neg logit contributions | |
P | -0.017 |
rob | -0.015 |
robat | -0.014 |
Deal | -0.014 |
orn | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
P | +0.011 |
rob | +0.010 |
Deal | +0.010 |
robat | +0.010 |
orn | +0.009 |
Neg logit contributions | |
runway | -0.007 |
ramids | -0.006 |
ifying | -0.006 |
plets | -0.006 |
uring | -0.006 |
Token | wheel |
Token ID | 7825 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
P | +0.027 |
rob | +0.025 |
joy | +0.024 |
robat | +0.024 |
best | +0.023 |
Neg logit contributions | |
runway | -0.037 |
plets | -0.036 |
ramids | -0.035 |
ifying | -0.035 |
umes | -0.034 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
P | +0.059 |
joy | +0.053 |
moderation | +0.052 |
rob | +0.050 |
best | +0.049 |
Neg logit contributions | |
runway | -0.057 |
plets | -0.055 |
ramids | -0.054 |
ifying | -0.052 |
ents | -0.050 |
Token | row |
Token ID | 808 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
joy | +0.212 |
P | +0.187 |
Deal | +0.186 |
seeker | +0.182 |
moderation | +0.182 |
Neg logit contributions | |
ric | -0.100 |
runway | -0.097 |
lights | -0.097 |
oves | -0.096 |
plets | -0.092 |
Token | she |
Token ID | 673 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
P | +0.023 |
rob | +0.020 |
robat | +0.019 |
joy | +0.019 |
moderation | +0.019 |
Neg logit contributions | |
runway | -0.022 |
plets | -0.022 |
ramids | -0.021 |
ifying | -0.021 |
uring | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
P | +0.013 |
joy | +0.012 |
rob | +0.012 |
moderation | +0.012 |
robat | +0.011 |
Neg logit contributions | |
runway | -0.010 |
plets | -0.010 |
ramids | -0.009 |
ifying | -0.009 |
umes | -0.009 |
Token | found |
Token ID | 1043 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
P | +0.010 |
best | +0.009 |
my | +0.008 |
joy | +0.008 |
seeker | +0.008 |
Neg logit contributions | |
plets | -0.012 |
ramids | -0.012 |
runway | -0.012 |
inated | -0.011 |
ifying | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
P | +0.030 |
best | +0.026 |
joy | +0.025 |
rob | +0.025 |
robat | +0.025 |
Neg logit contributions | |
plets | -0.038 |
runway | -0.038 |
ramids | -0.038 |
ifying | -0.037 |
umes | -0.036 |
Token | back |
Token ID | 736 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
plets | +0.021 |
runway | +0.020 |
ramids | +0.020 |
ifying | +0.020 |
umes | +0.019 |
Neg logit contributions | |
P | -0.020 |
best | -0.018 |
joy | -0.018 |
seeker | -0.017 |
robat | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -4.82e-04 |
Pos logit contributions | |
P | +0.006 |
best | +0.006 |
joy | +0.006 |
rob | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.008 |
runway | -0.008 |
ramids | -0.008 |
ifying | -0.008 |
umes | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
P | +0.001 |
rob | +0.001 |
robat | +0.001 |
Deal | +0.001 |
seeker | +0.001 |
Neg logit contributions | |
ifying | -0.001 |
runway | -0.001 |
ured | -0.001 |
wil | -0.001 |
flashing | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
P | +0.033 |
rob | +0.032 |
robat | +0.029 |
Deal | +0.028 |
ests | +0.027 |
Neg logit contributions | |
runway | -0.034 |
plets | -0.034 |
ifying | -0.033 |
umes | -0.032 |
mic | -0.032 |
Token | wheel |
Token ID | 7825 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
P | +0.022 |
rob | +0.020 |
Deal | +0.018 |
robat | +0.017 |
ests | +0.017 |
Neg logit contributions | |
runway | -0.019 |
plets | -0.018 |
flashing | -0.016 |
mic | -0.016 |
ifying | -0.016 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
P | +0.049 |
best | +0.042 |
joy | +0.042 |
rob | +0.041 |
robat | +0.041 |
Neg logit contributions | |
plets | -0.066 |
ramids | -0.065 |
runway | -0.065 |
ifying | -0.063 |
umes | -0.062 |
Token | row |
Token ID | 808 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
P | +0.214 |
joy | +0.212 |
rob | +0.200 |
moderation | +0.198 |
Deal | +0.198 |
Neg logit contributions | |
plets | -0.092 |
oves | -0.083 |
ants | -0.079 |
lights | -0.079 |
runway | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-05 |
Pos logit contributions | |
P | +0.021 |
rob | +0.018 |
robat | +0.017 |
moderation | +0.017 |
best | +0.017 |
Neg logit contributions | |
plets | -0.023 |
runway | -0.023 |
ramids | -0.023 |
ifying | -0.022 |
umes | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
plets | +0.000 |
runway | +0.000 |
ramids | +0.000 |
ifying | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
joy | -0.000 |
best | -0.000 |
rob | -0.000 |
robat | -0.000 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
P | +0.010 |
best | +0.009 |
joy | +0.008 |
rob | +0.008 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.011 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
umes | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
P | +0.036 |
rob | +0.033 |
robat | +0.032 |
seeker | +0.031 |
joy | +0.030 |
Neg logit contributions | |
ramids | -0.025 |
ured | -0.025 |
runway | -0.024 |
uring | -0.024 |
plets | -0.023 |
Token | sund |
Token ID | 37437 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
P | +0.002 |
rob | +0.002 |
robat | +0.002 |
moderation | +0.002 |
joy | +0.002 |
Neg logit contributions | |
plets | -0.003 |
ifying | -0.003 |
runway | -0.003 |
ramids | -0.002 |
umes | -0.002 |
Token | ae |
Token ID | 3609 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
P | +0.080 |
joy | +0.079 |
rob | +0.076 |
seeker | +0.073 |
robat | +0.071 |
Neg logit contributions | |
ifying | -0.078 |
plets | -0.078 |
umes | -0.074 |
runway | -0.074 |
keys | -0.073 |
Token | with |
Token ID | 351 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
plets | +0.016 |
ramids | +0.016 |
runway | +0.016 |
ifying | +0.015 |
umes | +0.015 |
Neg logit contributions | |
P | -0.011 |
best | -0.009 |
joy | -0.009 |
robat | -0.009 |
rob | -0.009 |
Token | lots |
Token ID | 6041 |
Feature activation | +5.26e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.006 |
joy | +0.005 |
rob | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.008 |
runway | -0.008 |
ramids | -0.008 |
ifying | -0.007 |
umes | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +4.11e-04 |
Pos logit contributions | |
ramids | +0.010 |
runway | +0.010 |
plets | +0.009 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
joy | -0.006 |
my | -0.006 |
moderation | -0.006 |
Token | topp |
Token ID | 23126 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
ramids | +0.001 |
plets | +0.001 |
runway | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
seeker | -0.001 |
robat | -0.001 |
joy | -0.001 |
rob | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | +2.65e-05 |
Pos logit contributions | |
P | +0.170 |
joy | +0.156 |
rob | +0.156 |
seeker | +0.155 |
moderation | +0.153 |
Neg logit contributions | |
ramids | -0.126 |
plets | -0.124 |
ifying | -0.118 |
ured | -0.115 |
umes | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
plets | +0.000 |
runway | +0.000 |
ramids | +0.000 |
ifying | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
best | -0.000 |
joy | -0.000 |
robat | -0.000 |
rob | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
P | +0.010 |
joy | +0.008 |
best | +0.008 |
rob | +0.008 |
moderation | +0.008 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.013 |
umes | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
joy | +0.005 |
rob | +0.005 |
robat | +0.004 |
Neg logit contributions | |
plets | -0.011 |
ramids | -0.011 |
runway | -0.011 |
ifying | -0.010 |
umes | -0.010 |
Token | They |
Token ID | 2990 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
P | +0.002 |
Ben | +0.002 |
my | +0.002 |
ossible | +0.001 |
Today | +0.001 |
Neg logit contributions | |
flies | -0.002 |
plets | -0.002 |
lights | -0.002 |
ric | -0.002 |
ramids | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.78e-04 |
Pos logit contributions | |
plets | +0.034 |
runway | +0.033 |
ramids | +0.033 |
ifying | +0.032 |
umes | +0.031 |
Neg logit contributions | |
P | -0.022 |
best | -0.020 |
rob | -0.019 |
joy | -0.019 |
robat | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
P | +0.000 |
best | +0.000 |
joy | +0.000 |
rob | +0.000 |
seeker | +0.000 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
umes | -0.001 |
Token | found |
Token ID | 1043 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
P | +0.010 |
best | +0.009 |
joy | +0.009 |
rob | +0.009 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.014 |
runway | -0.014 |
ramids | -0.014 |
ifying | -0.014 |
umes | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
P | +0.019 |
robat | +0.016 |
rob | +0.016 |
joy | +0.016 |
seeker | +0.016 |
Neg logit contributions | |
plets | -0.019 |
ramids | -0.019 |
runway | -0.019 |
ifying | -0.018 |
umes | -0.018 |
Token | wheel |
Token ID | 7825 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
P | +0.010 |
rob | +0.009 |
joy | +0.009 |
robat | +0.009 |
best | +0.008 |
Neg logit contributions | |
plets | -0.014 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.013 |
umes | -0.013 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
P | +0.031 |
best | +0.027 |
rob | +0.026 |
joy | +0.026 |
robat | +0.026 |
Neg logit contributions | |
plets | -0.038 |
runway | -0.037 |
ramids | -0.037 |
ifying | -0.036 |
umes | -0.036 |
Token | row |
Token ID | 808 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
joy | +0.189 |
P | +0.185 |
moderation | +0.173 |
Deal | +0.167 |
rob | +0.162 |
Neg logit contributions | |
plets | -0.107 |
lights | -0.100 |
ric | -0.095 |
ramids | -0.094 |
runway | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
P | +0.002 |
rob | +0.002 |
moderation | +0.002 |
robat | +0.002 |
joy | +0.002 |
Neg logit contributions | |
plets | -0.002 |
ramids | -0.002 |
runway | -0.002 |
ifying | -0.002 |
umes | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
plets | +0.006 |
ramids | +0.005 |
runway | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.004 |
best | -0.003 |
joy | -0.003 |
rob | -0.003 |
robat | -0.003 |
Token | tr |
Token ID | 491 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
P | +0.013 |
rob | +0.011 |
joy | +0.011 |
best | +0.011 |
robat | +0.011 |
Neg logit contributions | |
plets | -0.019 |
runway | -0.019 |
ramids | -0.018 |
ifying | -0.018 |
umes | -0.018 |
Token | amp |
Token ID | 696 |
Feature activation | +6.16e-03 |
Pos logit contributions | |
P | +0.023 |
best | +0.021 |
joy | +0.020 |
rob | +0.019 |
moderation | +0.019 |
Neg logit contributions | |
plets | -0.029 |
ramids | -0.028 |
runway | -0.028 |
ifying | -0.028 |
umes | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
plets | +0.056 |
runway | +0.053 |
mic | +0.051 |
ller | +0.050 |
ramids | +0.049 |
Neg logit contributions | |
P | -0.026 |
best | -0.025 |
my | -0.023 |
right | -0.021 |
ossible | -0.021 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
plets | +0.006 |
runway | +0.006 |
ramids | +0.006 |
ifying | +0.005 |
keys | +0.005 |
Neg logit contributions | |
P | -0.004 |
best | -0.004 |
joy | -0.004 |
moderation | -0.004 |
seeker | -0.004 |
Token | my |
Token ID | 1820 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
P | +0.011 |
rob | +0.007 |
robat | +0.006 |
joy | +0.006 |
seeker | +0.006 |
Neg logit contributions | |
ramids | -0.054 |
plets | -0.053 |
runway | -0.053 |
umes | -0.053 |
ifying | -0.052 |
Token | one |
Token ID | 530 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
P | +0.011 |
best | +0.010 |
my | +0.010 |
joy | +0.009 |
moderation | +0.009 |
Neg logit contributions | |
plets | -0.022 |
runway | -0.021 |
ramids | -0.021 |
ifying | -0.020 |
mic | -0.020 |
Token | by |
Token ID | 416 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
P | +0.094 |
rob | +0.079 |
best | +0.079 |
joy | +0.079 |
robat | +0.078 |
Neg logit contributions | |
plets | -0.131 |
runway | -0.129 |
ramids | -0.128 |
ifying | -0.125 |
umes | -0.123 |
Token | one |
Token ID | 530 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
P | +0.011 |
best | +0.009 |
joy | +0.009 |
rob | +0.008 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.023 |
runway | -0.023 |
ramids | -0.023 |
ifying | -0.022 |
umes | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
P | +0.140 |
rob | +0.127 |
robat | +0.120 |
seeker | +0.119 |
joy | +0.117 |
Neg logit contributions | |
plets | -0.156 |
runway | -0.154 |
ramids | -0.153 |
ifying | -0.153 |
umes | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
P | +0.010 |
joy | +0.009 |
best | +0.008 |
ossible | +0.007 |
seeker | +0.007 |
Neg logit contributions | |
runway | -0.024 |
plets | -0.024 |
keys | -0.023 |
ifying | -0.022 |
mic | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.002 |
joy | +0.002 |
rob | +0.002 |
ossible | +0.002 |
Neg logit contributions | |
plets | -0.010 |
runway | -0.010 |
ifying | -0.010 |
ramids | -0.009 |
umes | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
P | +0.004 |
best | +0.002 |
ossible | +0.002 |
m | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
plets | -0.005 |
runway | -0.005 |
flies | -0.005 |
rubble | -0.005 |
lights | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
plets | +0.057 |
runway | +0.055 |
ramids | +0.054 |
mic | +0.053 |
ifying | +0.052 |
Neg logit contributions | |
P | -0.052 |
best | -0.051 |
joy | -0.047 |
seeker | -0.046 |
m | -0.045 |
Token | â |
Token ID | 22940 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
plets | +0.009 |
runway | +0.009 |
ramids | +0.008 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
joy | -0.006 |
rob | -0.006 |
robat | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
P | +0.004 |
joy | +0.004 |
best | +0.004 |
moderation | +0.004 |
seeker | +0.004 |
Neg logit contributions | |
plets | -0.005 |
ramids | -0.004 |
ured | -0.004 |
runway | -0.004 |
uring | -0.004 |
Token | � |
Token ID | 129 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
plets | +0.029 |
ramids | +0.029 |
runway | +0.029 |
ifying | +0.027 |
umes | +0.027 |
Neg logit contributions | |
P | -0.029 |
best | -0.025 |
rob | -0.024 |
robat | -0.024 |
seeker | -0.024 |
Token | � |
Token ID | 241 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
plets | +0.009 |
ifying | +0.008 |
lights | +0.008 |
runway | +0.008 |
umes | +0.007 |
Neg logit contributions | |
P | -0.011 |
best | -0.010 |
Deal | -0.010 |
robat | -0.009 |
rob | -0.009 |
Token | That |
Token ID | 2504 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
plets | +0.004 |
ifying | +0.004 |
ramids | +0.004 |
runway | +0.003 |
umes | +0.003 |
Neg logit contributions | |
P | -0.003 |
best | -0.003 |
rob | -0.003 |
robat | -0.003 |
joy | -0.003 |
Token | one |
Token ID | 530 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
P | +0.020 |
joy | +0.017 |
rob | +0.017 |
best | +0.017 |
robat | +0.017 |
Neg logit contributions | |
plets | -0.025 |
runway | -0.024 |
ramids | -0.024 |
ifying | -0.024 |
umes | -0.023 |
Token | costs |
Token ID | 3484 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
P | +0.132 |
rob | +0.116 |
joy | +0.116 |
robat | +0.113 |
seeker | +0.112 |
Neg logit contributions | |
plets | -0.154 |
runway | -0.150 |
ramids | -0.149 |
umes | -0.147 |
ifying | -0.147 |
Token | more |
Token ID | 517 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
P | +0.062 |
rob | +0.055 |
robat | +0.054 |
joy | +0.053 |
seeker | +0.052 |
Neg logit contributions | |
plets | -0.070 |
ramids | -0.069 |
runway | -0.069 |
ifying | -0.068 |
umes | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
P | +0.054 |
best | +0.048 |
joy | +0.045 |
robat | +0.044 |
seeker | +0.044 |
Neg logit contributions | |
plets | -0.073 |
ramids | -0.072 |
runway | -0.071 |
ifying | -0.070 |
umes | -0.067 |
Token | â |
Token ID | 22940 |
Feature activation | -5.09e-03 |
Pos logit contributions | |
P | +0.013 |
best | +0.012 |
joy | +0.012 |
rob | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.012 |
umes | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
joy | +0.007 |
P | +0.007 |
best | +0.007 |
seeker | +0.007 |
moderation | +0.007 |
Neg logit contributions | |
plets | -0.008 |
ured | -0.008 |
uring | -0.008 |
runway | -0.007 |
inated | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
plets | +0.007 |
runway | +0.007 |
ramids | +0.007 |
ifying | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.009 |
best | -0.008 |
rob | -0.008 |
joy | -0.008 |
robat | -0.008 |
Token | cand |
Token ID | 2658 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
P | +0.022 |
joy | +0.020 |
seeker | +0.020 |
rob | +0.019 |
robat | +0.019 |
Neg logit contributions | |
plets | -0.019 |
ramids | -0.019 |
runway | -0.018 |
ifying | -0.018 |
umes | -0.018 |
Token | ies |
Token ID | 444 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
P | +0.020 |
best | +0.018 |
joy | +0.017 |
robat | +0.017 |
rob | +0.017 |
Neg logit contributions | |
plets | -0.015 |
runway | -0.014 |
ramids | -0.014 |
ifying | -0.014 |
umes | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
plets | +0.063 |
runway | +0.062 |
ramids | +0.062 |
ifying | +0.059 |
umes | +0.058 |
Neg logit contributions | |
P | -0.045 |
best | -0.040 |
joy | -0.038 |
robat | -0.037 |
moderation | -0.037 |
Token | by |
Token ID | 416 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
P | +0.128 |
rob | +0.123 |
seeker | +0.117 |
joy | +0.116 |
robat | +0.112 |
Neg logit contributions | |
plets | -0.104 |
ifying | -0.103 |
umes | -0.100 |
runway | -0.099 |
ender | -0.098 |
Token | one |
Token ID | 530 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
P | +0.027 |
rob | +0.023 |
robat | +0.023 |
joy | +0.022 |
best | +0.022 |
Neg logit contributions | |
ramids | -0.033 |
runway | -0.033 |
plets | -0.033 |
ured | -0.033 |
inated | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
P | +0.145 |
rob | +0.135 |
joy | +0.123 |
seeker | +0.121 |
robat | +0.120 |
Neg logit contributions | |
runway | -0.146 |
ifying | -0.146 |
plets | -0.145 |
ramids | -0.145 |
umes | -0.141 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
plets | +0.008 |
runway | +0.008 |
ramids | +0.008 |
ifying | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.010 |
best | -0.009 |
rob | -0.009 |
joy | -0.009 |
robat | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
plets | +0.013 |
runway | +0.013 |
ramids | +0.012 |
ifying | +0.012 |
mic | +0.012 |
Neg logit contributions | |
P | -0.015 |
best | -0.014 |
joy | -0.014 |
moderation | -0.013 |
rob | -0.013 |
Token | all |
Token ID | 477 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
P | +0.006 |
rob | +0.006 |
robat | +0.006 |
joy | +0.006 |
seeker | +0.005 |
Neg logit contributions | |
runway | -0.006 |
ramids | -0.006 |
plets | -0.006 |
umes | -0.006 |
ifying | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
P | +0.003 |
rob | +0.002 |
seeker | +0.002 |
robat | +0.002 |
joy | +0.002 |
Neg logit contributions | |
ramids | -0.003 |
plets | -0.003 |
runway | -0.003 |
ifying | -0.003 |
umes | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
P | +0.021 |
rob | +0.018 |
best | +0.018 |
joy | +0.018 |
robat | +0.018 |
Neg logit contributions | |
plets | -0.028 |
runway | -0.027 |
ramids | -0.027 |
ifying | -0.026 |
umes | -0.026 |
Token | this |
Token ID | 428 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
P | +0.006 |
joy | +0.006 |
best | +0.006 |
my | +0.006 |
moderation | +0.005 |
Neg logit contributions | |
plets | -0.008 |
runway | -0.008 |
ramids | -0.008 |
ifying | -0.008 |
umes | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
P | +0.014 |
best | +0.012 |
joy | +0.012 |
robat | +0.012 |
rob | +0.011 |
Neg logit contributions | |
ramids | -0.023 |
plets | -0.023 |
runway | -0.023 |
ifying | -0.022 |
umes | -0.022 |
Token | adding |
Token ID | 4375 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
plets | +0.013 |
runway | +0.013 |
ramids | +0.013 |
ifying | +0.012 |
umes | +0.012 |
Neg logit contributions | |
P | -0.009 |
best | -0.008 |
joy | -0.008 |
seeker | -0.007 |
robat | -0.007 |
Token | an |
Token ID | 281 |
Feature activation | -3.69e-03 |
Pos logit contributions | |
P | +0.054 |
rob | +0.048 |
robat | +0.047 |
seeker | +0.047 |
joy | +0.046 |
Neg logit contributions | |
plets | -0.050 |
runway | -0.050 |
ramids | -0.049 |
ifying | -0.048 |
umes | -0.047 |
Token | ult |
Token ID | 3789 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
P | +0.005 |
best | +0.005 |
joy | +0.005 |
rob | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.006 |
ramids | -0.006 |
ifying | -0.006 |
umes | -0.006 |
Token | im |
Token ID | 320 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
P | +0.126 |
best | +0.120 |
rob | +0.117 |
joy | +0.117 |
robat | +0.111 |
Neg logit contributions | |
ramids | -0.155 |
inated | -0.143 |
ured | -0.141 |
ric | -0.141 |
uring | -0.139 |
Token | atum |
Token ID | 21307 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
P | +0.013 |
best | +0.012 |
robat | +0.011 |
rob | +0.011 |
joy | +0.011 |
Neg logit contributions | |
runway | -0.014 |
plets | -0.014 |
ramids | -0.014 |
ifying | -0.013 |
umes | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
P | +0.030 |
rob | +0.026 |
moderation | +0.025 |
joy | +0.025 |
robat | +0.025 |
Neg logit contributions | |
plets | -0.030 |
runway | -0.030 |
ramids | -0.029 |
ifying | -0.029 |
ured | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
P | +0.009 |
rob | +0.008 |
robat | +0.008 |
best | +0.008 |
seeker | +0.008 |
Neg logit contributions | |
plets | -0.012 |
ramids | -0.011 |
ifying | -0.011 |
runway | -0.011 |
umes | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
plets | +0.030 |
runway | +0.030 |
ramids | +0.030 |
ifying | +0.029 |
umes | +0.028 |
Neg logit contributions | |
P | -0.022 |
best | -0.019 |
rob | -0.018 |
joy | -0.018 |
robat | -0.018 |
Token | rag |
Token ID | 34232 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
P | +0.001 |
rob | +0.001 |
robat | +0.001 |
joy | +0.001 |
Deal | +0.001 |
Neg logit contributions | |
runway | -0.001 |
plets | -0.001 |
ramids | -0.001 |
umes | -0.001 |
ured | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
plets | +0.003 |
ramids | +0.003 |
runway | +0.003 |
ifying | +0.003 |
umes | +0.003 |
Neg logit contributions | |
P | -0.002 |
best | -0.002 |
joy | -0.002 |
robat | -0.002 |
rob | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
P | +0.032 |
best | +0.030 |
moderation | +0.029 |
joy | +0.029 |
seeker | +0.027 |
Neg logit contributions | |
plets | -0.044 |
ramids | -0.043 |
ifying | -0.041 |
runway | -0.041 |
umes | -0.040 |
Token | shiny |
Token ID | 22441 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
P | +0.044 |
best | +0.040 |
joy | +0.039 |
seeker | +0.036 |
robat | +0.036 |
Neg logit contributions | |
plets | -0.063 |
ramids | -0.063 |
runway | -0.061 |
umes | -0.059 |
ifying | -0.059 |
Token | new |
Token ID | 649 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
P | +0.054 |
rob | +0.047 |
robat | +0.045 |
joy | +0.043 |
best | +0.042 |
Neg logit contributions | |
runway | -0.064 |
plets | -0.063 |
ifying | -0.062 |
ramids | -0.062 |
ured | -0.060 |
Token | one |
Token ID | 530 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
P | +0.049 |
rob | +0.046 |
robat | +0.041 |
Deal | +0.039 |
moderation | +0.039 |
Neg logit contributions | |
runway | -0.060 |
inated | -0.055 |
ured | -0.054 |
plets | -0.054 |
ramids | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
P | +0.126 |
rob | +0.111 |
joy | +0.106 |
robat | +0.105 |
seeker | +0.104 |
Neg logit contributions | |
plets | -0.160 |
runway | -0.157 |
ifying | -0.154 |
ramids | -0.153 |
umes | -0.150 |
Token | she |
Token ID | 673 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
P | +0.018 |
best | +0.016 |
joy | +0.016 |
rob | +0.016 |
robat | +0.015 |
Neg logit contributions | |
plets | -0.015 |
ramids | -0.015 |
runway | -0.015 |
ifying | -0.014 |
umes | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.002 |
my | +0.002 |
joy | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.003 |
ramids | -0.003 |
runway | -0.003 |
ifying | -0.003 |
umes | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.002 |
joy | +0.002 |
moderation | +0.002 |
seeker | +0.002 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.004 |
keys | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
P | +0.007 |
best | +0.006 |
joy | +0.006 |
moderation | +0.006 |
rob | +0.006 |
Neg logit contributions | |
plets | -0.007 |
ramids | -0.007 |
runway | -0.007 |
ifying | -0.007 |
umes | -0.007 |
Token | shining |
Token ID | 22751 |
Feature activation | -8.92e-03 |
Pos logit contributions | |
P | +0.012 |
robat | +0.011 |
rob | +0.011 |
joy | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
plets | -0.012 |
ramids | -0.012 |
runway | -0.012 |
ifying | -0.012 |
umes | -0.011 |
Token | brightly |
Token ID | 35254 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
P | +0.012 |
best | +0.010 |
joy | +0.010 |
rob | +0.009 |
robat | +0.009 |
Neg logit contributions | |
plets | -0.016 |
runway | -0.016 |
ramids | -0.016 |
umes | -0.016 |
ifying | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
P | +0.019 |
best | +0.017 |
joy | +0.016 |
rob | +0.016 |
robat | +0.016 |
Neg logit contributions | |
plets | -0.028 |
runway | -0.028 |
ramids | -0.027 |
umes | -0.027 |
ifying | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
P | +0.037 |
rob | +0.033 |
robat | +0.033 |
best | +0.033 |
joy | +0.032 |
Neg logit contributions | |
plets | -0.027 |
runway | -0.027 |
ramids | -0.027 |
ifying | -0.026 |
umes | -0.025 |
Token | sky |
Token ID | 6766 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
P | +0.030 |
best | +0.026 |
joy | +0.025 |
seeker | +0.024 |
my | +0.024 |
Neg logit contributions | |
plets | -0.035 |
ramids | -0.035 |
runway | -0.034 |
umes | -0.034 |
ured | -0.033 |
Token | one |
Token ID | 530 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
P | +0.050 |
best | +0.043 |
joy | +0.041 |
robat | +0.040 |
rob | +0.040 |
Neg logit contributions | |
plets | -0.081 |
runway | -0.080 |
ramids | -0.080 |
ifying | -0.077 |
umes | -0.077 |
Token | day |
Token ID | 1110 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
P | +0.106 |
best | +0.087 |
rob | +0.087 |
joy | +0.087 |
robat | +0.086 |
Neg logit contributions | |
plets | -0.180 |
runway | -0.178 |
ramids | -0.177 |
ifying | -0.173 |
umes | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
P | +0.020 |
best | +0.017 |
joy | +0.016 |
seeker | +0.015 |
my | +0.014 |
Neg logit contributions | |
ramids | -0.039 |
runway | -0.039 |
plets | -0.038 |
umes | -0.037 |
ifying | -0.037 |
Token | But |
Token ID | 887 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
plets | +0.004 |
runway | +0.004 |
ramids | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.003 |
joy | -0.003 |
best | -0.003 |
rob | -0.003 |
seeker | -0.003 |
Token | then |
Token ID | 788 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
plets | +0.005 |
runway | +0.005 |
ramids | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.006 |
best | -0.005 |
joy | -0.005 |
seeker | -0.005 |
moderation | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
P | +0.034 |
best | +0.029 |
rob | +0.029 |
joy | +0.029 |
robat | +0.029 |
Neg logit contributions | |
plets | -0.042 |
runway | -0.041 |
ramids | -0.041 |
ifying | -0.040 |
umes | -0.039 |
Token | him |
Token ID | 683 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
P | +0.011 |
rob | +0.010 |
seeker | +0.010 |
robat | +0.010 |
moderation | +0.010 |
Neg logit contributions | |
ramids | -0.008 |
ifying | -0.008 |
plets | -0.008 |
runway | -0.008 |
umes | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
plets | +0.009 |
runway | +0.009 |
ramids | +0.009 |
ifying | +0.009 |
umes | +0.008 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
joy | -0.006 |
rob | -0.006 |
robat | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
P | +0.008 |
rob | +0.007 |
robat | +0.007 |
moderation | +0.007 |
joy | +0.007 |
Neg logit contributions | |
runway | -0.010 |
ramids | -0.009 |
plets | -0.009 |
ifying | -0.009 |
umes | -0.009 |
Token | red |
Token ID | 2266 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
P | +0.003 |
rob | +0.003 |
moderation | +0.002 |
Deal | +0.002 |
robat | +0.002 |
Neg logit contributions | |
runway | -0.004 |
plets | -0.003 |
ifying | -0.003 |
ramids | -0.003 |
mic | -0.003 |
Token | wheel |
Token ID | 7825 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
P | +0.034 |
rob | +0.029 |
joy | +0.029 |
moderation | +0.029 |
best | +0.029 |
Neg logit contributions | |
runway | -0.046 |
ramids | -0.046 |
plets | -0.046 |
ifying | -0.045 |
umes | -0.043 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
P | +0.034 |
joy | +0.029 |
rob | +0.029 |
moderation | +0.028 |
best | +0.028 |
Neg logit contributions | |
plets | -0.041 |
runway | -0.041 |
ramids | -0.041 |
ifying | -0.039 |
umes | -0.039 |
Token | row |
Token ID | 808 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
joy | +0.170 |
P | +0.164 |
moderation | +0.157 |
seeker | +0.149 |
rob | +0.147 |
Neg logit contributions | |
plets | -0.115 |
lights | -0.111 |
runway | -0.110 |
ramids | -0.106 |
drops | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
plets | +0.006 |
runway | +0.006 |
ramids | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.006 |
rob | -0.005 |
joy | -0.005 |
robat | -0.005 |
best | -0.005 |
Token | filled |
Token ID | 5901 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
plets | +0.019 |
ramids | +0.019 |
runway | +0.019 |
ifying | +0.018 |
umes | +0.018 |
Neg logit contributions | |
P | -0.016 |
best | -0.014 |
rob | -0.013 |
joy | -0.013 |
seeker | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
plets | +0.044 |
ramids | +0.044 |
runway | +0.043 |
ifying | +0.041 |
umes | +0.040 |
Neg logit contributions | |
P | -0.084 |
best | -0.076 |
joy | -0.076 |
rob | -0.076 |
robat | -0.075 |
Token | with |
Token ID | 351 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
plets | +0.035 |
runway | +0.035 |
ramids | +0.035 |
ifying | +0.034 |
umes | +0.033 |
Neg logit contributions | |
P | -0.026 |
best | -0.022 |
joy | -0.021 |
rob | -0.021 |
robat | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
P | +0.003 |
seeker | +0.002 |
rob | +0.002 |
robat | +0.002 |
joy | +0.002 |
Neg logit contributions | |
runway | -0.002 |
ramids | -0.002 |
ifying | -0.002 |
plets | -0.002 |
uring | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
P | +0.009 |
rob | +0.008 |
robat | +0.008 |
best | +0.008 |
seeker | +0.008 |
Neg logit contributions | |
plets | -0.014 |
ramids | -0.014 |
runway | -0.014 |
ifying | -0.013 |
ured | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
plets | +0.028 |
ramids | +0.027 |
runway | +0.027 |
ifying | +0.026 |
umes | +0.026 |
Neg logit contributions | |
P | -0.023 |
best | -0.020 |
joy | -0.020 |
rob | -0.019 |
robat | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
P | +0.017 |
best | +0.015 |
joy | +0.015 |
rob | +0.015 |
robat | +0.015 |
Neg logit contributions | |
plets | -0.018 |
runway | -0.018 |
ramids | -0.018 |
ifying | -0.017 |
umes | -0.017 |
Token | wheel |
Token ID | 7825 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
P | +0.005 |
rob | +0.004 |
robat | +0.004 |
joy | +0.004 |
best | +0.004 |
Neg logit contributions | |
runway | -0.006 |
plets | -0.006 |
ramids | -0.006 |
ifying | -0.005 |
umes | -0.005 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
P | +0.027 |
best | +0.025 |
rob | +0.024 |
robat | +0.024 |
joy | +0.024 |
Neg logit contributions | |
plets | -0.030 |
ramids | -0.030 |
runway | -0.030 |
ifying | -0.029 |
umes | -0.028 |
Token | row |
Token ID | 808 |
Feature activation | +9.42e-06 |
Pos logit contributions | |
P | +0.180 |
joy | +0.178 |
moderation | +0.163 |
seeker | +0.162 |
rob | +0.160 |
Neg logit contributions | |
plets | -0.101 |
lights | -0.093 |
ric | -0.091 |
runway | -0.090 |
oves | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +5.35e-03 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
plets | +0.010 |
ramids | +0.009 |
runway | +0.009 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.007 |
best | -0.007 |
joy | -0.007 |
my | -0.006 |
moderation | -0.006 |
Token | large |
Token ID | 1588 |
Feature activation | -1.26e-04 |
Pos logit contributions | |
P | +0.015 |
rob | +0.012 |
best | +0.012 |
joy | +0.012 |
robat | +0.012 |
Neg logit contributions | |
plets | -0.019 |
runway | -0.019 |
ramids | -0.019 |
ifying | -0.018 |
umes | -0.018 |
Token | sp |
Token ID | 599 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
P | +0.000 |
rob | +0.000 |
robat | +0.000 |
Deal | +0.000 |
moderation | +0.000 |
Neg logit contributions | |
runway | -0.000 |
plets | -0.000 |
ramids | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | â |
Token ID | 22940 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
P | +0.001 |
joy | +0.001 |
best | +0.001 |
moderation | +0.001 |
my | +0.001 |
Neg logit contributions | |
plets | -0.001 |
runway | -0.001 |
ramids | -0.001 |
ifying | -0.001 |
flies | -0.001 |
Token | € |
Token ID | 26391 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
P | +0.008 |
best | +0.007 |
joy | +0.007 |
seeker | +0.007 |
rob | +0.007 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
runway | -0.010 |
ifying | -0.009 |
ured | -0.009 |
Token | � |
Token ID | 129 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
runway | +0.033 |
ifying | +0.033 |
ured | +0.032 |
plets | +0.032 |
ramids | +0.032 |
Neg logit contributions | |
P | -0.027 |
joy | -0.026 |
my | -0.024 |
rob | -0.023 |
best | -0.023 |
Token | � |
Token ID | 241 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
ifying | +0.006 |
plets | +0.006 |
lights | +0.006 |
runway | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.006 |
right | -0.005 |
Deal | -0.005 |
robat | -0.005 |
best | -0.005 |
Token | This |
Token ID | 1212 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
P | +0.003 |
best | +0.003 |
rob | +0.003 |
joy | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.003 |
umes | -0.003 |
Token | one |
Token ID | 530 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
P | +0.036 |
joy | +0.033 |
Deal | +0.032 |
moderation | +0.032 |
seeker | +0.030 |
Neg logit contributions | |
runway | -0.039 |
plets | -0.036 |
ramids | -0.036 |
ifying | -0.035 |
umes | -0.035 |
Token | please |
Token ID | 3387 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
P | +0.126 |
joy | +0.107 |
rob | +0.107 |
robat | +0.105 |
best | +0.105 |
Neg logit contributions | |
plets | -0.157 |
runway | -0.155 |
ramids | -0.154 |
ifying | -0.150 |
umes | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
P | +0.030 |
best | +0.026 |
rob | +0.025 |
joy | +0.025 |
robat | +0.025 |
Neg logit contributions | |
plets | -0.037 |
runway | -0.037 |
ramids | -0.037 |
ifying | -0.036 |
umes | -0.035 |
Token | â |
Token ID | 22940 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
P | +0.011 |
best | +0.010 |
my | +0.009 |
joy | +0.009 |
seeker | +0.009 |
Neg logit contributions | |
plets | -0.011 |
runway | -0.011 |
ramids | -0.011 |
ifying | -0.010 |
umes | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
P | +0.010 |
joy | +0.009 |
best | +0.009 |
seeker | +0.009 |
rob | +0.009 |
Neg logit contributions | |
plets | -0.012 |
runway | -0.011 |
ramids | -0.011 |
ured | -0.011 |
ifying | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
runway | +0.034 |
plets | +0.033 |
ramids | +0.033 |
ifying | +0.032 |
ured | +0.032 |
Neg logit contributions | |
P | -0.034 |
joy | -0.031 |
seeker | -0.029 |
best | -0.029 |
rob | -0.029 |
Token | |
Token ID | 220 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
P | +0.012 |
best | +0.010 |
rob | +0.010 |
robat | +0.010 |
joy | +0.010 |
Neg logit contributions | |
plets | -0.019 |
ramids | -0.018 |
runway | -0.018 |
ifying | -0.018 |
umes | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
P | +0.004 |
best | +0.003 |
rob | +0.003 |
joy | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.008 |
ramids | -0.008 |
runway | -0.008 |
ifying | -0.008 |
umes | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
P | +0.002 |
seeker | +0.001 |
best | +0.001 |
joy | +0.001 |
rob | +0.001 |
Neg logit contributions | |
plets | -0.002 |
ramids | -0.002 |
runway | -0.002 |
uring | -0.002 |
umes | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
runway | +0.002 |
ramids | +0.002 |
plets | +0.002 |
ifying | +0.002 |
umes | +0.002 |
Neg logit contributions | |
P | -0.003 |
robat | -0.002 |
best | -0.002 |
rob | -0.002 |
moderation | -0.002 |
Token | wheel |
Token ID | 7825 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
P | +0.019 |
rob | +0.016 |
robat | +0.016 |
joy | +0.016 |
best | +0.016 |
Neg logit contributions | |
plets | -0.021 |
runway | -0.021 |
ramids | -0.020 |
ifying | -0.020 |
umes | -0.020 |
Token | bar |
Token ID | 5657 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
P | +0.040 |
best | +0.035 |
joy | +0.034 |
robat | +0.034 |
rob | +0.034 |
Neg logit contributions | |
plets | -0.040 |
ramids | -0.039 |
runway | -0.039 |
ifying | -0.038 |
umes | -0.038 |
Token | row |
Token ID | 808 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
P | +0.171 |
joy | +0.164 |
seeker | +0.156 |
moderation | +0.154 |
rob | +0.151 |
Neg logit contributions | |
plets | -0.109 |
ramids | -0.099 |
runway | -0.098 |
lights | -0.098 |
ric | -0.094 |
Token | wheel |
Token ID | 7825 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
P | +0.003 |
best | +0.003 |
joy | +0.003 |
my | +0.003 |
robat | +0.003 |
Neg logit contributions | |
runway | -0.004 |
ramids | -0.004 |
plets | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | ed |
Token ID | 276 |
Feature activation | +3.53e-04 |
Pos logit contributions | |
P | +0.035 |
best | +0.032 |
robat | +0.031 |
joy | +0.030 |
my | +0.030 |
Neg logit contributions | |
plets | -0.035 |
runway | -0.035 |
ramids | -0.035 |
ifying | -0.034 |
umes | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
plets | +0.001 |
runway | +0.001 |
ramids | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.000 |
joy | -0.000 |
rob | -0.000 |
robat | -0.000 |
Token | cup |
Token ID | 6508 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
P | +0.008 |
rob | +0.006 |
best | +0.006 |
joy | +0.006 |
robat | +0.006 |
Neg logit contributions | |
plets | -0.009 |
runway | -0.009 |
ramids | -0.009 |
ifying | -0.009 |
umes | -0.009 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.33e-04 |
Pos logit contributions | |
P | +0.036 |
Deal | +0.032 |
rob | +0.032 |
robat | +0.032 |
seeker | +0.031 |
Neg logit contributions | |
ramids | -0.028 |
runway | -0.026 |
plets | -0.026 |
ifying | -0.026 |
ured | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
plets | +0.000 |
ramids | +0.000 |
runway | +0.000 |
ifying | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
best | -0.000 |
my | -0.000 |
robat | -0.000 |
joy | -0.000 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
runway | +0.005 |
ramids | +0.005 |
plets | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.005 |
rob | -0.005 |
robat | -0.004 |
joy | -0.004 |
moderation | -0.004 |
Token | one |
Token ID | 530 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
P | +0.014 |
best | +0.012 |
joy | +0.012 |
robat | +0.012 |
seeker | +0.011 |
Neg logit contributions | |
plets | -0.026 |
ramids | -0.025 |
runway | -0.025 |
ifying | -0.025 |
umes | -0.024 |
Token | by |
Token ID | 416 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
P | +0.108 |
rob | +0.094 |
joy | +0.092 |
robat | +0.091 |
seeker | +0.091 |
Neg logit contributions | |
plets | -0.110 |
runway | -0.108 |
ramids | -0.106 |
ifying | -0.105 |
umes | -0.101 |
Token | one |
Token ID | 530 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
P | +0.021 |
rob | +0.018 |
robat | +0.017 |
best | +0.017 |
joy | +0.017 |
Neg logit contributions | |
runway | -0.026 |
plets | -0.026 |
ramids | -0.026 |
ifying | -0.025 |
ured | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
P | +0.135 |
rob | +0.118 |
joy | +0.110 |
seeker | +0.110 |
robat | +0.109 |
Neg logit contributions | |
runway | -0.153 |
plets | -0.152 |
ifying | -0.149 |
ramids | -0.149 |
ured | -0.142 |
Token | made |
Token ID | 925 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
plets | +0.012 |
runway | +0.011 |
ramids | +0.011 |
ifying | +0.011 |
umes | +0.011 |
Neg logit contributions | |
P | -0.012 |
best | -0.011 |
rob | -0.011 |
joy | -0.011 |
robat | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
plets | +0.014 |
runway | +0.013 |
ramids | +0.013 |
ifying | +0.013 |
umes | +0.013 |
Neg logit contributions | |
P | -0.012 |
best | -0.011 |
joy | -0.010 |
rob | -0.010 |
robat | -0.010 |
Token | surrender |
Token ID | 16908 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
plets | +0.041 |
ramids | +0.039 |
umes | +0.037 |
runway | +0.037 |
ifying | +0.037 |
Neg logit contributions | |
best | -0.027 |
P | -0.026 |
joy | -0.024 |
seeker | -0.024 |
idea | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
P | +0.027 |
best | +0.023 |
joy | +0.023 |
rob | +0.022 |
robat | +0.022 |
Neg logit contributions | |
plets | -0.034 |
runway | -0.034 |
ramids | -0.034 |
ifying | -0.033 |
umes | -0.032 |
Token | € |
Token ID | 26391 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
joy | +0.010 |
P | +0.010 |
best | +0.009 |
seeker | +0.009 |
rob | +0.009 |
Neg logit contributions | |
plets | -0.010 |
uring | -0.010 |
ured | -0.010 |
runway | -0.010 |
ifying | -0.009 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
plets | +0.038 |
runway | +0.038 |
ramids | +0.037 |
ifying | +0.036 |
umes | +0.035 |
Neg logit contributions | |
P | -0.055 |
joy | -0.050 |
best | -0.050 |
seeker | -0.049 |
robat | -0.048 |
Token | t |
Token ID | 83 |
Feature activation | -9.36e-03 |
Pos logit contributions | |
P | +0.023 |
best | +0.020 |
joy | +0.020 |
rob | +0.020 |
robat | +0.020 |
Neg logit contributions | |
runway | -0.019 |
plets | -0.019 |
ramids | -0.019 |
ifying | -0.018 |
umes | -0.018 |
Token | an |
Token ID | 281 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
P | +0.013 |
best | +0.012 |
joy | +0.011 |
my | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
ramids | -0.017 |
plets | -0.017 |
ifying | -0.016 |
runway | -0.016 |
umes | -0.016 |
Token | expensive |
Token ID | 5789 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
P | +0.032 |
rob | +0.028 |
joy | +0.027 |
robat | +0.027 |
best | +0.026 |
Neg logit contributions | |
runway | -0.039 |
plets | -0.038 |
ramids | -0.037 |
uring | -0.036 |
ured | -0.036 |
Token | one |
Token ID | 530 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
P | +0.028 |
rob | +0.023 |
moderation | +0.022 |
robat | +0.022 |
Deal | +0.022 |
Neg logit contributions | |
runway | -0.036 |
plets | -0.034 |
ramids | -0.034 |
ured | -0.033 |
uring | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
P | +0.131 |
rob | +0.113 |
joy | +0.110 |
robat | +0.109 |
seeker | +0.108 |
Neg logit contributions | |
plets | -0.152 |
runway | -0.149 |
ramids | -0.148 |
ifying | -0.146 |
umes | -0.143 |
Token | He |
Token ID | 679 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
P | +0.012 |
best | +0.010 |
rob | +0.010 |
robat | +0.010 |
joy | +0.010 |
Neg logit contributions | |
plets | -0.020 |
ramids | -0.019 |
runway | -0.019 |
ifying | -0.019 |
umes | -0.018 |
Token | smiled |
Token ID | 13541 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
P | +0.013 |
best | +0.012 |
joy | +0.011 |
my | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
plets | -0.015 |
ramids | -0.014 |
ifying | -0.014 |
runway | -0.014 |
umes | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
P | +0.013 |
rob | +0.011 |
robat | +0.011 |
moderation | +0.011 |
best | +0.010 |
Neg logit contributions | |
plets | -0.016 |
ramids | -0.016 |
runway | -0.016 |
ifying | -0.016 |
umes | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
P | +0.018 |
best | +0.016 |
rob | +0.015 |
joy | +0.015 |
seeker | +0.015 |
Neg logit contributions | |
plets | -0.025 |
ramids | -0.025 |
runway | -0.025 |
ifying | -0.024 |
umes | -0.024 |
Token | him |
Token ID | 683 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
P | +0.008 |
rob | +0.007 |
best | +0.007 |
joy | +0.007 |
robat | +0.007 |
Neg logit contributions | |
plets | -0.008 |
runway | -0.008 |
ramids | -0.008 |
ifying | -0.007 |
umes | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
P | +0.005 |
best | +0.004 |
my | +0.004 |
seeker | +0.004 |
moderation | +0.004 |
Neg logit contributions | |
plets | -0.007 |
ramids | -0.007 |
runway | -0.006 |
ifying | -0.006 |
umes | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
P | +0.023 |
best | +0.021 |
robat | +0.019 |
joy | +0.019 |
seeker | +0.019 |
Neg logit contributions | |
plets | -0.026 |
ramids | -0.025 |
runway | -0.025 |
ifying | -0.024 |
umes | -0.024 |
Token | grant |
Token ID | 7264 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
plets | +0.034 |
ramids | +0.033 |
runway | +0.032 |
ifying | +0.032 |
umes | +0.031 |
Neg logit contributions | |
P | -0.033 |
best | -0.029 |
seeker | -0.028 |
joy | -0.028 |
robat | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
P | +0.014 |
best | +0.012 |
joy | +0.012 |
rob | +0.012 |
moderation | +0.012 |
Neg logit contributions | |
plets | -0.021 |
ramids | -0.021 |
runway | -0.020 |
ifying | -0.020 |
umes | -0.020 |
Token | one |
Token ID | 530 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
P | +0.029 |
rob | +0.026 |
robat | +0.026 |
joy | +0.024 |
seeker | +0.024 |
Neg logit contributions | |
ifying | -0.030 |
runway | -0.029 |
plets | -0.029 |
ramids | -0.029 |
umes | -0.028 |
Token | wish |
Token ID | 4601 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
P | +0.151 |
rob | +0.142 |
robat | +0.131 |
joy | +0.127 |
seeker | +0.124 |
Neg logit contributions | |
ifying | -0.134 |
runway | -0.129 |
plets | -0.129 |
ured | -0.122 |
umes | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
P | +0.002 |
rob | +0.002 |
joy | +0.002 |
best | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.003 |
runway | -0.003 |
ramids | -0.003 |
ifying | -0.003 |
umes | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
P | +0.009 |
rob | +0.008 |
robat | +0.008 |
seeker | +0.008 |
best | +0.008 |
Neg logit contributions | |
plets | -0.008 |
ramids | -0.008 |
runway | -0.008 |
ifying | -0.007 |
umes | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
P | +0.013 |
rob | +0.011 |
robat | +0.011 |
seeker | +0.011 |
joy | +0.011 |
Neg logit contributions | |
runway | -0.011 |
plets | -0.011 |
ramids | -0.011 |
ifying | -0.011 |
ured | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
runway | +0.033 |
plets | +0.031 |
inated | +0.031 |
as | +0.031 |
bell | +0.030 |
Neg logit contributions | |
P | -0.037 |
rob | -0.036 |
robat | -0.035 |
Deal | -0.031 |
ossible | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
P | +0.022 |
robat | +0.022 |
rob | +0.021 |
ah | +0.020 |
seeker | +0.020 |
Neg logit contributions | |
ramids | -0.021 |
plets | -0.020 |
runway | -0.019 |
ents | -0.019 |
umes | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
plets | +0.021 |
runway | +0.021 |
ramids | +0.021 |
ifying | +0.021 |
umes | +0.020 |
Neg logit contributions | |
P | -0.010 |
best | -0.008 |
joy | -0.008 |
rob | -0.008 |
robat | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
plets | +0.022 |
runway | +0.021 |
ramids | +0.021 |
ifying | +0.021 |
umes | +0.020 |
Neg logit contributions | |
P | -0.010 |
best | -0.008 |
joy | -0.008 |
rob | -0.008 |
robat | -0.008 |
Token | But |
Token ID | 1537 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
plets | +0.023 |
ramids | +0.022 |
runway | +0.022 |
ifying | +0.021 |
umes | +0.021 |
Neg logit contributions | |
P | -0.020 |
joy | -0.019 |
best | -0.019 |
robat | -0.018 |
seeker | -0.018 |
Token | this |
Token ID | 428 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
plets | +0.002 |
runway | +0.002 |
ramids | +0.002 |
ifying | +0.002 |
umes | +0.002 |
Neg logit contributions | |
P | -0.002 |
best | -0.002 |
seeker | -0.002 |
joy | -0.002 |
moderation | -0.002 |
Token | one |
Token ID | 530 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
P | +0.062 |
joy | +0.054 |
rob | +0.051 |
robat | +0.051 |
moderation | +0.050 |
Neg logit contributions | |
runway | -0.069 |
plets | -0.069 |
ramids | -0.068 |
umes | -0.065 |
ifying | -0.064 |
Token | is |
Token ID | 318 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
P | +0.139 |
joy | +0.125 |
rob | +0.119 |
seeker | +0.114 |
robat | +0.113 |
Neg logit contributions | |
plets | -0.140 |
runway | -0.138 |
ramids | -0.133 |
ifying | -0.132 |
keys | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
best | +0.036 |
P | +0.035 |
seeker | +0.031 |
moderation | +0.030 |
my | +0.030 |
Neg logit contributions | |
plets | -0.049 |
runway | -0.046 |
ramids | -0.045 |
ifying | -0.044 |
mic | -0.043 |
Token | best |
Token ID | 1266 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
P | +0.010 |
joy | +0.009 |
rob | +0.009 |
robat | +0.008 |
ability | +0.008 |
Neg logit contributions | |
runway | -0.014 |
ifying | -0.013 |
ramids | -0.013 |
umes | -0.013 |
plets | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
P | +0.031 |
rob | +0.027 |
joy | +0.027 |
robat | +0.026 |
moderation | +0.026 |
Neg logit contributions | |
runway | -0.034 |
plets | -0.034 |
ramids | -0.034 |
ifying | -0.032 |
umes | -0.032 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
P | +0.028 |
best | +0.023 |
joy | +0.023 |
rob | +0.022 |
seeker | +0.022 |
Neg logit contributions | |
plets | -0.050 |
runway | -0.049 |
ramids | -0.049 |
ifying | -0.048 |
umes | -0.047 |
Token | sund |
Token ID | 37437 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
P | +0.029 |
joy | +0.028 |
moderation | +0.026 |
ability | +0.025 |
irrel | +0.025 |
Neg logit contributions | |
plets | -0.032 |
ramids | -0.031 |
ifying | -0.030 |
runway | -0.030 |
drops | -0.030 |
Token | ae |
Token ID | 3609 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
joy | +0.079 |
rob | +0.073 |
P | +0.072 |
irk | +0.067 |
vest | +0.067 |
Neg logit contributions | |
ifying | -0.065 |
plets | -0.063 |
keys | -0.060 |
umes | -0.060 |
runway | -0.059 |
Token | with |
Token ID | 351 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
plets | +0.024 |
runway | +0.024 |
ramids | +0.023 |
ifying | +0.023 |
umes | +0.023 |
Neg logit contributions | |
P | -0.019 |
rob | -0.017 |
joy | -0.016 |
seeker | -0.016 |
robat | -0.016 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
P | +0.004 |
best | +0.003 |
joy | +0.003 |
rob | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.005 |
runway | -0.005 |
ramids | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
runway | +0.023 |
ramids | +0.023 |
plets | +0.023 |
umes | +0.022 |
mic | +0.022 |
Neg logit contributions | |
P | -0.018 |
best | -0.016 |
joy | -0.015 |
moderation | -0.015 |
robat | -0.015 |
Token | topp |
Token ID | 23126 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
ramids | +0.016 |
plets | +0.016 |
ifying | +0.015 |
runway | +0.015 |
umes | +0.015 |
Neg logit contributions | |
P | -0.014 |
seeker | -0.013 |
robat | -0.012 |
joy | -0.012 |
rob | -0.012 |
Token | ings |
Token ID | 654 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
P | +0.159 |
rob | +0.152 |
joy | +0.151 |
seeker | +0.148 |
moderation | +0.147 |
Neg logit contributions | |
ramids | -0.118 |
plets | -0.115 |
ifying | -0.109 |
ants | -0.106 |
ured | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
plets | +0.013 |
ramids | +0.013 |
runway | +0.012 |
ifying | +0.012 |
umes | +0.012 |
Neg logit contributions | |
P | -0.010 |
joy | -0.009 |
best | -0.009 |
rob | -0.008 |
robat | -0.008 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ramids | +0.004 |
plets | +0.004 |
runway | +0.004 |
inated | +0.004 |
ifying | +0.004 |
Neg logit contributions | |
P | -0.004 |
robat | -0.003 |
best | -0.003 |
rob | -0.003 |
seeker | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
P | +0.029 |
joy | +0.028 |
rob | +0.026 |
seeker | +0.025 |
robat | +0.024 |
Neg logit contributions | |
couldn | -0.042 |
ric | -0.042 |
ents | -0.040 |
llers | -0.040 |
ller | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
P | +0.011 |
joy | +0.010 |
rob | +0.010 |
robat | +0.010 |
seeker | +0.010 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
runway | -0.010 |
inated | -0.010 |
ifying | -0.009 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
P | +0.005 |
best | +0.005 |
rob | +0.004 |
robat | +0.004 |
seeker | +0.004 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.005 |
ramids | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
P | +0.014 |
best | +0.013 |
joy | +0.012 |
robat | +0.011 |
my | +0.011 |
Neg logit contributions | |
plets | -0.021 |
ramids | -0.020 |
runway | -0.020 |
ifying | -0.019 |
umes | -0.019 |
Token | display |
Token ID | 3359 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
P | +0.033 |
joy | +0.029 |
best | +0.029 |
rob | +0.028 |
robat | +0.028 |
Neg logit contributions | |
plets | -0.036 |
runway | -0.036 |
ramids | -0.036 |
ifying | -0.035 |
umes | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
P | +0.016 |
best | +0.015 |
joy | +0.014 |
robat | +0.014 |
rob | +0.014 |
Neg logit contributions | |
plets | -0.015 |
runway | -0.015 |
ramids | -0.014 |
ifying | -0.014 |
umes | -0.014 |
Token | show |
Token ID | 905 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
P | +0.004 |
best | +0.004 |
my | +0.003 |
vest | +0.003 |
moderation | +0.003 |
Neg logit contributions | |
plets | -0.005 |
ramids | -0.005 |
ifying | -0.005 |
umes | -0.005 |
runway | -0.005 |
Token | off |
Token ID | 572 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
plets | +0.006 |
runway | +0.005 |
ifying | +0.005 |
ramids | +0.005 |
ulus | +0.005 |
Neg logit contributions | |
best | -0.007 |
P | -0.007 |
my | -0.006 |
joy | -0.006 |
idea | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
plets | +0.174 |
mic | +0.153 |
runway | +0.152 |
ifying | +0.151 |
ender | +0.150 |
Neg logit contributions | |
joy | -0.060 |
best | -0.055 |
P | -0.055 |
his | -0.053 |
my | -0.045 |
Token | her |
Token ID | 607 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
runway | +0.011 |
ramids | +0.010 |
plets | +0.010 |
ured | +0.010 |
ifying | +0.010 |
Neg logit contributions | |
P | -0.013 |
rob | -0.011 |
joy | -0.011 |
robat | -0.011 |
seeker | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
runway | +0.035 |
ramids | +0.034 |
plets | +0.033 |
umes | +0.033 |
ifying | +0.033 |
Neg logit contributions | |
P | -0.019 |
rob | -0.016 |
robat | -0.015 |
joy | -0.015 |
moderation | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
joy | +0.002 |
robat | +0.002 |
rob | +0.002 |
Neg logit contributions | |
plets | -0.004 |
runway | -0.004 |
ramids | -0.004 |
ifying | -0.003 |
umes | -0.003 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
P | +0.004 |
robat | +0.003 |
rob | +0.003 |
seeker | +0.003 |
best | +0.003 |
Neg logit contributions | |
ramids | -0.003 |
inated | -0.003 |
plets | -0.002 |
runway | -0.002 |
umes | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.11e-04 |
Pos logit contributions | |
P | +0.021 |
best | +0.018 |
joy | +0.017 |
rob | +0.017 |
robat | +0.016 |
Neg logit contributions | |
runway | -0.031 |
plets | -0.031 |
ramids | -0.031 |
ifying | -0.030 |
umes | -0.029 |
Token | his |
Token ID | 465 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
ramids | +0.000 |
runway | +0.000 |
ured | +0.000 |
uring | +0.000 |
lights | +0.000 |
Neg logit contributions | |
P | -0.000 |
rob | -0.000 |
robat | -0.000 |
Deal | -0.000 |
seeker | -0.000 |
Token | mother |
Token ID | 2802 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
runway | +0.004 |
ramids | +0.004 |
inated | +0.004 |
ifying | +0.004 |
ller | +0.004 |
Neg logit contributions | |
P | -0.011 |
rob | -0.011 |
robat | -0.010 |
moderation | -0.010 |
Deal | -0.010 |
Token | before |
Token ID | 878 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
plets | +0.010 |
runway | +0.009 |
ramids | +0.009 |
ifying | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.007 |
rob | -0.006 |
best | -0.006 |
joy | -0.006 |
robat | -0.006 |
Token | running |
Token ID | 2491 |
Feature activation | -5.70e-03 |
Pos logit contributions | |
plets | +0.035 |
runway | +0.034 |
ramids | +0.034 |
ifying | +0.033 |
umes | +0.033 |
Neg logit contributions | |
P | -0.035 |
best | -0.030 |
joy | -0.030 |
rob | -0.030 |
robat | -0.030 |
Token | off |
Token ID | 572 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
P | +0.008 |
joy | +0.007 |
best | +0.007 |
robat | +0.007 |
seeker | +0.007 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
runway | -0.010 |
umes | -0.010 |
keys | -0.009 |
Token | again |
Token ID | 757 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
plets | +0.095 |
runway | +0.094 |
ramids | +0.093 |
ifying | +0.091 |
umes | +0.089 |
Neg logit contributions | |
P | -0.072 |
best | -0.062 |
joy | -0.061 |
rob | -0.061 |
robat | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
P | +0.052 |
rob | +0.045 |
robat | +0.044 |
seeker | +0.043 |
best | +0.043 |
Neg logit contributions | |
runway | -0.058 |
plets | -0.058 |
ramids | -0.057 |
ifying | -0.056 |
ured | -0.054 |
Token | He |
Token ID | 679 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
P | +0.011 |
joy | +0.009 |
best | +0.009 |
rob | +0.008 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.021 |
runway | -0.021 |
ramids | -0.021 |
ifying | -0.020 |
umes | -0.020 |
Token | would |
Token ID | 561 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
P | +0.009 |
best | +0.008 |
joy | +0.008 |
rob | +0.007 |
robat | +0.007 |
Neg logit contributions | |
plets | -0.011 |
ramids | -0.011 |
runway | -0.011 |
ifying | -0.011 |
umes | -0.011 |
Token | always |
Token ID | 1464 |
Feature activation | -6.92e-04 |
Pos logit contributions | |
plets | +0.045 |
ramids | +0.043 |
umes | +0.042 |
runway | +0.042 |
ifying | +0.041 |
Neg logit contributions | |
P | -0.031 |
best | -0.029 |
my | -0.028 |
seeker | -0.028 |
joy | -0.027 |
Token | sweep |
Token ID | 16085 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
plets | +0.015 |
runway | +0.015 |
ramids | +0.015 |
ifying | +0.015 |
umes | +0.014 |
Neg logit contributions | |
P | -0.014 |
best | -0.012 |
joy | -0.012 |
rob | -0.012 |
robat | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
plets | +0.038 |
runway | +0.038 |
ramids | +0.037 |
ifying | +0.036 |
umes | +0.035 |
Neg logit contributions | |
P | -0.046 |
best | -0.041 |
rob | -0.040 |
robat | -0.040 |
joy | -0.040 |
Token | flour |
Token ID | 10601 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
plets | +0.036 |
ramids | +0.035 |
runway | +0.035 |
ifying | +0.034 |
umes | +0.034 |
Neg logit contributions | |
P | -0.031 |
best | -0.027 |
joy | -0.026 |
rob | -0.026 |
robat | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
plets | +0.034 |
runway | +0.034 |
ramids | +0.034 |
ifying | +0.033 |
umes | +0.032 |
Neg logit contributions | |
P | -0.028 |
joy | -0.024 |
rob | -0.024 |
best | -0.024 |
robat | -0.024 |
Token | throw |
Token ID | 3714 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
plets | +0.043 |
ramids | +0.043 |
runway | +0.042 |
ifying | +0.041 |
inated | +0.041 |
Neg logit contributions | |
P | -0.032 |
moderation | -0.029 |
best | -0.029 |
my | -0.028 |
joy | -0.026 |
Token | away |
Token ID | 1497 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
P | +0.011 |
best | +0.010 |
moderation | +0.009 |
joy | +0.009 |
rob | +0.009 |
Neg logit contributions | |
runway | -0.010 |
plets | -0.010 |
ramids | -0.009 |
ifying | -0.009 |
umes | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
runway | +0.099 |
plets | +0.098 |
mic | +0.096 |
ramids | +0.094 |
ured | +0.093 |
Neg logit contributions | |
P | -0.079 |
best | -0.074 |
moderation | -0.066 |
my | -0.065 |
joy | -0.063 |
Token | jar |
Token ID | 17379 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
plets | +0.025 |
runway | +0.025 |
ramids | +0.025 |
ifying | +0.024 |
umes | +0.024 |
Neg logit contributions | |
P | -0.020 |
rob | -0.017 |
joy | -0.017 |
robat | -0.017 |
best | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.34e-04 |
Pos logit contributions | |
plets | +0.041 |
ramids | +0.040 |
runway | +0.040 |
ifying | +0.039 |
umes | +0.038 |
Neg logit contributions | |
P | -0.028 |
best | -0.024 |
joy | -0.023 |
rob | -0.023 |
robat | -0.023 |
Token | Then |
Token ID | 3244 |
Feature activation | +6.55e-04 |
Pos logit contributions | |
P | +0.001 |
best | +0.001 |
joy | +0.001 |
seeker | +0.001 |
moderation | +0.001 |
Neg logit contributions | |
keys | -0.001 |
plets | -0.001 |
runway | -0.001 |
ured | -0.001 |
umes | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
plets | +0.001 |
runway | +0.001 |
mic | +0.001 |
ifying | +0.001 |
inated | +0.001 |
Neg logit contributions | |
best | -0.001 |
P | -0.001 |
seeker | -0.001 |
joy | -0.001 |
my | -0.001 |
Token | able |
Token ID | 1498 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
P | +0.013 |
rob | +0.011 |
robat | +0.011 |
joy | +0.011 |
moderation | +0.011 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.013 |
umes | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
plets | +0.015 |
ramids | +0.015 |
runway | +0.015 |
ifying | +0.014 |
inated | +0.014 |
Neg logit contributions | |
best | -0.009 |
P | -0.008 |
joy | -0.008 |
my | -0.008 |
moderation | -0.007 |
Token | watch |
Token ID | 2342 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
plets | +0.012 |
ramids | +0.012 |
umes | +0.012 |
ifying | +0.012 |
lights | +0.011 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
seeker | -0.007 |
my | -0.007 |
robat | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
plets | +0.007 |
ramids | +0.007 |
runway | +0.007 |
ifying | +0.007 |
umes | +0.006 |
Neg logit contributions | |
P | -0.006 |
best | -0.006 |
joy | -0.006 |
robat | -0.006 |
rob | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
ramids | +0.039 |
plets | +0.038 |
ifying | +0.036 |
ured | +0.036 |
runway | +0.036 |
Neg logit contributions | |
P | -0.037 |
best | -0.037 |
joy | -0.033 |
robat | -0.033 |
seeker | -0.032 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
plets | +0.133 |
runway | +0.132 |
ramids | +0.130 |
ifying | +0.127 |
umes | +0.126 |
Neg logit contributions | |
P | -0.055 |
rob | -0.042 |
robat | -0.041 |
best | -0.040 |
joy | -0.039 |
Token | smile |
Token ID | 8212 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
plets | +0.110 |
ramids | +0.107 |
runway | +0.103 |
ifying | +0.101 |
inated | +0.099 |
Neg logit contributions | |
best | -0.064 |
P | -0.062 |
joy | -0.060 |
my | -0.059 |
robat | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
P | +0.003 |
rob | +0.003 |
best | +0.003 |
joy | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.005 |
runway | -0.004 |
ramids | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.005 |
runway | +0.004 |
umes | +0.004 |
ifying | +0.004 |
Neg logit contributions | |
P | -0.003 |
best | -0.003 |
joy | -0.003 |
seeker | -0.003 |
robat | -0.003 |
Token | remember |
Token ID | 3505 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.009 |
runway | +0.009 |
umes | +0.008 |
ifying | +0.008 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
joy | -0.006 |
my | -0.006 |
moderation | -0.006 |
Token | when |
Token ID | 618 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
plets | +0.029 |
ramids | +0.027 |
runway | +0.027 |
ifying | +0.025 |
umes | +0.025 |
Neg logit contributions | |
P | -0.029 |
best | -0.028 |
joy | -0.027 |
moderation | -0.026 |
my | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
P | +0.032 |
seeker | +0.031 |
best | +0.029 |
joy | +0.028 |
rob | +0.028 |
Neg logit contributions | |
plets | -0.039 |
ramids | -0.038 |
inated | -0.037 |
runway | -0.036 |
uring | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ramids | +0.019 |
plets | +0.019 |
runway | +0.018 |
keys | +0.018 |
inated | +0.018 |
Neg logit contributions | |
seeker | -0.018 |
P | -0.017 |
joy | -0.017 |
best | -0.016 |
moderation | -0.016 |
Token | So |
Token ID | 2396 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
plets | +0.017 |
ramids | +0.017 |
ifying | +0.017 |
runway | +0.017 |
umes | +0.016 |
Neg logit contributions | |
P | -0.018 |
Deal | -0.015 |
robat | -0.014 |
best | -0.014 |
rob | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
plets | +0.010 |
runway | +0.010 |
ramids | +0.010 |
umes | +0.009 |
ifying | +0.009 |
Neg logit contributions | |
P | -0.005 |
best | -0.005 |
joy | -0.004 |
seeker | -0.004 |
rob | -0.004 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
plets | +0.020 |
ramids | +0.019 |
runway | +0.018 |
ifying | +0.018 |
umes | +0.018 |
Neg logit contributions | |
P | -0.020 |
best | -0.017 |
seeker | -0.017 |
robat | -0.016 |
my | -0.016 |
Token | off |
Token ID | 572 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
P | +0.003 |
best | +0.003 |
seeker | +0.003 |
joy | +0.003 |
my | +0.003 |
Neg logit contributions | |
plets | -0.004 |
ifying | -0.004 |
keys | -0.004 |
ramids | -0.004 |
umes | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
plets | +0.116 |
ramids | +0.112 |
runway | +0.111 |
ifying | +0.111 |
umes | +0.108 |
Neg logit contributions | |
P | -0.094 |
joy | -0.084 |
best | -0.083 |
rob | -0.079 |
seeker | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
runway | +0.005 |
plets | +0.005 |
ramids | +0.005 |
ifying | +0.005 |
umes | +0.005 |
Neg logit contributions | |
P | -0.004 |
rob | -0.003 |
best | -0.003 |
joy | -0.003 |
robat | -0.003 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
P | +0.002 |
rob | +0.002 |
robat | +0.002 |
joy | +0.002 |
moderation | +0.002 |
Neg logit contributions | |
runway | -0.002 |
ramids | -0.002 |
ured | -0.002 |
ifying | -0.002 |
plets | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
runway | +0.028 |
ramids | +0.027 |
plets | +0.027 |
uring | +0.026 |
umes | +0.026 |
Neg logit contributions | |
P | -0.024 |
rob | -0.021 |
robat | -0.021 |
seeker | -0.020 |
best | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
plets | +0.012 |
ramids | +0.011 |
runway | +0.011 |
ifying | +0.011 |
umes | +0.011 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
seeker | -0.006 |
my | -0.005 |
joy | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
P | +0.019 |
best | +0.018 |
joy | +0.017 |
my | +0.016 |
robat | +0.016 |
Neg logit contributions | |
ramids | -0.033 |
plets | -0.033 |
runway | -0.033 |
umes | -0.032 |
ifying | -0.032 |
Token | |
Token ID | 220 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
P | +0.007 |
joy | +0.006 |
best | +0.006 |
moderation | +0.006 |
rob | +0.006 |
Neg logit contributions | |
runway | -0.009 |
plets | -0.009 |
ramids | -0.009 |
ifying | -0.009 |
umes | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
runway | +0.009 |
plets | +0.009 |
ramids | +0.008 |
ifying | +0.008 |
ured | +0.008 |
Neg logit contributions | |
P | -0.003 |
best | -0.002 |
joy | -0.002 |
my | -0.002 |
moderation | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
plets | +0.003 |
ramids | +0.003 |
runway | +0.002 |
ifying | +0.002 |
umes | +0.002 |
Neg logit contributions | |
P | -0.002 |
best | -0.001 |
rob | -0.001 |
robat | -0.001 |
seeker | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
plets | +0.004 |
runway | +0.004 |
ramids | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.005 |
joy | -0.004 |
robat | -0.003 |
best | -0.003 |
moderation | -0.003 |
Token | smart |
Token ID | 4451 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
P | +0.009 |
best | +0.008 |
joy | +0.007 |
seeker | +0.007 |
robat | +0.007 |
Neg logit contributions | |
plets | -0.011 |
ramids | -0.011 |
runway | -0.011 |
ifying | -0.011 |
umes | -0.010 |
Token | thing |
Token ID | 1517 |
Feature activation | -8.68e-03 |
Pos logit contributions | |
plets | +0.012 |
ramids | +0.012 |
runway | +0.011 |
ifying | +0.011 |
umes | +0.011 |
Neg logit contributions | |
P | -0.007 |
best | -0.006 |
joy | -0.006 |
seeker | -0.006 |
robat | -0.006 |
Token | spun |
Token ID | 26843 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
best | +0.011 |
P | +0.011 |
my | +0.010 |
joy | +0.009 |
robat | +0.009 |
Neg logit contributions | |
ramids | -0.016 |
plets | -0.016 |
runway | -0.016 |
ifying | -0.015 |
umes | -0.015 |
Token | higher |
Token ID | 2440 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
P | +0.005 |
best | +0.005 |
joy | +0.005 |
robat | +0.005 |
my | +0.005 |
Neg logit contributions | |
ramids | -0.007 |
plets | -0.007 |
runway | -0.006 |
umes | -0.006 |
keys | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
P | +0.011 |
best | +0.009 |
joy | +0.009 |
rob | +0.009 |
robat | +0.009 |
Neg logit contributions | |
plets | -0.016 |
runway | -0.016 |
ramids | -0.016 |
ifying | -0.016 |
umes | -0.015 |
Token | higher |
Token ID | 2440 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.006 |
rob | +0.006 |
joy | +0.006 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.006 |
runway | -0.006 |
ramids | -0.006 |
ifying | -0.006 |
umes | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
runway | +0.031 |
ramids | +0.031 |
ifying | +0.030 |
plets | +0.029 |
flashing | +0.029 |
Neg logit contributions | |
P | -0.029 |
rob | -0.026 |
robat | -0.026 |
Deal | -0.026 |
seeker | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
P | +0.029 |
rob | +0.026 |
robat | +0.025 |
moderation | +0.024 |
joy | +0.024 |
Neg logit contributions | |
runway | -0.026 |
ramids | -0.026 |
plets | -0.025 |
umes | -0.025 |
ifying | -0.025 |
Token | school |
Token ID | 1524 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
P | +0.011 |
rob | +0.010 |
robat | +0.010 |
orn | +0.010 |
Deal | +0.010 |
Neg logit contributions | |
runway | -0.007 |
ramids | -0.006 |
uring | -0.006 |
ured | -0.006 |
mic | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
plets | +0.022 |
runway | +0.022 |
ramids | +0.022 |
ifying | +0.021 |
umes | +0.021 |
Neg logit contributions | |
P | -0.015 |
best | -0.012 |
joy | -0.012 |
rob | -0.012 |
robat | -0.012 |
Token | holding |
Token ID | 4769 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
plets | +0.005 |
ramids | +0.005 |
runway | +0.005 |
ifying | +0.005 |
umes | +0.004 |
Neg logit contributions | |
P | -0.003 |
best | -0.003 |
joy | -0.003 |
rob | -0.003 |
robat | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
P | +0.004 |
rob | +0.003 |
Deal | +0.003 |
robat | +0.003 |
joy | +0.003 |
Neg logit contributions | |
ifying | -0.005 |
ramids | -0.005 |
ured | -0.004 |
umes | -0.004 |
runway | -0.004 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
runway | +0.011 |
ifying | +0.011 |
ramids | +0.011 |
plets | +0.011 |
umes | +0.011 |
Neg logit contributions | |
P | -0.011 |
rob | -0.010 |
robat | -0.009 |
orn | -0.009 |
Deal | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
P | +0.012 |
best | +0.011 |
my | +0.011 |
vest | +0.010 |
seeker | +0.010 |
Neg logit contributions | |
plets | -0.023 |
runway | -0.022 |
ramids | -0.021 |
mic | -0.020 |
umes | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
plets | +0.018 |
runway | +0.018 |
ramids | +0.018 |
ifying | +0.017 |
umes | +0.017 |
Neg logit contributions | |
P | -0.017 |
best | -0.015 |
joy | -0.014 |
rob | -0.014 |
robat | -0.014 |
Token | way |
Token ID | 835 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
runway | +0.008 |
ramids | +0.008 |
ifying | +0.008 |
umes | +0.007 |
boarding | +0.007 |
Neg logit contributions | |
P | -0.007 |
rob | -0.007 |
joy | -0.006 |
robat | -0.006 |
Deal | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-03 |
Pos logit contributions | |
plets | +0.052 |
ramids | +0.049 |
runway | +0.049 |
umes | +0.048 |
ifying | +0.048 |
Neg logit contributions | |
P | -0.030 |
best | -0.028 |
my | -0.027 |
joy | -0.026 |
seeker | -0.025 |
Token | field |
Token ID | 2214 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
plets | +0.001 |
ifying | +0.001 |
umes | +0.001 |
ured | +0.001 |
ramids | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.001 |
vest | -0.001 |
my | -0.001 |
joy | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
plets | +0.026 |
runway | +0.026 |
ramids | +0.026 |
ifying | +0.025 |
umes | +0.024 |
Neg logit contributions | |
P | -0.022 |
rob | -0.019 |
robat | -0.018 |
best | -0.018 |
joy | -0.018 |
Token | over |
Token ID | 625 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
plets | +0.007 |
ifying | +0.006 |
ramids | +0.006 |
runway | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.004 |
best | -0.004 |
joy | -0.004 |
seeker | -0.003 |
rob | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
runway | +0.020 |
plets | +0.020 |
ramids | +0.020 |
ifying | +0.019 |
umes | +0.018 |
Neg logit contributions | |
P | -0.029 |
robat | -0.027 |
rob | -0.027 |
seeker | -0.026 |
best | -0.026 |
Token | mountains |
Token ID | 12269 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.009 |
ifying | +0.009 |
ured | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.009 |
best | -0.008 |
seeker | -0.007 |
joy | -0.007 |
my | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
P | +0.005 |
best | +0.004 |
joy | +0.004 |
my | +0.004 |
robat | +0.004 |
Neg logit contributions | |
plets | -0.011 |
ramids | -0.011 |
ifying | -0.011 |
runway | -0.010 |
umes | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
plets | +0.033 |
ifying | +0.033 |
ramids | +0.032 |
runway | +0.032 |
umes | +0.031 |
Neg logit contributions | |
P | -0.032 |
best | -0.029 |
rob | -0.028 |
joy | -0.028 |
my | -0.028 |
Token | sea |
Token ID | 5417 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
plets | +0.032 |
ramids | +0.032 |
runway | +0.031 |
ifying | +0.031 |
umes | +0.030 |
Neg logit contributions | |
P | -0.035 |
best | -0.032 |
joy | -0.031 |
robat | -0.030 |
rob | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
ifying | +0.027 |
ramids | +0.026 |
plets | +0.026 |
runway | +0.026 |
umes | +0.025 |
Neg logit contributions | |
best | -0.011 |
P | -0.010 |
joy | -0.009 |
my | -0.009 |
m | -0.008 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ifying | +0.012 |
plets | +0.012 |
umes | +0.012 |
runway | +0.012 |
ramids | +0.011 |
Neg logit contributions | |
P | -0.009 |
joy | -0.008 |
best | -0.008 |
seeker | -0.008 |
my | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +9.40e-04 |
Pos logit contributions | |
plets | +0.031 |
ramids | +0.031 |
umes | +0.031 |
runway | +0.031 |
ifying | +0.031 |
Neg logit contributions | |
P | -0.032 |
best | -0.030 |
joy | -0.028 |
rob | -0.027 |
moderation | -0.027 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
P | +0.010 |
best | +0.008 |
rob | +0.008 |
joy | +0.008 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.013 |
umes | -0.013 |
Token | pale |
Token ID | 14005 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
plets | +0.021 |
ramids | +0.020 |
runway | +0.020 |
ifying | +0.020 |
umes | +0.019 |
Neg logit contributions | |
P | -0.018 |
rob | -0.016 |
best | -0.015 |
robat | -0.015 |
joy | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
plets | +0.019 |
ramids | +0.019 |
ifying | +0.019 |
runway | +0.019 |
umes | +0.018 |
Neg logit contributions | |
P | -0.017 |
rob | -0.014 |
robat | -0.014 |
moderation | -0.014 |
seeker | -0.013 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
P | +0.014 |
rob | +0.012 |
robat | +0.012 |
best | +0.012 |
joy | +0.012 |
Neg logit contributions | |
plets | -0.013 |
runway | -0.013 |
ramids | -0.013 |
ifying | -0.013 |
umes | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
plets | +0.035 |
runway | +0.035 |
ramids | +0.035 |
ifying | +0.034 |
umes | +0.033 |
Neg logit contributions | |
P | -0.030 |
rob | -0.026 |
robat | -0.025 |
joy | -0.025 |
seeker | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
P | +0.005 |
robat | +0.005 |
rob | +0.005 |
ah | +0.004 |
best | +0.004 |
Neg logit contributions | |
ramids | -0.007 |
ifying | -0.007 |
plets | -0.007 |
runway | -0.007 |
inated | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
plets | +0.024 |
runway | +0.024 |
ramids | +0.023 |
ifying | +0.023 |
umes | +0.023 |
Neg logit contributions | |
P | -0.017 |
best | -0.014 |
my | -0.014 |
rob | -0.014 |
joy | -0.013 |
Token | his |
Token ID | 465 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
rob | +0.005 |
joy | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.010 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
umes | -0.010 |
Token | teeth |
Token ID | 9941 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
P | +0.005 |
rob | +0.004 |
robat | +0.004 |
Deal | +0.004 |
joy | +0.004 |
Neg logit contributions | |
runway | -0.005 |
ramids | -0.004 |
plets | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
plets | +0.026 |
ramids | +0.025 |
runway | +0.025 |
ifying | +0.024 |
umes | +0.024 |
Neg logit contributions | |
P | -0.018 |
best | -0.016 |
joy | -0.015 |
rob | -0.015 |
robat | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
vest | +0.002 |
joy | +0.002 |
my | +0.002 |
Neg logit contributions | |
plets | -0.005 |
ramids | -0.005 |
runway | -0.005 |
umes | -0.005 |
ifying | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
plets | +0.013 |
ifying | +0.012 |
ramids | +0.012 |
runway | +0.012 |
lights | +0.012 |
Neg logit contributions | |
P | -0.005 |
best | -0.005 |
joy | -0.004 |
my | -0.004 |
right | -0.004 |
Token | go |
Token ID | 467 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
plets | +0.030 |
ramids | +0.028 |
ifying | +0.027 |
runway | +0.027 |
umes | +0.027 |
Neg logit contributions | |
P | -0.025 |
best | -0.022 |
seeker | -0.021 |
moderation | -0.021 |
vest | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
P | +0.020 |
Deal | +0.019 |
moderation | +0.019 |
joy | +0.019 |
robat | +0.018 |
Neg logit contributions | |
runway | -0.018 |
uring | -0.017 |
umes | -0.017 |
ramids | -0.017 |
plets | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
plets | +0.040 |
ramids | +0.037 |
ifying | +0.037 |
runway | +0.036 |
umes | +0.036 |
Neg logit contributions | |
P | -0.040 |
best | -0.036 |
joy | -0.036 |
seeker | -0.035 |
rob | -0.035 |
Token | park |
Token ID | 3952 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
plets | +0.020 |
ramids | +0.019 |
runway | +0.019 |
ifying | +0.019 |
umes | +0.018 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
rob | -0.006 |
seeker | -0.006 |
joy | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
runway | +0.004 |
ramids | +0.004 |
uring | +0.003 |
plets | +0.003 |
umes | +0.003 |
Neg logit contributions | |
P | -0.004 |
rob | -0.004 |
robat | -0.004 |
joy | -0.003 |
moderation | -0.003 |
Token | play |
Token ID | 711 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
runway | +0.006 |
ramids | +0.006 |
plets | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.005 |
joy | -0.005 |
best | -0.005 |
rob | -0.005 |
robat | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
joy | +0.018 |
moderation | +0.017 |
icer | +0.017 |
rev | +0.017 |
P | +0.017 |
Neg logit contributions | |
as | -0.011 |
uring | -0.011 |
ured | -0.011 |
runway | -0.010 |
plets | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
plets | +0.015 |
keys | +0.014 |
runway | +0.014 |
ifying | +0.014 |
ramids | +0.014 |
Neg logit contributions | |
P | -0.008 |
my | -0.007 |
joy | -0.007 |
vest | -0.006 |
seeker | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.28e-03 |
Pos logit contributions | |
plets | +0.040 |
ramids | +0.039 |
runway | +0.039 |
ifying | +0.038 |
umes | +0.037 |
Neg logit contributions | |
P | -0.033 |
best | -0.028 |
rob | -0.028 |
joy | -0.028 |
robat | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
P | +0.003 |
best | +0.003 |
joy | +0.003 |
rob | +0.003 |
robat | +0.003 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
P | +0.027 |
best | +0.023 |
rob | +0.023 |
robat | +0.023 |
joy | +0.023 |
Neg logit contributions | |
plets | -0.025 |
ramids | -0.025 |
runway | -0.025 |
ifying | -0.024 |
umes | -0.024 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.57e-04 |
Pos logit contributions | |
P | +0.032 |
best | +0.025 |
rob | +0.024 |
robat | +0.024 |
joy | +0.023 |
Neg logit contributions | |
runway | -0.062 |
plets | -0.062 |
ramids | -0.061 |
ifying | -0.061 |
umes | -0.059 |
Token | shouted |
Token ID | 17293 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
P | +0.000 |
best | +0.000 |
joy | +0.000 |
rob | +0.000 |
robat | +0.000 |
Neg logit contributions | |
plets | -0.000 |
runway | -0.000 |
ramids | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
P | +0.017 |
best | +0.015 |
joy | +0.015 |
seeker | +0.014 |
my | +0.014 |
Neg logit contributions | |
plets | -0.025 |
runway | -0.024 |
ramids | -0.024 |
ifying | -0.024 |
umes | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
plets | +0.015 |
runway | +0.015 |
ramids | +0.014 |
ifying | +0.014 |
umes | +0.014 |
Neg logit contributions | |
P | -0.012 |
rob | -0.010 |
robat | -0.010 |
best | -0.010 |
joy | -0.010 |
Token | threw |
Token ID | 9617 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
P | +0.022 |
best | +0.019 |
rob | +0.019 |
robat | +0.019 |
joy | +0.019 |
Neg logit contributions | |
plets | -0.019 |
ramids | -0.019 |
runway | -0.019 |
ifying | -0.018 |
umes | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
P | +0.051 |
rob | +0.044 |
joy | +0.044 |
robat | +0.043 |
best | +0.043 |
Neg logit contributions | |
runway | -0.050 |
plets | -0.050 |
ramids | -0.050 |
ifying | -0.048 |
umes | -0.046 |
Token | red |
Token ID | 2266 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
plets | +0.022 |
runway | +0.022 |
ramids | +0.021 |
ifying | +0.021 |
umes | +0.020 |
Neg logit contributions | |
P | -0.025 |
joy | -0.022 |
rob | -0.022 |
best | -0.022 |
robat | -0.022 |
Token | rocket |
Token ID | 10701 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
plets | +0.019 |
ramids | +0.019 |
runway | +0.018 |
umes | +0.018 |
ifying | +0.018 |
Neg logit contributions | |
P | -0.018 |
best | -0.016 |
robat | -0.015 |
rob | -0.015 |
joy | -0.015 |
Token | as |
Token ID | 355 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
plets | +0.011 |
ramids | +0.011 |
umes | +0.011 |
runway | +0.010 |
ifying | +0.010 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
my | -0.007 |
vest | -0.007 |
robat | -0.006 |
Token | high |
Token ID | 1029 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
plets | +0.046 |
ramids | +0.045 |
runway | +0.045 |
ifying | +0.044 |
umes | +0.043 |
Neg logit contributions | |
P | -0.041 |
rob | -0.035 |
robat | -0.035 |
joy | -0.035 |
best | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.006 |
rob | +0.005 |
joy | +0.005 |
seeker | +0.005 |
Neg logit contributions | |
plets | -0.010 |
ramids | -0.010 |
runway | -0.010 |
ifying | -0.010 |
umes | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
joy | +0.002 |
rob | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.002 |
runway | -0.002 |
ramids | -0.002 |
ifying | -0.002 |
umes | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
P | +0.008 |
rob | +0.007 |
joy | +0.007 |
best | +0.007 |
robat | +0.007 |
Neg logit contributions | |
plets | -0.011 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
umes | -0.010 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
runway | +0.026 |
plets | +0.026 |
ifying | +0.025 |
drops | +0.024 |
umes | +0.024 |
Neg logit contributions | |
P | -0.022 |
rob | -0.021 |
robat | -0.020 |
moderation | -0.019 |
Deal | -0.019 |
Token | listened |
Token ID | 16399 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
plets | +0.012 |
ramids | +0.012 |
runway | +0.012 |
ifying | +0.012 |
umes | +0.012 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
joy | -0.007 |
my | -0.007 |
seeker | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
plets | +0.025 |
runway | +0.024 |
ramids | +0.023 |
ifying | +0.023 |
umes | +0.023 |
Neg logit contributions | |
P | -0.016 |
best | -0.015 |
joy | -0.014 |
my | -0.013 |
right | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
P | +0.008 |
joy | +0.008 |
best | +0.007 |
my | +0.007 |
seeker | +0.007 |
Neg logit contributions | |
plets | -0.012 |
runway | -0.011 |
ramids | -0.011 |
keys | -0.011 |
ifying | -0.011 |
Token | heard |
Token ID | 2982 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
plets | +0.033 |
ramids | +0.032 |
runway | +0.032 |
ifying | +0.031 |
umes | +0.031 |
Neg logit contributions | |
P | -0.024 |
best | -0.022 |
my | -0.021 |
joy | -0.020 |
robat | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.008 |
runway | +0.008 |
ifying | +0.008 |
inated | +0.008 |
Neg logit contributions | |
best | -0.006 |
P | -0.005 |
joy | -0.005 |
my | -0.005 |
vest | -0.005 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
plets | +0.008 |
runway | +0.008 |
ramids | +0.008 |
ifying | +0.007 |
umes | +0.007 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
rob | -0.007 |
joy | -0.007 |
robat | -0.007 |
Token | singing |
Token ID | 13777 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ramids | +0.027 |
plets | +0.027 |
ifying | +0.026 |
umes | +0.025 |
runway | +0.025 |
Neg logit contributions | |
my | -0.026 |
best | -0.025 |
m | -0.025 |
P | -0.024 |
joy | -0.023 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
P | +0.014 |
best | +0.013 |
joy | +0.012 |
moderation | +0.011 |
my | +0.011 |
Neg logit contributions | |
ramids | -0.018 |
runway | -0.018 |
plets | -0.018 |
umes | -0.017 |
ifying | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
plets | +0.023 |
runway | +0.023 |
ramids | +0.023 |
ifying | +0.022 |
umes | +0.022 |
Neg logit contributions | |
P | -0.014 |
best | -0.012 |
joy | -0.012 |
robat | -0.011 |
rob | -0.011 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
P | +0.015 |
rob | +0.013 |
robat | +0.013 |
seeker | +0.013 |
best | +0.012 |
Neg logit contributions | |
ramids | -0.022 |
plets | -0.021 |
inated | -0.020 |
runway | -0.020 |
ifying | -0.020 |
Token | felt |
Token ID | 2936 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
P | +0.017 |
best | +0.015 |
my | +0.015 |
joy | +0.014 |
rob | +0.014 |
Neg logit contributions | |
plets | -0.025 |
ramids | -0.024 |
runway | -0.024 |
ifying | -0.024 |
umes | -0.023 |
Token | bad |
Token ID | 2089 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
ramids | +0.013 |
runway | +0.013 |
plets | +0.012 |
umes | +0.012 |
mic | +0.011 |
Neg logit contributions | |
P | -0.008 |
best | -0.007 |
moderation | -0.007 |
joy | -0.007 |
right | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
plets | +0.015 |
runway | +0.014 |
ured | +0.014 |
ramids | +0.014 |
uring | +0.014 |
Neg logit contributions | |
P | -0.017 |
moderation | -0.014 |
rob | -0.014 |
robat | -0.014 |
seeker | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
P | +0.023 |
best | +0.021 |
my | +0.019 |
Deal | +0.019 |
joy | +0.019 |
Neg logit contributions | |
plets | -0.035 |
ramids | -0.034 |
runway | -0.034 |
ifying | -0.034 |
umes | -0.033 |
Token | apologised |
Token ID | 46397 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
P | +0.038 |
best | +0.034 |
my | +0.032 |
Deal | +0.031 |
che | +0.030 |
Neg logit contributions | |
plets | -0.057 |
ramids | -0.056 |
runway | -0.056 |
ifying | -0.055 |
umes | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
ramids | +0.006 |
plets | +0.006 |
ured | +0.006 |
runway | +0.006 |
ifying | +0.006 |
Neg logit contributions | |
P | -0.007 |
rob | -0.006 |
robat | -0.006 |
seeker | -0.006 |
moderation | -0.006 |
Token | Sam |
Token ID | 3409 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
P | +0.004 |
rob | +0.003 |
robat | +0.003 |
seeker | +0.003 |
Deal | +0.003 |
Neg logit contributions | |
ramids | -0.005 |
runway | -0.005 |
plets | -0.005 |
uring | -0.004 |
ured | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
P | +0.009 |
rob | +0.008 |
robat | +0.007 |
seeker | +0.007 |
joy | +0.007 |
Neg logit contributions | |
ramids | -0.008 |
runway | -0.008 |
umes | -0.008 |
ured | -0.008 |
plets | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
P | +0.000 |
joy | +0.000 |
rob | +0.000 |
robat | +0.000 |
best | +0.000 |
Neg logit contributions | |
plets | -0.000 |
runway | -0.000 |
ramids | -0.000 |
ifying | -0.000 |
umes | -0.000 |
Token | tag |
Token ID | 7621 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
runway | +0.043 |
uring | +0.041 |
plets | +0.041 |
mic | +0.041 |
ramids | +0.040 |
Neg logit contributions | |
P | -0.042 |
joy | -0.037 |
moderation | -0.036 |
rob | -0.036 |
orn | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.52e-03 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.009 |
runway | +0.008 |
ifying | +0.008 |
umes | +0.008 |
Neg logit contributions | |
P | -0.005 |
best | -0.005 |
rob | -0.005 |
robat | -0.005 |
seeker | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
plets | +0.012 |
keys | +0.012 |
runway | +0.012 |
ifying | +0.011 |
ramids | +0.011 |
Neg logit contributions | |
P | -0.006 |
my | -0.005 |
best | -0.005 |
joy | -0.004 |
ossible | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +2.90e-04 |
Pos logit contributions | |
plets | +0.014 |
runway | +0.014 |
ramids | +0.014 |
umes | +0.013 |
ifying | +0.013 |
Neg logit contributions | |
P | -0.013 |
joy | -0.011 |
rob | -0.011 |
best | -0.011 |
robat | -0.011 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
plets | +0.001 |
ifying | +0.000 |
ramids | +0.000 |
runway | +0.000 |
lights | +0.000 |
Neg logit contributions | |
best | -0.000 |
P | -0.000 |
seeker | -0.000 |
joy | -0.000 |
my | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
P | +0.005 |
rob | +0.005 |
robat | +0.005 |
joy | +0.005 |
best | +0.004 |
Neg logit contributions | |
plets | -0.005 |
runway | -0.005 |
ramids | -0.005 |
ifying | -0.005 |
umes | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
P | +0.037 |
best | +0.033 |
joy | +0.032 |
rob | +0.032 |
robat | +0.032 |
Neg logit contributions | |
plets | -0.037 |
runway | -0.036 |
ramids | -0.036 |
ifying | -0.035 |
umes | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
P | +0.034 |
rob | +0.030 |
robat | +0.029 |
joy | +0.029 |
best | +0.029 |
Neg logit contributions | |
plets | -0.038 |
runway | -0.037 |
ramids | -0.037 |
ifying | -0.036 |
umes | -0.035 |
Token | it |
Token ID | 270 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
P | +0.010 |
joy | +0.009 |
rob | +0.009 |
best | +0.009 |
robat | +0.008 |
Neg logit contributions | |
plets | -0.010 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.010 |
umes | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
P | +0.015 |
best | +0.014 |
my | +0.013 |
seeker | +0.013 |
robat | +0.012 |
Neg logit contributions | |
runway | -0.020 |
plets | -0.020 |
ramids | -0.019 |
lights | -0.019 |
umes | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
P | +0.028 |
rob | +0.024 |
robat | +0.024 |
best | +0.023 |
seeker | +0.023 |
Neg logit contributions | |
plets | -0.044 |
ramids | -0.044 |
runway | -0.043 |
ifying | -0.042 |
umes | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
plets | +0.016 |
runway | +0.016 |
ramids | +0.016 |
ifying | +0.016 |
umes | +0.015 |
Neg logit contributions | |
P | -0.008 |
best | -0.006 |
joy | -0.006 |
rob | -0.006 |
robat | -0.006 |
Token | Mom |
Token ID | 29252 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
plets | +0.009 |
ramids | +0.009 |
ifying | +0.009 |
runway | +0.009 |
umes | +0.009 |
Neg logit contributions | |
P | -0.010 |
best | -0.008 |
my | -0.008 |
moderation | -0.008 |
robat | -0.008 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
P | +0.012 |
moderation | +0.011 |
seeker | +0.011 |
best | +0.011 |
joy | +0.011 |
Neg logit contributions | |
plets | -0.013 |
ramids | -0.013 |
runway | -0.013 |
umes | -0.012 |
ifying | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ramids | +0.024 |
plets | +0.023 |
runway | +0.023 |
ifying | +0.022 |
umes | +0.022 |
Neg logit contributions | |
P | -0.032 |
robat | -0.029 |
rob | -0.029 |
best | -0.028 |
joy | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
ramids | +0.039 |
plets | +0.039 |
runway | +0.039 |
ifying | +0.038 |
umes | +0.038 |
Neg logit contributions | |
P | -0.035 |
rob | -0.030 |
robat | -0.029 |
moderation | -0.028 |
joy | -0.028 |
Token | said |
Token ID | 531 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
P | +0.008 |
robat | +0.007 |
joy | +0.007 |
best | +0.007 |
seeker | +0.007 |
Neg logit contributions | |
plets | -0.012 |
ramids | -0.012 |
runway | -0.012 |
umes | -0.012 |
ifying | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
plets | +0.019 |
ramids | +0.019 |
runway | +0.018 |
umes | +0.018 |
ured | +0.018 |
Neg logit contributions | |
P | -0.013 |
robat | -0.011 |
rob | -0.011 |
moderation | -0.011 |
seeker | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
plets | +0.018 |
runway | +0.018 |
ifying | +0.017 |
ramids | +0.017 |
umes | +0.017 |
Neg logit contributions | |
P | -0.017 |
best | -0.016 |
joy | -0.016 |
rob | -0.015 |
robat | -0.015 |
Token | Okay |
Token ID | 16454 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
plets | +0.028 |
runway | +0.026 |
ramids | +0.026 |
ifying | +0.024 |
umes | +0.024 |
Neg logit contributions | |
seeker | -0.028 |
best | -0.027 |
P | -0.027 |
joy | -0.027 |
idea | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
P | +0.012 |
best | +0.010 |
rob | +0.010 |
joy | +0.010 |
robat | +0.010 |
Neg logit contributions | |
plets | -0.023 |
runway | -0.022 |
ramids | -0.022 |
ifying | -0.022 |
umes | -0.021 |
Token | many |
Token ID | 867 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
plets | +0.022 |
ramids | +0.021 |
runway | +0.020 |
umes | +0.020 |
ifying | +0.020 |
Neg logit contributions | |
P | -0.013 |
best | -0.012 |
seeker | -0.010 |
joy | -0.010 |
moderation | -0.010 |
Token | toys |
Token ID | 14958 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
P | +0.017 |
robat | +0.015 |
rob | +0.015 |
seeker | +0.015 |
joy | +0.015 |
Neg logit contributions | |
runway | -0.017 |
lights | -0.016 |
ramids | -0.016 |
ifying | -0.015 |
plets | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
P | +0.002 |
best | +0.002 |
rob | +0.002 |
joy | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.004 |
umes | -0.004 |
Token | but |
Token ID | 475 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
plets | +0.018 |
runway | +0.018 |
ramids | +0.018 |
ifying | +0.017 |
umes | +0.017 |
Neg logit contributions | |
P | -0.011 |
joy | -0.009 |
rob | -0.009 |
robat | -0.009 |
best | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -4.65e-03 |
Pos logit contributions | |
P | +0.015 |
best | +0.014 |
seeker | +0.013 |
joy | +0.013 |
moderation | +0.013 |
Neg logit contributions | |
plets | -0.011 |
runway | -0.010 |
ramids | -0.010 |
ifying | -0.009 |
umes | -0.009 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
P | +0.006 |
rob | +0.005 |
robat | +0.005 |
joy | +0.005 |
best | +0.005 |
Neg logit contributions | |
runway | -0.008 |
ramids | -0.008 |
plets | -0.008 |
ifying | -0.008 |
umes | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
P | +0.082 |
joy | +0.069 |
rob | +0.068 |
robat | +0.067 |
best | +0.066 |
Neg logit contributions | |
runway | -0.100 |
ramids | -0.100 |
plets | -0.099 |
ifying | -0.096 |
umes | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
P | +0.014 |
best | +0.013 |
my | +0.012 |
joy | +0.012 |
seeker | +0.012 |
Neg logit contributions | |
plets | -0.019 |
runway | -0.018 |
ramids | -0.018 |
ifying | -0.018 |
ured | -0.017 |
Token | big |
Token ID | 1263 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
P | +0.010 |
rob | +0.009 |
robat | +0.009 |
joy | +0.008 |
moderation | +0.008 |
Neg logit contributions | |
runway | -0.013 |
ramids | -0.013 |
plets | -0.013 |
ifying | -0.012 |
umes | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
runway | +0.013 |
ramids | +0.011 |
ifying | +0.010 |
cum | +0.010 |
plets | +0.010 |
Neg logit contributions | |
P | -0.012 |
rob | -0.010 |
robat | -0.009 |
Deal | -0.009 |
ability | -0.009 |
Token | soft |
Token ID | 2705 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
runway | +0.021 |
plets | +0.021 |
ramids | +0.021 |
ifying | +0.021 |
umes | +0.020 |
Neg logit contributions | |
P | -0.017 |
rob | -0.015 |
robat | -0.015 |
joy | -0.015 |
seeker | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
P | +0.031 |
rob | +0.028 |
joy | +0.028 |
best | +0.028 |
robat | +0.028 |
Neg logit contributions | |
plets | -0.020 |
runway | -0.020 |
ramids | -0.019 |
ifying | -0.019 |
umes | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
P | +0.006 |
best | +0.005 |
joy | +0.005 |
rob | +0.005 |
robat | +0.005 |
Neg logit contributions | |
plets | -0.006 |
ramids | -0.006 |
runway | -0.006 |
ifying | -0.006 |
umes | -0.006 |
Token | difference |
Token ID | 3580 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
plets | +0.006 |
ramids | +0.006 |
runway | +0.006 |
ifying | +0.006 |
umes | +0.006 |
Neg logit contributions | |
P | -0.005 |
best | -0.004 |
joy | -0.004 |
robat | -0.004 |
seeker | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
P | +0.034 |
rob | +0.030 |
joy | +0.029 |
robat | +0.029 |
best | +0.029 |
Neg logit contributions | |
plets | -0.036 |
runway | -0.036 |
ramids | -0.035 |
ifying | -0.035 |
umes | -0.034 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
P | +0.011 |
rob | +0.010 |
robat | +0.010 |
best | +0.009 |
seeker | +0.009 |
Neg logit contributions | |
plets | -0.014 |
ramids | -0.014 |
ifying | -0.014 |
runway | -0.014 |
umes | -0.013 |
Token | One |
Token ID | 3198 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
P | +0.002 |
Deal | +0.002 |
moderation | +0.002 |
seeker | +0.002 |
robat | +0.002 |
Neg logit contributions | |
plets | -0.002 |
ifying | -0.002 |
ramids | -0.002 |
runway | -0.002 |
umes | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
P | +0.048 |
rob | +0.039 |
robat | +0.037 |
joy | +0.036 |
seeker | +0.035 |
Neg logit contributions | |
plets | -0.124 |
runway | -0.123 |
ramids | -0.122 |
ifying | -0.121 |
umes | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
runway | +0.004 |
plets | +0.004 |
ramids | +0.004 |
ifying | +0.004 |
umes | +0.004 |
Neg logit contributions | |
P | -0.002 |
best | -0.001 |
joy | -0.001 |
seeker | -0.001 |
rob | -0.001 |
Token | Jack |
Token ID | 3619 |
Feature activation | -8.64e-03 |
Pos logit contributions | |
runway | +0.005 |
plets | +0.005 |
ramids | +0.005 |
umes | +0.005 |
mic | +0.005 |
Neg logit contributions | |
P | -0.003 |
best | -0.003 |
joy | -0.003 |
seeker | -0.003 |
my | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
P | +0.012 |
best | +0.010 |
joy | +0.010 |
rob | +0.010 |
robat | +0.010 |
Neg logit contributions | |
plets | -0.015 |
runway | -0.015 |
ramids | -0.015 |
ifying | -0.014 |
umes | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
runway | +0.017 |
plets | +0.016 |
uring | +0.016 |
ifying | +0.016 |
umes | +0.016 |
Neg logit contributions | |
robat | -0.020 |
rob | -0.020 |
P | -0.020 |
Deal | -0.019 |
orn | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
P | +0.004 |
rob | +0.003 |
best | +0.003 |
robat | +0.003 |
joy | +0.003 |
Neg logit contributions | |
plets | -0.009 |
ramids | -0.009 |
runway | -0.009 |
ifying | -0.009 |
umes | -0.008 |
Token | refrigerator |
Token ID | 30500 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
P | +0.014 |
rob | +0.012 |
robat | +0.012 |
best | +0.012 |
joy | +0.012 |
Neg logit contributions | |
plets | -0.016 |
runway | -0.016 |
ramids | -0.016 |
ifying | -0.015 |
umes | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
plets | +0.017 |
ramids | +0.017 |
runway | +0.017 |
ifying | +0.016 |
umes | +0.016 |
Neg logit contributions | |
P | -0.017 |
best | -0.015 |
joy | -0.015 |
rob | -0.015 |
robat | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
best | +0.011 |
P | +0.010 |
joy | +0.010 |
my | +0.009 |
seeker | +0.009 |
Neg logit contributions | |
plets | -0.015 |
ramids | -0.014 |
runway | -0.014 |
umes | -0.014 |
ifying | -0.013 |
Token | new |
Token ID | 649 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
P | +0.015 |
rob | +0.013 |
robat | +0.013 |
joy | +0.013 |
best | +0.012 |
Neg logit contributions | |
plets | -0.021 |
runway | -0.021 |
ramids | -0.021 |
ifying | -0.021 |
umes | -0.020 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
P | +0.024 |
rob | +0.022 |
robat | +0.020 |
Deal | +0.018 |
moderation | +0.017 |
Neg logit contributions | |
runway | -0.030 |
ramids | -0.029 |
ifying | -0.028 |
inated | -0.028 |
plets | -0.028 |
Token | thing |
Token ID | 1517 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
P | +0.071 |
rob | +0.059 |
joy | +0.057 |
robat | +0.057 |
best | +0.057 |
Neg logit contributions | |
plets | -0.104 |
runway | -0.104 |
ramids | -0.103 |
ifying | -0.101 |
umes | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
P | +0.033 |
best | +0.029 |
joy | +0.028 |
rob | +0.028 |
robat | +0.028 |
Neg logit contributions | |
plets | -0.040 |
runway | -0.039 |
ramids | -0.039 |
ifying | -0.037 |
umes | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
P | +0.009 |
rob | +0.007 |
best | +0.007 |
robat | +0.007 |
joy | +0.007 |
Neg logit contributions | |
plets | -0.013 |
ramids | -0.012 |
runway | -0.012 |
ifying | -0.012 |
umes | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
P | +0.019 |
best | +0.017 |
my | +0.016 |
joy | +0.016 |
vest | +0.015 |
Neg logit contributions | |
plets | -0.024 |
ramids | -0.023 |
ifying | -0.023 |
runway | -0.023 |
umes | -0.022 |
Token | so |
Token ID | 523 |
Feature activation | +2.80e-04 |
Pos logit contributions | |
best | +0.003 |
joy | +0.003 |
P | +0.003 |
my | +0.003 |
seeker | +0.003 |
Neg logit contributions | |
plets | -0.004 |
ramids | -0.004 |
runway | -0.004 |
ifying | -0.004 |
keys | -0.004 |
Token | over |
Token ID | 625 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
plets | +0.001 |
ramids | +0.001 |
runway | +0.001 |
ifying | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.002 |
rob | -0.002 |
best | -0.002 |
robat | -0.002 |
joy | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -7.64e-04 |
Pos logit contributions | |
ifying | +0.023 |
ramids | +0.023 |
runway | +0.022 |
as | +0.022 |
shaped | +0.021 |
Neg logit contributions | |
P | -0.049 |
rob | -0.047 |
robat | -0.046 |
seeker | -0.044 |
Deal | -0.044 |
Token | it |
Token ID | 340 |
Feature activation | +2.16e-04 |
Pos logit contributions | |
P | +0.002 |
rob | +0.001 |
robat | +0.001 |
ests | +0.001 |
best | +0.001 |
Neg logit contributions | |
ured | -0.001 |
ramids | -0.001 |
runway | -0.001 |
uring | -0.001 |
ifying | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
plets | +0.000 |
runway | +0.000 |
ramids | +0.000 |
ifying | +0.000 |
umes | +0.000 |
Neg logit contributions | |
P | -0.000 |
rob | -0.000 |
robat | -0.000 |
seeker | -0.000 |
joy | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
P | +0.019 |
best | +0.016 |
joy | +0.016 |
rob | +0.015 |
my | +0.015 |
Neg logit contributions | |
plets | -0.021 |
runway | -0.021 |
ramids | -0.020 |
ifying | -0.020 |
umes | -0.019 |
Token | one |
Token ID | 530 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
P | +0.005 |
rob | +0.005 |
robat | +0.005 |
Deal | +0.005 |
seeker | +0.005 |
Neg logit contributions | |
ifying | -0.004 |
plets | -0.004 |
runway | -0.004 |
ramids | -0.004 |
ured | -0.004 |
Token | bite |
Token ID | 13197 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
P | +0.127 |
rob | +0.127 |
robat | +0.113 |
seeker | +0.110 |
ests | +0.101 |
Neg logit contributions | |
ifying | -0.106 |
plets | -0.096 |
ured | -0.090 |
as | -0.090 |
inated | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
P | +0.058 |
rob | +0.051 |
robat | +0.049 |
seeker | +0.049 |
joy | +0.048 |
Neg logit contributions | |
plets | -0.078 |
ramids | -0.076 |
ifying | -0.075 |
runway | -0.074 |
umes | -0.073 |
Token | he |
Token ID | 339 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
P | +0.020 |
rob | +0.017 |
robat | +0.017 |
best | +0.016 |
seeker | +0.016 |
Neg logit contributions | |
plets | -0.027 |
ramids | -0.027 |
runway | -0.027 |
ifying | -0.026 |
umes | -0.026 |
Token | slur |
Token ID | 40066 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
P | +0.042 |
best | +0.037 |
joy | +0.036 |
rob | +0.035 |
robat | +0.035 |
Neg logit contributions | |
plets | -0.041 |
runway | -0.041 |
ramids | -0.041 |
ifying | -0.039 |
umes | -0.038 |
Token | ped |
Token ID | 9124 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
P | +0.024 |
best | +0.022 |
rob | +0.022 |
robat | +0.022 |
joy | +0.022 |
Neg logit contributions | |
runway | -0.012 |
plets | -0.012 |
ramids | -0.012 |
ifying | -0.011 |
umes | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
plets | +0.022 |
runway | +0.022 |
ramids | +0.022 |
ifying | +0.021 |
umes | +0.021 |
Neg logit contributions | |
P | -0.019 |
rob | -0.016 |
joy | -0.016 |
robat | -0.016 |
best | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
P | +0.010 |
rob | +0.009 |
best | +0.009 |
robat | +0.009 |
joy | +0.009 |
Neg logit contributions | |
plets | -0.007 |
ramids | -0.007 |
runway | -0.007 |
ifying | -0.007 |
umes | -0.006 |
Token | tray |
Token ID | 26473 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
P | +0.013 |
best | +0.011 |
robat | +0.011 |
seeker | +0.011 |
joy | +0.011 |
Neg logit contributions | |
plets | -0.017 |
ramids | -0.017 |
runway | -0.017 |
ifying | -0.016 |
umes | -0.016 |
Token | broke |
Token ID | 6265 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ramids | +0.018 |
plets | +0.018 |
runway | +0.018 |
umes | +0.017 |
ifying | +0.017 |
Neg logit contributions | |
P | -0.018 |
best | -0.016 |
robat | -0.015 |
seeker | -0.015 |
rob | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
P | +0.015 |
best | +0.013 |
joy | +0.013 |
my | +0.012 |
seeker | +0.012 |
Neg logit contributions | |
runway | -0.025 |
plets | -0.024 |
ramids | -0.024 |
mic | -0.024 |
umes | -0.024 |
Token | half |
Token ID | 2063 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
P | +0.038 |
rob | +0.032 |
robat | +0.032 |
best | +0.032 |
joy | +0.031 |
Neg logit contributions | |
ramids | -0.064 |
plets | -0.064 |
runway | -0.063 |
ifying | -0.062 |
umes | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +5.96e-04 |
Pos logit contributions | |
P | +0.075 |
rob | +0.064 |
best | +0.063 |
joy | +0.063 |
robat | +0.063 |
Neg logit contributions | |
plets | -0.103 |
runway | -0.101 |
ramids | -0.101 |
ifying | -0.099 |
umes | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ramids | +0.001 |
plets | +0.001 |
runway | +0.001 |
mic | +0.001 |
umes | +0.001 |
Neg logit contributions | |
P | -0.001 |
best | -0.001 |
seeker | -0.001 |
joy | -0.001 |
my | -0.001 |
Token | shapes |
Token ID | 15268 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
P | +0.014 |
best | +0.012 |
joy | +0.012 |
rob | +0.012 |
robat | +0.012 |
Neg logit contributions | |
plets | -0.018 |
ramids | -0.018 |
runway | -0.018 |
ifying | -0.017 |
umes | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ramids | +0.007 |
umes | +0.006 |
runway | +0.006 |
plets | +0.006 |
ulus | +0.006 |
Neg logit contributions | |
P | -0.004 |
best | -0.004 |
idea | -0.003 |
m | -0.003 |
joy | -0.003 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
plets | +0.031 |
ramids | +0.031 |
umes | +0.030 |
mic | +0.030 |
runway | +0.030 |
Neg logit contributions | |
P | -0.025 |
best | -0.024 |
my | -0.022 |
joy | -0.022 |
moderation | -0.021 |