Token | and |
Token ID | 290 |
Feature activation | +5.25e-03 |
Pos logit contributions | |
avail | +0.009 |
lor | +0.008 |
sel | +0.008 |
suitcase | +0.008 |
reality | +0.008 |
Neg logit contributions | |
hog | -0.005 |
ranger | -0.005 |
about | -0.005 |
Sharing | -0.005 |
Tim | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
avail | +0.011 |
lor | +0.010 |
reality | +0.010 |
growth | +0.009 |
ucer | +0.009 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.006 |
Token | cloth |
Token ID | 16270 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
avail | +0.046 |
lor | +0.040 |
reality | +0.039 |
growth | +0.036 |
sel | +0.036 |
Neg logit contributions | |
about | -0.036 |
hog | -0.033 |
ranger | -0.032 |
Tim | -0.032 |
: | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.006 |
reality | +0.006 |
suitcase | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.004 |
hog | -0.004 |
ranger | -0.004 |
Tim | -0.004 |
Sharing | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
lor | +0.028 |
avail | +0.026 |
ucer | +0.024 |
reality | +0.024 |
sie | +0.024 |
Neg logit contributions | |
about | -0.018 |
Tim | -0.018 |
Tom | -0.015 |
Mark | -0.015 |
: | -0.015 |
Token | other |
Token ID | 584 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
avail | +0.051 |
lor | +0.045 |
reality | +0.042 |
sel | +0.038 |
growth | +0.038 |
Neg logit contributions | |
about | -0.049 |
hog | -0.045 |
Tim | -0.044 |
ranger | -0.044 |
Sharing | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
avail | +0.134 |
lor | +0.123 |
reality | +0.113 |
growth | +0.104 |
ucer | +0.104 |
Neg logit contributions | |
about | -0.079 |
Tim | -0.066 |
: | -0.065 |
hog | -0.063 |
owner | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
Tim | +0.003 |
ranger | +0.003 |
Sharing | +0.002 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.005 |
sel | -0.004 |
growth | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
avail | +0.017 |
lor | +0.015 |
reality | +0.015 |
growth | +0.013 |
Beck | +0.013 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
avail | +0.019 |
lor | +0.016 |
reality | +0.016 |
suitcase | +0.014 |
sel | +0.014 |
Neg logit contributions | |
about | -0.020 |
hog | -0.019 |
Tim | -0.018 |
ranger | -0.018 |
: | -0.017 |
Token | M |
Token ID | 44 |
Feature activation | +2.85e-04 |
Pos logit contributions | |
avail | +0.008 |
lor | +0.007 |
reality | +0.007 |
suitcase | +0.007 |
ucer | +0.006 |
Neg logit contributions | |
about | -0.007 |
Tim | -0.007 |
hog | -0.007 |
ranger | -0.007 |
Sharing | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
hog | +0.010 |
about | +0.009 |
ranger | +0.009 |
uddy | +0.009 |
aring | +0.009 |
Neg logit contributions | |
avail | -0.020 |
reality | -0.018 |
valleys | -0.017 |
drift | -0.017 |
lor | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.014 |
lor | +0.013 |
growth | +0.012 |
Beck | +0.012 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
ranger | -0.010 |
Sharing | -0.010 |
: | -0.010 |
Token | sailor |
Token ID | 43272 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
avail | +0.041 |
lor | +0.039 |
reality | +0.034 |
ucer | +0.034 |
Beck | +0.033 |
Neg logit contributions | |
about | -0.022 |
old | -0.021 |
owner | -0.020 |
driver | -0.020 |
ranger | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
avail | +0.023 |
lor | +0.022 |
reality | +0.021 |
sel | +0.020 |
awoke | +0.019 |
Neg logit contributions | |
about | -0.020 |
hog | -0.019 |
Sharing | -0.018 |
ranger | -0.018 |
Tim | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
avail | +0.034 |
lor | +0.032 |
reality | +0.030 |
sel | +0.028 |
ucer | +0.028 |
Neg logit contributions | |
about | -0.019 |
Tim | -0.017 |
hog | -0.017 |
ranger | -0.017 |
owner | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
avail | +0.046 |
lor | +0.043 |
reality | +0.038 |
ucer | +0.038 |
growth | +0.038 |
Neg logit contributions | |
about | -0.023 |
old | -0.022 |
owner | -0.021 |
ranger | -0.021 |
driver | -0.021 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
lor | +0.154 |
irs | +0.137 |
avail | +0.134 |
growth | +0.132 |
vation | +0.132 |
Neg logit contributions | |
old | -0.057 |
driver | -0.049 |
Tim | -0.045 |
owner | -0.045 |
elephant | -0.043 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
avail | +0.050 |
lor | +0.044 |
reality | +0.044 |
sel | +0.040 |
suitcase | +0.040 |
Neg logit contributions | |
about | -0.044 |
hog | -0.042 |
ranger | -0.040 |
Sharing | -0.039 |
Tim | -0.039 |
Token | into |
Token ID | 656 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
avail | +0.003 |
lor | +0.002 |
reality | +0.002 |
ucer | +0.002 |
suitcase | +0.002 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
Sharing | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
Tim | +0.010 |
about | +0.009 |
Mark | +0.007 |
ranger | +0.007 |
that | +0.007 |
Neg logit contributions | |
avail | -0.021 |
lor | -0.021 |
ucer | -0.018 |
sel | -0.018 |
reality | -0.018 |
Token | water |
Token ID | 1660 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
Beck | +0.006 |
growth | +0.006 |
Neg logit contributions | |
about | -0.006 |
hog | -0.005 |
ranger | -0.005 |
Tim | -0.005 |
: | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
avail | +0.030 |
lor | +0.026 |
reality | +0.025 |
growth | +0.023 |
suitcase | +0.023 |
Neg logit contributions | |
about | -0.023 |
hog | -0.021 |
ranger | -0.021 |
Tim | -0.020 |
Sharing | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
avail | +0.025 |
lor | +0.022 |
reality | +0.022 |
growth | +0.020 |
ucer | +0.020 |
Neg logit contributions | |
about | -0.016 |
hog | -0.014 |
ranger | -0.014 |
Tim | -0.013 |
Sharing | -0.013 |
Token | teacher |
Token ID | 4701 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
avail | +0.041 |
reality | +0.033 |
lor | +0.032 |
suitcase | +0.029 |
sel | +0.029 |
Neg logit contributions | |
about | -0.057 |
hog | -0.053 |
Tim | -0.051 |
ranger | -0.051 |
Sharing | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
awoke | +0.002 |
lor | +0.002 |
sel | +0.002 |
avail | +0.002 |
reality | +0.002 |
Neg logit contributions | |
Sharing | -0.002 |
hog | -0.002 |
automobiles | -0.002 |
ranger | -0.002 |
disl | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
avail | +0.039 |
reality | +0.034 |
lor | +0.033 |
Beck | +0.031 |
growth | +0.031 |
Neg logit contributions | |
about | -0.029 |
hog | -0.026 |
ranger | -0.025 |
Sharing | -0.024 |
Tim | -0.024 |
Token | little |
Token ID | 1310 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
avail | +0.041 |
lor | +0.036 |
reality | +0.035 |
growth | +0.032 |
ucer | +0.032 |
Neg logit contributions | |
about | -0.027 |
hog | -0.025 |
ranger | -0.024 |
Tim | -0.024 |
Sharing | -0.022 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
lor | +0.107 |
avail | +0.105 |
reality | +0.091 |
growth | +0.087 |
ucer | +0.085 |
Neg logit contributions | |
hog | -0.087 |
about | -0.084 |
ranger | -0.084 |
Tim | -0.081 |
elephant | -0.078 |
Token | talked |
Token ID | 6619 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
avail | +0.034 |
reality | +0.031 |
lor | +0.030 |
sel | +0.029 |
awoke | +0.029 |
Neg logit contributions | |
hog | -0.029 |
about | -0.029 |
ranger | -0.028 |
Sharing | -0.027 |
Tim | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
hog | +0.006 |
ranger | +0.005 |
Sharing | +0.005 |
aring | +0.005 |
anda | +0.005 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.009 |
suitcase | -0.008 |
Avery | -0.008 |
lor | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
about | +0.032 |
hog | +0.029 |
Tim | +0.028 |
ranger | +0.028 |
: | +0.027 |
Neg logit contributions | |
avail | -0.038 |
lor | -0.033 |
reality | -0.032 |
ucer | -0.030 |
sel | -0.029 |
Token | long |
Token ID | 890 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
about | +0.037 |
hog | +0.035 |
ranger | +0.033 |
Tim | +0.033 |
Sharing | +0.032 |
Neg logit contributions | |
avail | -0.037 |
lor | -0.031 |
reality | -0.031 |
suitcase | -0.027 |
Beck | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.004 |
Beck | +0.003 |
reality | +0.003 |
Elsa | +0.003 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.003 |
trucks | -0.002 |
Tim | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.006 |
reality | +0.005 |
Beck | +0.005 |
Elsa | +0.005 |
Neg logit contributions | |
about | -0.007 |
hog | -0.006 |
Tim | -0.006 |
ranger | -0.006 |
trucks | -0.006 |
Token | man |
Token ID | 582 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
avail | +0.021 |
lor | +0.018 |
reality | +0.018 |
growth | +0.017 |
ucer | +0.017 |
Neg logit contributions | |
about | -0.009 |
ranger | -0.008 |
hog | -0.008 |
owner | -0.007 |
Tim | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
lor | +0.004 |
awoke | +0.004 |
sel | +0.004 |
avail | +0.004 |
reality | +0.004 |
Neg logit contributions | |
Sharing | -0.004 |
about | -0.004 |
automobiles | -0.003 |
disl | -0.003 |
hog | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
avail | +0.064 |
lor | +0.062 |
reality | +0.056 |
ucer | +0.053 |
sel | +0.053 |
Neg logit contributions | |
about | -0.058 |
Tim | -0.055 |
hog | -0.053 |
ranger | -0.053 |
owner | -0.050 |
Token | little |
Token ID | 1310 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
avail | +0.050 |
lor | +0.045 |
reality | +0.042 |
growth | +0.041 |
ucer | +0.041 |
Neg logit contributions | |
about | -0.022 |
ranger | -0.022 |
hog | -0.021 |
old | -0.021 |
owner | -0.021 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
lor | +0.121 |
avail | +0.113 |
reality | +0.108 |
growth | +0.106 |
ucer | +0.103 |
Neg logit contributions | |
ranger | -0.070 |
hog | -0.070 |
Tim | -0.067 |
old | -0.067 |
about | -0.067 |
Token | set |
Token ID | 900 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
avail | +0.047 |
lor | +0.041 |
reality | +0.040 |
sel | +0.038 |
suitcase | +0.037 |
Neg logit contributions | |
about | -0.044 |
hog | -0.042 |
ranger | -0.040 |
Sharing | -0.040 |
Tim | -0.039 |
Token | off |
Token ID | 572 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
avail | +0.023 |
lor | +0.021 |
reality | +0.021 |
Elsa | +0.018 |
ucer | +0.018 |
Neg logit contributions | |
about | -0.018 |
Tim | -0.017 |
: | -0.016 |
hog | -0.015 |
ranger | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.025 |
reality | +0.025 |
growth | +0.023 |
suitcase | +0.023 |
Neg logit contributions | |
about | -0.018 |
hog | -0.017 |
ranger | -0.016 |
Tim | -0.016 |
Sharing | -0.015 |
Token | explore |
Token ID | 7301 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
lor | +0.022 |
avail | +0.021 |
ucer | +0.019 |
reality | +0.019 |
Elsa | +0.019 |
Neg logit contributions | |
about | -0.016 |
Tim | -0.015 |
not | -0.014 |
Mark | -0.013 |
: | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
hog | +0.007 |
about | +0.007 |
ranger | +0.006 |
Sharing | +0.006 |
Tim | +0.006 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.011 |
lor | -0.010 |
Beck | -0.010 |
Avery | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
avail | +0.002 |
reality | +0.002 |
suitcase | +0.002 |
lor | +0.002 |
Avery | +0.002 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
Tim | -0.002 |
Sharing | -0.002 |
Token | princess |
Token ID | 21752 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
avail | +0.049 |
lor | +0.046 |
reality | +0.040 |
growth | +0.039 |
ucer | +0.038 |
Neg logit contributions | |
about | -0.047 |
hog | -0.043 |
Tim | -0.043 |
ranger | -0.043 |
owner | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
avail | +0.042 |
lor | +0.037 |
reality | +0.037 |
suitcase | +0.033 |
sel | +0.033 |
Neg logit contributions | |
about | -0.030 |
hog | -0.028 |
Tim | -0.027 |
ranger | -0.027 |
Sharing | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.005 |
aring | +0.005 |
ike | +0.004 |
Neg logit contributions | |
avail | -0.009 |
lor | -0.007 |
reality | -0.007 |
suitcase | -0.007 |
Beck | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
avail | +0.050 |
lor | +0.046 |
ucer | +0.042 |
growth | +0.042 |
reality | +0.041 |
Neg logit contributions | |
about | -0.023 |
ranger | -0.019 |
owner | -0.019 |
old | -0.019 |
driver | -0.018 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
lor | +0.121 |
avail | +0.119 |
growth | +0.109 |
irs | +0.104 |
pped | +0.102 |
Neg logit contributions | |
old | -0.070 |
about | -0.069 |
owner | -0.066 |
ranger | -0.064 |
driver | -0.064 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
awoke | +0.038 |
reality | +0.034 |
suitcase | +0.034 |
Beck | +0.033 |
sel | +0.033 |
Neg logit contributions | |
ranger | -0.036 |
hog | -0.035 |
aring | -0.034 |
ooters | -0.034 |
automobiles | -0.034 |
Token | when |
Token ID | 618 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
hog | +0.029 |
aring | +0.027 |
Sharing | +0.026 |
ranger | +0.025 |
about | +0.025 |
Neg logit contributions | |
avail | -0.028 |
reality | -0.025 |
veil | -0.022 |
Avery | -0.022 |
anything | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
avail | +0.016 |
lor | +0.015 |
reality | +0.014 |
sel | +0.013 |
ucer | +0.013 |
Neg logit contributions | |
about | -0.015 |
Tim | -0.014 |
ranger | -0.013 |
hog | -0.013 |
: | -0.012 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.013 |
reality | +0.013 |
growth | +0.012 |
ucer | +0.012 |
Neg logit contributions | |
about | -0.006 |
hog | -0.006 |
ranger | -0.005 |
Tim | -0.005 |
: | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
about | +0.009 |
hog | +0.009 |
automobiles | +0.009 |
Sharing | +0.009 |
aring | +0.008 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.013 |
lor | -0.013 |
awoke | -0.012 |
suitcase | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
avail | +0.055 |
lor | +0.053 |
growth | +0.048 |
reality | +0.046 |
sel | +0.046 |
Neg logit contributions | |
about | -0.025 |
Tim | -0.024 |
not | -0.018 |
Mark | -0.018 |
that | -0.018 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
avail | +0.045 |
lor | +0.040 |
reality | +0.039 |
sel | +0.036 |
growth | +0.036 |
Neg logit contributions | |
about | -0.029 |
hog | -0.026 |
ranger | -0.025 |
Tim | -0.025 |
: | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.002 |
sel | +0.002 |
awoke | +0.002 |
reality | +0.002 |
Neg logit contributions | |
Sharing | -0.002 |
about | -0.002 |
hog | -0.002 |
aring | -0.002 |
meanings | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
lor | +0.078 |
avail | +0.078 |
growth | +0.066 |
sel | +0.065 |
reality | +0.065 |
Neg logit contributions | |
about | -0.045 |
Tim | -0.042 |
old | -0.035 |
: | -0.033 |
ranger | -0.033 |
Token | little |
Token ID | 1310 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
avail | +0.040 |
lor | +0.036 |
reality | +0.034 |
growth | +0.032 |
sel | +0.032 |
Neg logit contributions | |
about | -0.027 |
hog | -0.025 |
ranger | -0.024 |
Tim | -0.024 |
: | -0.022 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
lor | +0.118 |
avail | +0.111 |
growth | +0.098 |
reality | +0.096 |
ucer | +0.092 |
Neg logit contributions | |
Tim | -0.073 |
about | -0.071 |
hog | -0.070 |
ranger | -0.068 |
old | -0.067 |
Token | found |
Token ID | 1043 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
avail | +0.042 |
reality | +0.039 |
lor | +0.038 |
suitcase | +0.037 |
sel | +0.036 |
Neg logit contributions | |
about | -0.035 |
hog | -0.034 |
ranger | -0.032 |
Sharing | -0.032 |
aring | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.016 |
Beck | +0.014 |
growth | +0.014 |
Neg logit contributions | |
about | -0.013 |
Tim | -0.012 |
hog | -0.012 |
ranger | -0.011 |
: | -0.011 |
Token | spot |
Token ID | 4136 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.006 |
Tim | +0.006 |
ranger | +0.006 |
Sharing | +0.006 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
reality | -0.007 |
suitcase | -0.006 |
ucer | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
avail | +0.005 |
reality | +0.004 |
lor | +0.004 |
ucer | +0.004 |
suitcase | +0.004 |
Neg logit contributions | |
about | -0.003 |
Sharing | -0.003 |
hog | -0.003 |
Tim | -0.002 |
ranger | -0.002 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
hog | +0.021 |
ranger | +0.019 |
about | +0.018 |
aring | +0.018 |
ooters | +0.017 |
Neg logit contributions | |
avail | -0.028 |
reality | -0.024 |
Avery | -0.022 |
Clare | -0.021 |
lor | -0.021 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
about | +0.028 |
hog | +0.026 |
Tim | +0.026 |
ranger | +0.026 |
: | +0.025 |
Neg logit contributions | |
avail | -0.018 |
lor | -0.015 |
reality | -0.014 |
growth | -0.013 |
ucer | -0.012 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
avail | +0.043 |
lor | +0.037 |
reality | +0.037 |
growth | +0.035 |
ucer | +0.034 |
Neg logit contributions | |
about | -0.029 |
hog | -0.025 |
Tim | -0.025 |
ranger | -0.024 |
: | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.003 |
reality | +0.003 |
Beck | +0.003 |
growth | +0.003 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
Tim | -0.002 |
Sharing | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
avail | +0.028 |
lor | +0.025 |
reality | +0.025 |
growth | +0.023 |
sel | +0.023 |
Neg logit contributions | |
about | -0.014 |
hog | -0.013 |
ranger | -0.012 |
Tim | -0.012 |
Sharing | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
avail | +0.036 |
lor | +0.031 |
reality | +0.030 |
growth | +0.027 |
suitcase | +0.027 |
Neg logit contributions | |
about | -0.030 |
hog | -0.028 |
ranger | -0.027 |
Tim | -0.027 |
Sharing | -0.026 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
avail | +0.095 |
lor | +0.091 |
reality | +0.082 |
growth | +0.077 |
ucer | +0.073 |
Neg logit contributions | |
about | -0.093 |
hog | -0.090 |
Tim | -0.087 |
ranger | -0.087 |
: | -0.083 |
Token | nodded |
Token ID | 14464 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
avail | +0.035 |
Avery | +0.032 |
awoke | +0.031 |
reality | +0.030 |
Beck | +0.030 |
Neg logit contributions | |
automobiles | -0.030 |
ranger | -0.030 |
hog | -0.030 |
trucks | -0.028 |
ooters | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
avail | +0.031 |
lor | +0.028 |
reality | +0.027 |
ucer | +0.025 |
growth | +0.025 |
Neg logit contributions | |
about | -0.017 |
Tim | -0.014 |
: | -0.014 |
hog | -0.014 |
ranger | -0.013 |
Token | gazing |
Token ID | 50234 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
hog | +0.002 |
ranger | +0.002 |
about | +0.002 |
uddy | +0.002 |
automobiles | +0.002 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
lor | -0.003 |
Avery | -0.003 |
suitcase | -0.003 |
Token | up |
Token ID | 510 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
avail | +0.106 |
lor | +0.095 |
reality | +0.094 |
suitcase | +0.087 |
sel | +0.086 |
Neg logit contributions | |
about | -0.054 |
hog | -0.049 |
ranger | -0.047 |
Tim | -0.046 |
Sharing | -0.043 |
Token | father |
Token ID | 2988 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
avail | +0.009 |
reality | +0.008 |
lor | +0.007 |
suitcase | +0.007 |
Beck | +0.007 |
Neg logit contributions | |
about | -0.007 |
hog | -0.006 |
ranger | -0.006 |
Sharing | -0.006 |
Tim | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.013 |
reality | +0.012 |
sel | +0.012 |
ucer | +0.012 |
Neg logit contributions | |
about | -0.007 |
hog | -0.007 |
ranger | -0.006 |
Tim | -0.006 |
Sharing | -0.006 |
Token | daughter |
Token ID | 4957 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
lor | +0.027 |
avail | +0.026 |
arse | +0.024 |
ices | +0.023 |
vation | +0.023 |
Neg logit contributions | |
Tim | -0.011 |
about | -0.010 |
old | -0.009 |
that | -0.009 |
not | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
avail | +0.060 |
lor | +0.054 |
reality | +0.053 |
growth | +0.049 |
sel | +0.049 |
Neg logit contributions | |
about | -0.024 |
hog | -0.021 |
Tim | -0.020 |
ranger | -0.020 |
: | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
ranger | +0.005 |
aring | +0.005 |
: | +0.005 |
Neg logit contributions | |
avail | -0.011 |
growth | -0.009 |
reality | -0.009 |
lor | -0.009 |
Beck | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
avail | +0.040 |
lor | +0.039 |
reality | +0.034 |
growth | +0.034 |
ucer | +0.033 |
Neg logit contributions | |
about | -0.019 |
owner | -0.019 |
old | -0.018 |
driver | -0.017 |
Tim | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
lor | +0.135 |
avail | +0.121 |
growth | +0.118 |
reality | +0.115 |
irs | +0.111 |
Neg logit contributions | |
old | -0.062 |
owner | -0.059 |
Tim | -0.057 |
and | -0.053 |
elephant | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
awoke | +0.028 |
sel | +0.027 |
Beck | +0.026 |
suitcase | +0.026 |
aire | +0.026 |
Neg logit contributions | |
hog | -0.032 |
ranger | -0.031 |
aring | -0.031 |
about | -0.030 |
automobiles | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.009 |
reality | -0.009 |
suitcase | -0.008 |
Beck | -0.008 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
ranger | +0.013 |
Sharing | +0.013 |
Tim | +0.013 |
Neg logit contributions | |
avail | -0.024 |
reality | -0.021 |
lor | -0.020 |
Beck | -0.019 |
ucer | -0.019 |
Token | because |
Token ID | 780 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
avail | +0.004 |
reality | +0.004 |
lor | +0.003 |
suitcase | +0.003 |
ucer | +0.003 |
Neg logit contributions | |
hog | -0.002 |
ranger | -0.002 |
Sharing | -0.002 |
about | -0.002 |
Tim | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
avail | +0.011 |
reality | +0.009 |
lor | +0.009 |
growth | +0.008 |
sel | +0.008 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Sharing | -0.007 |
Tim | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
avail | +0.011 |
reality | +0.010 |
lor | +0.010 |
suitcase | +0.009 |
sel | +0.009 |
Neg logit contributions | |
about | -0.009 |
hog | -0.009 |
ranger | -0.008 |
Tim | -0.008 |
Sharing | -0.008 |
Token | brother |
Token ID | 3956 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
avail | +0.007 |
reality | +0.006 |
lor | +0.006 |
suitcase | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Sharing | -0.007 |
Tim | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
avail | +0.027 |
lor | +0.024 |
reality | +0.023 |
sel | +0.023 |
suitcase | +0.022 |
Neg logit contributions | |
about | -0.023 |
Sharing | -0.022 |
hog | -0.022 |
ranger | -0.021 |
automobiles | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.002 |
automobiles | +0.002 |
trucks | +0.002 |
Neg logit contributions | |
avail | -0.002 |
lor | -0.002 |
Avery | -0.002 |
growth | -0.002 |
aire | -0.002 |
Token | two |
Token ID | 734 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
avail | +0.045 |
lor | +0.040 |
reality | +0.039 |
growth | +0.036 |
ucer | +0.036 |
Neg logit contributions | |
about | -0.026 |
hog | -0.023 |
ranger | -0.022 |
Tim | -0.022 |
Sharing | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
avail | +0.125 |
lor | +0.113 |
reality | +0.109 |
growth | +0.102 |
ucer | +0.101 |
Neg logit contributions | |
about | -0.065 |
hog | -0.057 |
Tim | -0.055 |
ranger | -0.054 |
: | -0.051 |
Token | them |
Token ID | 606 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
avail | +0.050 |
lor | +0.042 |
reality | +0.042 |
growth | +0.037 |
Beck | +0.037 |
Neg logit contributions | |
about | -0.055 |
hog | -0.052 |
ranger | -0.050 |
Tim | -0.049 |
Sharing | -0.048 |
Token | polished |
Token ID | 23895 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
about | +0.016 |
Sharing | +0.015 |
hog | +0.015 |
ranger | +0.015 |
aring | +0.014 |
Neg logit contributions | |
avail | -0.017 |
reality | -0.015 |
sel | -0.015 |
lor | -0.014 |
suitcase | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
avail | +0.011 |
reality | +0.009 |
lor | +0.009 |
suitcase | +0.008 |
sel | +0.008 |
Neg logit contributions | |
about | -0.008 |
hog | -0.008 |
ranger | -0.008 |
Sharing | -0.007 |
Tim | -0.007 |
Token | belt |
Token ID | 10999 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.004 |
reality | +0.004 |
Beck | +0.004 |
growth | +0.004 |
Neg logit contributions | |
about | -0.002 |
old | -0.002 |
owner | -0.002 |
ranger | -0.002 |
driver | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
about | +0.021 |
hog | +0.019 |
Tim | +0.019 |
ranger | +0.019 |
: | +0.018 |
Neg logit contributions | |
avail | -0.024 |
lor | -0.021 |
reality | -0.020 |
growth | -0.018 |
ucer | -0.018 |
Token | little |
Token ID | 1310 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
avail | +0.010 |
reality | +0.009 |
lor | +0.009 |
suitcase | +0.008 |
growth | +0.008 |
Neg logit contributions | |
about | -0.008 |
hog | -0.008 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
lor | +0.064 |
avail | +0.060 |
reality | +0.054 |
growth | +0.054 |
ucer | +0.053 |
Neg logit contributions | |
about | -0.057 |
Tim | -0.056 |
ranger | -0.056 |
hog | -0.055 |
owner | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
avail | +0.050 |
reality | +0.046 |
lor | +0.046 |
sel | +0.042 |
suitcase | +0.042 |
Neg logit contributions | |
about | -0.028 |
hog | -0.027 |
ranger | -0.026 |
Tim | -0.025 |
Sharing | -0.024 |
Token | The |
Token ID | 383 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
about | +0.004 |
trucks | +0.003 |
hog | +0.003 |
ranger | +0.003 |
aring | +0.003 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.005 |
Beck | -0.005 |
Avery | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
avail | +0.044 |
lor | +0.040 |
reality | +0.037 |
growth | +0.035 |
ucer | +0.035 |
Neg logit contributions | |
about | -0.029 |
hog | -0.026 |
ranger | -0.026 |
Tim | -0.026 |
owner | -0.024 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
lor | +0.108 |
avail | +0.102 |
growth | +0.091 |
reality | +0.090 |
ucer | +0.088 |
Neg logit contributions | |
about | -0.078 |
Tim | -0.077 |
ranger | -0.075 |
old | -0.075 |
owner | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | +3.53e-03 |
Pos logit contributions | |
awoke | +0.029 |
lor | +0.029 |
reality | +0.028 |
avail | +0.027 |
sel | +0.027 |
Neg logit contributions | |
automobiles | -0.036 |
Sharing | -0.034 |
about | -0.034 |
ooters | -0.034 |
trucks | -0.034 |
Token | so |
Token ID | 523 |
Feature activation | -9.76e-04 |
Pos logit contributions | |
avail | +0.007 |
reality | +0.007 |
lor | +0.007 |
suitcase | +0.006 |
Beck | +0.006 |
Neg logit contributions | |
hog | -0.004 |
ranger | -0.004 |
trucks | -0.004 |
Sharing | -0.004 |
about | -0.004 |
Token | excited |
Token ID | 6568 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
trucks | +0.001 |
hog | +0.001 |
automobiles | +0.001 |
about | +0.001 |
ranger | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
lor | -0.002 |
Beck | -0.002 |
Avery | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
hog | +0.007 |
Sharing | +0.006 |
ranger | +0.006 |
about | +0.006 |
moms | +0.006 |
Neg logit contributions | |
avail | -0.012 |
lor | -0.010 |
reality | -0.010 |
Avery | -0.009 |
suitcase | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
avail | +0.020 |
lor | +0.018 |
reality | +0.017 |
Beck | +0.015 |
growth | +0.015 |
Neg logit contributions | |
about | -0.018 |
hog | -0.016 |
ranger | -0.016 |
Tim | -0.016 |
Sharing | -0.015 |
Token | rich |
Token ID | 5527 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.015 |
ucer | +0.014 |
growth | +0.014 |
Neg logit contributions | |
about | -0.010 |
hog | -0.009 |
ranger | -0.009 |
Tim | -0.009 |
: | -0.008 |
Token | man |
Token ID | 582 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
avail | +0.003 |
lor | +0.003 |
reality | +0.003 |
suitcase | +0.003 |
sel | +0.003 |
Neg logit contributions | |
about | -0.002 |
hog | -0.001 |
Tim | -0.001 |
ranger | -0.001 |
Sharing | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
about | +0.003 |
Sharing | +0.003 |
automobiles | +0.003 |
hog | +0.003 |
ooters | +0.002 |
Neg logit contributions | |
avail | -0.003 |
lor | -0.003 |
awoke | -0.003 |
reality | -0.003 |
sel | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
avail | +0.044 |
reality | +0.038 |
lor | +0.038 |
growth | +0.034 |
suitcase | +0.034 |
Neg logit contributions | |
about | -0.032 |
hog | -0.029 |
ranger | -0.028 |
Tim | -0.028 |
Sharing | -0.027 |
Token | little |
Token ID | 1310 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
avail | +0.042 |
lor | +0.038 |
reality | +0.036 |
ucer | +0.034 |
growth | +0.034 |
Neg logit contributions | |
about | -0.024 |
hog | -0.022 |
ranger | -0.022 |
Tim | -0.021 |
owner | -0.020 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
lor | +0.121 |
avail | +0.107 |
growth | +0.101 |
reality | +0.101 |
ucer | +0.100 |
Neg logit contributions | |
ranger | -0.070 |
old | -0.067 |
hog | -0.066 |
Tim | -0.065 |
owner | -0.064 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
avail | +0.034 |
reality | +0.032 |
lor | +0.030 |
sel | +0.030 |
awoke | +0.029 |
Neg logit contributions | |
about | -0.032 |
hog | -0.031 |
ranger | -0.030 |
Sharing | -0.029 |
aring | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.026 |
reality | +0.026 |
growth | +0.023 |
suitcase | +0.023 |
Neg logit contributions | |
about | -0.017 |
hog | -0.016 |
ranger | -0.015 |
Tim | -0.015 |
Sharing | -0.014 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
avail | +0.007 |
reality | +0.006 |
lor | +0.006 |
suitcase | +0.006 |
growth | +0.006 |
Neg logit contributions | |
about | -0.004 |
hog | -0.004 |
ranger | -0.004 |
Tim | -0.004 |
Sharing | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
avail | +0.005 |
lor | +0.005 |
reality | +0.005 |
growth | +0.004 |
ucer | +0.004 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
Tim | -0.002 |
ranger | -0.002 |
: | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
about | +0.005 |
hog | +0.004 |
Tim | +0.004 |
ranger | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.006 |
lor | -0.005 |
reality | -0.005 |
growth | -0.005 |
sel | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
avail | +0.042 |
lor | +0.039 |
reality | +0.036 |
growth | +0.035 |
sel | +0.035 |
Neg logit contributions | |
about | -0.023 |
hog | -0.020 |
ranger | -0.020 |
Tim | -0.020 |
owner | -0.019 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
avail | +0.036 |
lor | +0.031 |
reality | +0.030 |
growth | +0.027 |
suitcase | +0.027 |
Neg logit contributions | |
about | -0.032 |
hog | -0.030 |
ranger | -0.029 |
Tim | -0.029 |
Sharing | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
avail | +0.038 |
reality | +0.036 |
lor | +0.036 |
suitcase | +0.034 |
awoke | +0.034 |
Neg logit contributions | |
hog | -0.024 |
about | -0.024 |
ranger | -0.023 |
Sharing | -0.023 |
automobiles | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
avail | +0.043 |
lor | +0.038 |
reality | +0.037 |
growth | +0.034 |
sel | +0.034 |
Neg logit contributions | |
about | -0.034 |
hog | -0.031 |
Tim | -0.030 |
ranger | -0.030 |
Sharing | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
avail | +0.046 |
lor | +0.042 |
reality | +0.039 |
growth | +0.037 |
sel | +0.037 |
Neg logit contributions | |
about | -0.026 |
hog | -0.024 |
ranger | -0.024 |
Tim | -0.023 |
owner | -0.022 |
Token | sister |
Token ID | 6621 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
lor | +0.117 |
avail | +0.105 |
growth | +0.098 |
ucer | +0.091 |
reality | +0.090 |
Neg logit contributions | |
Tim | -0.074 |
about | -0.073 |
hog | -0.073 |
ranger | -0.071 |
old | -0.070 |
Token | played |
Token ID | 2826 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
avail | +0.044 |
reality | +0.040 |
lor | +0.039 |
suitcase | +0.036 |
sel | +0.036 |
Neg logit contributions | |
about | -0.032 |
hog | -0.031 |
ranger | -0.029 |
Sharing | -0.028 |
Tim | -0.028 |
Token | together |
Token ID | 1978 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.024 |
reality | +0.023 |
growth | +0.022 |
ucer | +0.022 |
Neg logit contributions | |
about | -0.012 |
Tim | -0.010 |
hog | -0.010 |
ranger | -0.009 |
Sharing | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
hog | +0.008 |
about | +0.008 |
ranger | +0.008 |
Tim | +0.008 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.011 |
lor | -0.011 |
suitcase | -0.010 |
Beck | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
about | +0.009 |
hog | +0.008 |
ranger | +0.008 |
Tim | +0.008 |
: | +0.007 |
Neg logit contributions | |
avail | -0.018 |
lor | -0.016 |
reality | -0.016 |
growth | -0.015 |
Beck | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
avail | +0.017 |
reality | +0.015 |
lor | +0.015 |
Beck | +0.014 |
growth | +0.014 |
Neg logit contributions | |
about | -0.009 |
hog | -0.008 |
ranger | -0.008 |
Sharing | -0.008 |
Tim | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
avail | +0.012 |
lor | +0.011 |
reality | +0.010 |
sel | +0.010 |
growth | +0.009 |
Neg logit contributions | |
about | -0.011 |
Tim | -0.010 |
hog | -0.009 |
ranger | -0.009 |
: | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
avail | +0.048 |
lor | +0.042 |
reality | +0.042 |
suitcase | +0.039 |
growth | +0.039 |
Neg logit contributions | |
about | -0.028 |
hog | -0.025 |
ranger | -0.024 |
Tim | -0.024 |
Sharing | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
avail | +0.027 |
reality | +0.024 |
lor | +0.023 |
ucer | +0.022 |
suitcase | +0.022 |
Neg logit contributions | |
hog | -0.021 |
about | -0.020 |
ranger | -0.020 |
aring | -0.018 |
Sharing | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
: | +0.003 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
reality | -0.007 |
growth | -0.007 |
suitcase | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
avail | +0.033 |
lor | +0.029 |
reality | +0.028 |
growth | +0.025 |
sel | +0.025 |
Neg logit contributions | |
about | -0.023 |
hog | -0.021 |
ranger | -0.020 |
Tim | -0.020 |
Sharing | -0.019 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
avail | +0.114 |
lor | +0.112 |
reality | +0.102 |
growth | +0.099 |
outer | +0.090 |
Neg logit contributions | |
Tim | -0.073 |
about | -0.069 |
hog | -0.069 |
old | -0.067 |
owner | -0.067 |
Token | had |
Token ID | 550 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
awoke | +0.032 |
suitcase | +0.030 |
drifted | +0.029 |
veil | +0.029 |
aire | +0.029 |
Neg logit contributions | |
hog | -0.034 |
ranger | -0.034 |
aring | -0.031 |
uddy | -0.030 |
automobiles | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.005 |
reality | +0.005 |
growth | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.006 |
hog | -0.005 |
Tim | -0.005 |
ranger | -0.005 |
Sharing | -0.005 |
Token | sweet |
Token ID | 6029 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
about | +0.006 |
hog | +0.006 |
ranger | +0.005 |
Sharing | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
avail | -0.008 |
reality | -0.007 |
lor | -0.006 |
suitcase | -0.006 |
Beck | -0.006 |
Token | smile |
Token ID | 8212 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
Tim | +0.005 |
ranger | +0.005 |
: | +0.005 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
reality | -0.007 |
growth | -0.006 |
Beck | -0.006 |
Token | tightly |
Token ID | 17707 |
Feature activation | +6.36e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.016 |
suitcase | +0.015 |
sel | +0.015 |
Neg logit contributions | |
about | -0.011 |
Tim | -0.011 |
Sharing | -0.011 |
hog | -0.011 |
ranger | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
avail | +0.014 |
reality | +0.013 |
lor | +0.012 |
suitcase | +0.012 |
sel | +0.012 |
Neg logit contributions | |
ranger | -0.007 |
hog | -0.007 |
about | -0.007 |
Tim | -0.007 |
Sharing | -0.007 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
avail | +0.018 |
reality | +0.016 |
lor | +0.016 |
growth | +0.014 |
suitcase | +0.014 |
Neg logit contributions | |
about | -0.013 |
hog | -0.012 |
ranger | -0.011 |
Tim | -0.011 |
Sharing | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
avail | +0.034 |
lor | +0.030 |
reality | +0.029 |
growth | +0.027 |
ucer | +0.027 |
Neg logit contributions | |
about | -0.027 |
hog | -0.025 |
Tim | -0.024 |
ranger | -0.024 |
: | -0.023 |
Token | close |
Token ID | 1969 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.002 |
growth | +0.002 |
reality | +0.002 |
sel | +0.002 |
Neg logit contributions | |
about | -0.001 |
ranger | -0.001 |
hog | -0.001 |
owner | -0.001 |
driver | -0.001 |
Token | eye |
Token ID | 4151 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.023 |
reality | +0.022 |
Beck | +0.021 |
ucer | +0.021 |
Neg logit contributions | |
about | -0.018 |
hog | -0.016 |
ranger | -0.016 |
Tim | -0.016 |
: | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
avail | +0.113 |
lor | +0.099 |
reality | +0.098 |
growth | +0.090 |
Beck | +0.089 |
Neg logit contributions | |
about | -0.074 |
hog | -0.066 |
ranger | -0.063 |
Tim | -0.063 |
: | -0.060 |
Token | his |
Token ID | 465 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
avail | +0.010 |
lor | +0.009 |
reality | +0.009 |
growth | +0.008 |
suitcase | +0.008 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.007 |
Token | kingdom |
Token ID | 13239 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
avail | +0.025 |
reality | +0.021 |
lor | +0.021 |
suitcase | +0.019 |
growth | +0.019 |
Neg logit contributions | |
about | -0.026 |
hog | -0.024 |
Tim | -0.024 |
Sharing | -0.023 |
ranger | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.027 |
reality | +0.026 |
sel | +0.024 |
suitcase | +0.024 |
Neg logit contributions | |
about | -0.022 |
Tim | -0.021 |
hog | -0.021 |
Sharing | -0.021 |
ranger | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
avail | +0.010 |
reality | +0.009 |
lor | +0.009 |
Beck | +0.008 |
growth | +0.008 |
Neg logit contributions | |
hog | -0.008 |
ranger | -0.007 |
about | -0.007 |
aring | -0.007 |
Tim | -0.006 |
Token | wearing |
Token ID | 5762 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
hog | +0.006 |
Sharing | +0.005 |
ranger | +0.005 |
uddy | +0.005 |
about | +0.005 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.007 |
lor | -0.006 |
suitcase | -0.006 |
Avery | -0.006 |
Token | funny |
Token ID | 8258 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
avail | +0.016 |
lor | +0.014 |
reality | +0.014 |
suitcase | +0.012 |
growth | +0.012 |
Neg logit contributions | |
about | -0.015 |
hog | -0.015 |
ranger | -0.014 |
Tim | -0.014 |
Sharing | -0.013 |
Token | hats |
Token ID | 23910 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
avail | +0.022 |
lor | +0.019 |
reality | +0.018 |
suitcase | +0.017 |
growth | +0.017 |
Neg logit contributions | |
about | -0.018 |
hog | -0.017 |
ranger | -0.017 |
Tim | -0.017 |
Sharing | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
avail | +0.066 |
lor | +0.061 |
reality | +0.059 |
suitcase | +0.057 |
sel | +0.057 |
Neg logit contributions | |
hog | -0.027 |
about | -0.026 |
ranger | -0.025 |
Tim | -0.023 |
Sharing | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
avail | +0.012 |
lor | +0.011 |
reality | +0.010 |
suitcase | +0.009 |
growth | +0.009 |
Neg logit contributions | |
about | -0.011 |
hog | -0.010 |
ranger | -0.010 |
Tim | -0.010 |
Sharing | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
avail | +0.027 |
lor | +0.023 |
reality | +0.023 |
suitcase | +0.021 |
sel | +0.021 |
Neg logit contributions | |
about | -0.020 |
hog | -0.018 |
ranger | -0.017 |
Tim | -0.017 |
Sharing | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
avail | +0.089 |
lor | +0.085 |
reality | +0.074 |
growth | +0.072 |
ucer | +0.070 |
Neg logit contributions | |
about | -0.094 |
hog | -0.091 |
Tim | -0.088 |
ranger | -0.088 |
elephant | -0.082 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
avail | +0.076 |
reality | +0.069 |
lor | +0.069 |
suitcase | +0.065 |
sel | +0.064 |
Neg logit contributions | |
about | -0.053 |
hog | -0.050 |
ranger | -0.049 |
Sharing | -0.047 |
Tim | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
avail | +0.013 |
reality | +0.011 |
lor | +0.011 |
suitcase | +0.010 |
growth | +0.010 |
Neg logit contributions | |
about | -0.012 |
hog | -0.012 |
ranger | -0.011 |
Tim | -0.011 |
Sharing | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
about | +0.008 |
hog | +0.007 |
ranger | +0.007 |
Sharing | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
avail | -0.012 |
lor | -0.010 |
reality | -0.010 |
sel | -0.009 |
Beck | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
avail | +0.025 |
lor | +0.022 |
reality | +0.022 |
sel | +0.020 |
Beck | +0.020 |
Neg logit contributions | |
about | -0.014 |
hog | -0.013 |
ranger | -0.012 |
Tim | -0.012 |
Sharing | -0.011 |
Token | kinds |
Token ID | 6982 |
Feature activation | -1.11e-03 |
Pos logit contributions | |
avail | +0.017 |
lor | +0.015 |
reality | +0.015 |
growth | +0.013 |
sel | +0.013 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
ranger | -0.010 |
Tim | -0.010 |
Sharing | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ranger | +0.002 |
hog | +0.002 |
Tim | +0.002 |
about | +0.002 |
Sharing | +0.002 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
lor | -0.002 |
sel | -0.002 |
suitcase | -0.002 |
Token | cereal |
Token ID | 33158 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
avail | +0.022 |
reality | +0.019 |
lor | +0.018 |
suitcase | +0.017 |
Beck | +0.016 |
Neg logit contributions | |
hog | -0.018 |
about | -0.018 |
ranger | -0.018 |
Sharing | -0.017 |
Tim | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
avail | +0.045 |
lor | +0.040 |
reality | +0.039 |
growth | +0.036 |
sel | +0.036 |
Neg logit contributions | |
about | -0.029 |
hog | -0.026 |
ranger | -0.025 |
Tim | -0.025 |
Sharing | -0.023 |
Token | The |
Token ID | 383 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
ranger | +0.004 |
trucks | +0.004 |
aring | +0.003 |
Neg logit contributions | |
avail | -0.007 |
lor | -0.007 |
reality | -0.006 |
growth | -0.006 |
Beck | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
avail | +0.055 |
lor | +0.049 |
reality | +0.046 |
growth | +0.044 |
ucer | +0.044 |
Neg logit contributions | |
about | -0.031 |
hog | -0.028 |
ranger | -0.027 |
Tim | -0.026 |
: | -0.025 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
lor | +0.122 |
avail | +0.115 |
growth | +0.107 |
reality | +0.105 |
irs | +0.102 |
Neg logit contributions | |
old | -0.064 |
Tim | -0.062 |
about | -0.062 |
hog | -0.062 |
owner | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
lor | +0.040 |
awoke | +0.039 |
Beck | +0.039 |
sel | +0.039 |
avail | +0.038 |
Neg logit contributions | |
automobiles | -0.053 |
Sharing | -0.051 |
ooters | -0.049 |
about | -0.049 |
ranger | -0.049 |
Token | so |
Token ID | 523 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.012 |
lor | +0.011 |
Avery | +0.010 |
suitcase | +0.010 |
Neg logit contributions | |
hog | -0.009 |
ranger | -0.008 |
automobiles | -0.008 |
Sharing | -0.008 |
trucks | -0.008 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
avail | +0.005 |
reality | +0.005 |
lor | +0.004 |
Beck | +0.004 |
sel | +0.004 |
Neg logit contributions | |
hog | -0.003 |
about | -0.003 |
ranger | -0.003 |
trucks | -0.003 |
automobiles | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
hog | +0.004 |
ranger | +0.004 |
Sharing | +0.004 |
about | +0.003 |
trucks | +0.003 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
reality | -0.007 |
Avery | -0.006 |
sel | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
hog | +0.009 |
ranger | +0.008 |
Sharing | +0.008 |
Tim | +0.008 |
about | +0.008 |
Neg logit contributions | |
avail | -0.020 |
reality | -0.019 |
lor | -0.019 |
suitcase | -0.018 |
sel | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.028 |
reality | +0.025 |
ucer | +0.024 |
sie | +0.023 |
Neg logit contributions | |
about | -0.022 |
Tim | -0.021 |
ranger | -0.019 |
: | -0.019 |
Mark | -0.018 |
Token | room |
Token ID | 2119 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
avail | +0.061 |
lor | +0.052 |
reality | +0.050 |
ucer | +0.046 |
sel | +0.046 |
Neg logit contributions | |
about | -0.051 |
hog | -0.047 |
ranger | -0.045 |
Tim | -0.045 |
: | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.009 |
reality | -0.009 |
suitcase | -0.008 |
sel | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
avail | +0.022 |
reality | +0.020 |
lor | +0.019 |
suitcase | +0.018 |
ucer | +0.018 |
Neg logit contributions | |
about | -0.013 |
hog | -0.012 |
ranger | -0.012 |
Tim | -0.011 |
Sharing | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
avail | +0.031 |
reality | +0.027 |
lor | +0.027 |
suitcase | +0.024 |
sel | +0.024 |
Neg logit contributions | |
about | -0.026 |
hog | -0.024 |
ranger | -0.023 |
Tim | -0.023 |
Sharing | -0.022 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
avail | +0.092 |
lor | +0.092 |
growth | +0.078 |
reality | +0.077 |
ucer | +0.074 |
Neg logit contributions | |
about | -0.089 |
Tim | -0.084 |
hog | -0.084 |
ranger | -0.081 |
owner | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
avail | +0.069 |
lor | +0.061 |
reality | +0.061 |
sel | +0.055 |
suitcase | +0.055 |
Neg logit contributions | |
about | -0.042 |
hog | -0.038 |
ranger | -0.037 |
Tim | -0.036 |
Sharing | -0.034 |
Token | delighted |
Token ID | 20707 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.016 |
suitcase | +0.014 |
Beck | +0.014 |
Neg logit contributions | |
about | -0.008 |
hog | -0.008 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
hog | +0.016 |
about | +0.015 |
ranger | +0.015 |
Tim | +0.014 |
trucks | +0.014 |
Neg logit contributions | |
avail | -0.024 |
reality | -0.021 |
lor | -0.021 |
sel | -0.018 |
suitcase | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
avail | +0.023 |
lor | +0.020 |
reality | +0.019 |
sel | +0.018 |
ucer | +0.018 |
Neg logit contributions | |
about | -0.008 |
Tim | -0.007 |
: | -0.006 |
Sharing | -0.006 |
hog | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
avail | +0.034 |
lor | +0.030 |
reality | +0.029 |
ucer | +0.027 |
sel | +0.027 |
Neg logit contributions | |
about | -0.027 |
hog | -0.024 |
Tim | -0.024 |
ranger | -0.023 |
: | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
hog | +0.004 |
ranger | +0.004 |
Sharing | +0.004 |
about | +0.003 |
moms | +0.003 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.006 |
lor | -0.006 |
suitcase | -0.006 |
drift | -0.006 |
Token | always |
Token ID | 1464 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
Sharing | +0.004 |
ranger | +0.004 |
automobiles | +0.004 |
Neg logit contributions | |
avail | -0.006 |
reality | -0.005 |
lor | -0.005 |
suitcase | -0.005 |
Beck | -0.005 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
avail | +0.021 |
lor | +0.019 |
reality | +0.018 |
growth | +0.017 |
sel | +0.017 |
Neg logit contributions | |
about | -0.014 |
hog | -0.012 |
Tim | -0.012 |
ranger | -0.012 |
: | -0.011 |
Token | an |
Token ID | 281 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
avail | +0.035 |
lor | +0.031 |
reality | +0.030 |
growth | +0.027 |
ucer | +0.027 |
Neg logit contributions | |
about | -0.029 |
hog | -0.026 |
Tim | -0.025 |
ranger | -0.025 |
Sharing | -0.024 |
Token | eye |
Token ID | 4151 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
about | +0.042 |
hog | +0.041 |
Tim | +0.040 |
ranger | +0.040 |
Sharing | +0.039 |
Neg logit contributions | |
avail | -0.026 |
reality | -0.021 |
lor | -0.021 |
growth | -0.018 |
sel | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
avail | +0.103 |
reality | +0.087 |
lor | +0.086 |
growth | +0.082 |
Beck | +0.080 |
Neg logit contributions | |
about | -0.089 |
hog | -0.076 |
ranger | -0.073 |
Tim | -0.072 |
: | -0.072 |
Token | him |
Token ID | 683 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.005 |
reality | +0.005 |
growth | +0.004 |
suitcase | +0.004 |
Neg logit contributions | |
about | -0.005 |
hog | -0.004 |
ranger | -0.004 |
Tim | -0.004 |
Sharing | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-04 |
Pos logit contributions | |
avail | +0.013 |
lor | +0.012 |
reality | +0.012 |
suitcase | +0.011 |
sel | +0.011 |
Neg logit contributions | |
hog | -0.010 |
about | -0.010 |
ranger | -0.009 |
Tim | -0.009 |
Sharing | -0.009 |
Token | mind |
Token ID | 2000 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
hog | +0.000 |
about | +0.000 |
ranger | +0.000 |
Sharing | +0.000 |
automobiles | +0.000 |
Neg logit contributions | |
avail | -0.000 |
reality | -0.000 |
lor | -0.000 |
suitcase | -0.000 |
drift | -0.000 |
Token | ing |
Token ID | 278 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
about | +0.028 |
hog | +0.028 |
ranger | +0.028 |
Tim | +0.026 |
Sharing | +0.025 |
Neg logit contributions | |
avail | -0.044 |
reality | -0.040 |
lor | -0.040 |
ucer | -0.036 |
suitcase | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +3.94e-04 |
Pos logit contributions | |
avail | +0.002 |
reality | +0.002 |
lor | +0.002 |
growth | +0.001 |
suitcase | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Tim | -0.001 |
Sharing | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
avail | +0.001 |
lor | +0.001 |
reality | +0.001 |
sel | +0.001 |
ucer | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
Tim | -0.001 |
ranger | -0.001 |
: | -0.000 |
Token | fog |
Token ID | 19558 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.025 |
reality | +0.024 |
sel | +0.023 |
growth | +0.022 |
Neg logit contributions | |
about | -0.030 |
hog | -0.028 |
ranger | -0.027 |
Tim | -0.026 |
: | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
ranger | +0.003 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.005 |
suitcase | -0.005 |
sel | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
avail | +0.021 |
reality | +0.019 |
lor | +0.018 |
Beck | +0.017 |
suitcase | +0.017 |
Neg logit contributions | |
about | -0.013 |
hog | -0.012 |
Sharing | -0.012 |
aring | -0.011 |
ranger | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
avail | +0.045 |
lor | +0.039 |
reality | +0.039 |
suitcase | +0.035 |
growth | +0.035 |
Neg logit contributions | |
about | -0.039 |
hog | -0.036 |
Tim | -0.035 |
ranger | -0.035 |
Sharing | -0.033 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
avail | +0.106 |
lor | +0.102 |
reality | +0.091 |
ucer | +0.088 |
growth | +0.087 |
Neg logit contributions | |
about | -0.074 |
hog | -0.072 |
Tim | -0.069 |
ranger | -0.069 |
elephant | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
avail | +0.045 |
lor | +0.042 |
reality | +0.042 |
sel | +0.038 |
awoke | +0.038 |
Neg logit contributions | |
about | -0.032 |
hog | -0.030 |
ranger | -0.030 |
Sharing | -0.029 |
automobiles | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | -7.94e-03 |
Pos logit contributions | |
avail | +0.008 |
lor | +0.008 |
reality | +0.008 |
Beck | +0.007 |
suitcase | +0.007 |
Neg logit contributions | |
hog | -0.005 |
about | -0.005 |
Sharing | -0.005 |
trucks | -0.005 |
ranger | -0.005 |
Token | surprised |
Token ID | 6655 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
about | +0.011 |
automobiles | +0.010 |
hog | +0.010 |
trucks | +0.010 |
Sharing | +0.010 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.015 |
lor | -0.013 |
Beck | -0.013 |
Avery | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
hog | +0.014 |
about | +0.014 |
ranger | +0.013 |
Sharing | +0.012 |
trucks | +0.012 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.017 |
lor | -0.016 |
sel | -0.014 |
suitcase | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.007 |
reality | +0.006 |
Beck | +0.006 |
Elsa | +0.006 |
Neg logit contributions | |
about | -0.005 |
hog | -0.005 |
ranger | -0.005 |
trucks | -0.005 |
Sharing | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
avail | +0.009 |
lor | +0.008 |
reality | +0.008 |
Beck | +0.008 |
Elsa | +0.007 |
Neg logit contributions | |
about | -0.010 |
Tim | -0.009 |
hog | -0.009 |
ranger | -0.008 |
: | -0.008 |
Token | king |
Token ID | 5822 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
avail | +0.012 |
lor | +0.010 |
reality | +0.010 |
ucer | +0.009 |
growth | +0.009 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Tim | -0.007 |
: | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
lor | +0.014 |
awoke | +0.014 |
sel | +0.013 |
reality | +0.013 |
Beck | +0.013 |
Neg logit contributions | |
Sharing | -0.014 |
about | -0.013 |
automobiles | -0.013 |
disl | -0.012 |
ooters | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
avail | +0.063 |
lor | +0.056 |
reality | +0.053 |
ucer | +0.048 |
growth | +0.048 |
Neg logit contributions | |
about | -0.059 |
hog | -0.054 |
Tim | -0.054 |
ranger | -0.053 |
: | -0.050 |
Token | little |
Token ID | 1310 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
avail | +0.033 |
lor | +0.030 |
reality | +0.028 |
ucer | +0.026 |
growth | +0.026 |
Neg logit contributions | |
about | -0.021 |
hog | -0.019 |
ranger | -0.019 |
Tim | -0.018 |
owner | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
avail | +0.110 |
lor | +0.110 |
reality | +0.095 |
arse | +0.093 |
growth | +0.092 |
Neg logit contributions | |
ranger | -0.076 |
hog | -0.075 |
elephant | -0.073 |
Tim | -0.072 |
driver | -0.070 |
Token | searched |
Token ID | 16499 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
avail | +0.048 |
lor | +0.042 |
reality | +0.041 |
growth | +0.037 |
ucer | +0.037 |
Neg logit contributions | |
about | -0.039 |
hog | -0.036 |
ranger | -0.035 |
Tim | -0.035 |
Sharing | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
avail | +0.023 |
reality | +0.020 |
lor | +0.020 |
suitcase | +0.019 |
growth | +0.019 |
Neg logit contributions | |
about | -0.010 |
hog | -0.010 |
ranger | -0.009 |
Tim | -0.009 |
Sharing | -0.009 |
Token | searched |
Token ID | 16499 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.012 |
reality | +0.012 |
ucer | +0.011 |
growth | +0.011 |
Neg logit contributions | |
about | -0.009 |
Tim | -0.008 |
hog | -0.008 |
ranger | -0.008 |
: | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.023 |
reality | +0.023 |
growth | +0.021 |
suitcase | +0.021 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
ranger | -0.010 |
Tim | -0.010 |
Sharing | -0.009 |
Token | now |
Token ID | 783 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
about | +0.001 |
hog | +0.001 |
ranger | +0.001 |
Sharing | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
avail | -0.001 |
lor | -0.001 |
reality | -0.001 |
suitcase | -0.001 |
sel | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.013 |
reality | +0.013 |
growth | +0.012 |
sel | +0.012 |
Neg logit contributions | |
about | -0.009 |
Tim | -0.008 |
hog | -0.008 |
ranger | -0.007 |
: | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
about | +0.018 |
hog | +0.016 |
ranger | +0.016 |
aring | +0.015 |
trucks | +0.015 |
Neg logit contributions | |
avail | -0.025 |
lor | -0.024 |
growth | -0.023 |
Beck | -0.022 |
Avery | -0.022 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
about | +0.013 |
hog | +0.011 |
Sharing | +0.010 |
Tim | +0.010 |
aring | +0.010 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.015 |
lor | -0.014 |
suitcase | -0.013 |
sel | -0.013 |
Token | in |
Token ID | 259 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
about | +0.039 |
Tim | +0.035 |
ranger | +0.035 |
hog | +0.034 |
: | +0.033 |
Neg logit contributions | |
avail | -0.018 |
lor | -0.017 |
reality | -0.016 |
ucer | -0.014 |
Beck | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
about | +0.046 |
automobiles | +0.043 |
Sharing | +0.042 |
ooters | +0.041 |
Tim | +0.041 |
Neg logit contributions | |
lor | -0.018 |
awoke | -0.013 |
Beck | -0.012 |
antly | -0.012 |
sel | -0.012 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
about | +0.123 |
Tim | +0.097 |
exciting | +0.094 |
not | +0.092 |
Sharing | +0.092 |
Neg logit contributions | |
lor | -0.075 |
avail | -0.075 |
sel | -0.054 |
growth | -0.053 |
ipping | -0.052 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
automobiles | +0.035 |
ooters | +0.033 |
trucks | +0.031 |
Sharing | +0.031 |
about | +0.030 |
Neg logit contributions | |
awoke | -0.029 |
lor | -0.028 |
sel | -0.027 |
reality | -0.026 |
Beck | -0.025 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
ucer | +0.006 |
growth | +0.006 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
Tim | -0.003 |
ranger | -0.003 |
: | -0.002 |
Token | too |
Token ID | 1165 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
hog | +0.001 |
automobiles | +0.001 |
about | +0.001 |
ranger | +0.001 |
trucks | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
lor | -0.002 |
suitcase | -0.002 |
sel | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
about | +0.034 |
hog | +0.031 |
ranger | +0.030 |
Tim | +0.029 |
Sharing | +0.028 |
Neg logit contributions | |
avail | -0.060 |
lor | -0.053 |
reality | -0.052 |
growth | -0.048 |
sel | -0.048 |
Token | Why |
Token ID | 5195 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
about | +0.010 |
hog | +0.009 |
ranger | +0.009 |
Tim | +0.009 |
Sharing | +0.009 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.009 |
reality | -0.009 |
Beck | -0.008 |
growth | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
avail | +0.013 |
reality | +0.012 |
lor | +0.011 |
suitcase | +0.010 |
ucer | +0.010 |
Neg logit contributions | |
hog | -0.013 |
ranger | -0.012 |
about | -0.011 |
Tim | -0.011 |
elephant | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
hog | +0.023 |
about | +0.023 |
ranger | +0.022 |
Sharing | +0.020 |
driver | +0.020 |
Neg logit contributions | |
avail | -0.017 |
reality | -0.013 |
anything | -0.012 |
Avery | -0.012 |
lor | -0.011 |
Token | being |
Token ID | 852 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
hog | +0.016 |
ranger | +0.015 |
about | +0.013 |
uddy | +0.013 |
Sharing | +0.013 |
Neg logit contributions | |
avail | -0.020 |
reality | -0.019 |
Avery | -0.017 |
arse | -0.017 |
lor | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e-05 |
Pos logit contributions | |
hog | +0.038 |
ranger | +0.036 |
uddy | +0.036 |
Sharing | +0.034 |
about | +0.033 |
Neg logit contributions | |
avail | -0.054 |
reality | -0.051 |
anything | -0.047 |
Avery | -0.047 |
Beck | -0.044 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
avail | +0.000 |
reality | +0.000 |
Avery | +0.000 |
sie | +0.000 |
sel | +0.000 |
Neg logit contributions | |
about | -0.000 |
hog | -0.000 |
ranger | -0.000 |
Sharing | -0.000 |
Tim | -0.000 |
Token | y |
Token ID | 88 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
hog | +0.115 |
ranger | +0.114 |
about | +0.106 |
Tim | +0.104 |
Zip | +0.102 |
Neg logit contributions | |
avail | -0.066 |
lor | -0.052 |
ucer | -0.051 |
reality | -0.051 |
sel | -0.046 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
hog | +0.008 |
ranger | +0.008 |
Tim | +0.007 |
about | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.008 |
lor | -0.008 |
suitcase | -0.007 |
ucer | -0.007 |
Token | |
Token ID | 220 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
about | +0.006 |
trucks | +0.006 |
hog | +0.005 |
aring | +0.005 |
automobiles | +0.005 |
Neg logit contributions | |
avail | -0.008 |
Beck | -0.006 |
reality | -0.006 |
Avery | -0.006 |
lor | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.013 |
reality | +0.012 |
Beck | +0.011 |
growth | +0.011 |
Neg logit contributions | |
about | -0.008 |
hog | -0.008 |
ranger | -0.008 |
trucks | -0.007 |
Tim | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
avail | +0.017 |
lor | +0.015 |
Beck | +0.015 |
reality | +0.014 |
Avery | +0.013 |
Neg logit contributions | |
about | -0.015 |
trucks | -0.013 |
hog | -0.013 |
ranger | -0.013 |
automobiles | -0.013 |
Token | Mama |
Token ID | 40084 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
about | +0.009 |
hog | +0.008 |
ranger | +0.008 |
Sharing | +0.007 |
: | +0.007 |
Neg logit contributions | |
avail | -0.019 |
lor | -0.016 |
reality | -0.016 |
Beck | -0.015 |
growth | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
hog | +0.009 |
about | +0.009 |
ranger | +0.009 |
Sharing | +0.008 |
aring | +0.008 |
Neg logit contributions | |
avail | -0.011 |
lor | -0.010 |
reality | -0.009 |
ucer | -0.009 |
sel | -0.009 |
Token | Mama |
Token ID | 40084 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
about | +0.011 |
Tim | +0.010 |
hog | +0.009 |
ranger | +0.009 |
: | +0.008 |
Neg logit contributions | |
avail | -0.019 |
lor | -0.017 |
reality | -0.017 |
sel | -0.015 |
ucer | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
aring | +0.018 |
ooters | +0.018 |
hog | +0.017 |
rivals | +0.017 |
uddy | +0.016 |
Neg logit contributions | |
awoke | -0.011 |
Beck | -0.010 |
lor | -0.010 |
veil | -0.009 |
Natalie | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
about | +0.014 |
hog | +0.013 |
ranger | +0.013 |
Tim | +0.012 |
Sharing | +0.012 |
Neg logit contributions | |
avail | -0.026 |
lor | -0.023 |
reality | -0.023 |
suitcase | -0.021 |
Beck | -0.021 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
about | +0.024 |
hog | +0.023 |
ranger | +0.021 |
Sharing | +0.021 |
Tim | +0.021 |
Neg logit contributions | |
avail | -0.032 |
reality | -0.028 |
Elsa | -0.026 |
lor | -0.026 |
sie | -0.026 |
Token | y |
Token ID | 88 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
hog | +0.109 |
ranger | +0.107 |
about | +0.102 |
Tim | +0.098 |
moms | +0.098 |
Neg logit contributions | |
avail | -0.062 |
lor | -0.053 |
ucer | -0.053 |
reality | -0.053 |
ices | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
hog | +0.017 |
ranger | +0.017 |
Tim | +0.017 |
about | +0.017 |
moms | +0.017 |
Neg logit contributions | |
avail | -0.018 |
reality | -0.017 |
lor | -0.017 |
suitcase | -0.016 |
sel | -0.015 |
Token | always |
Token ID | 1464 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
hog | +0.006 |
ranger | +0.006 |
about | +0.005 |
aring | +0.005 |
ooters | +0.005 |
Neg logit contributions | |
avail | -0.008 |
reality | -0.007 |
sie | -0.007 |
Avery | -0.007 |
Stacy | -0.007 |
Token | told |
Token ID | 1297 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
hog | +0.003 |
about | +0.003 |
ranger | +0.003 |
uddy | +0.003 |
moms | +0.002 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.004 |
ucer | -0.004 |
lor | -0.004 |
Beck | -0.003 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
hog | +0.013 |
ranger | +0.012 |
Sharing | +0.012 |
about | +0.012 |
aring | +0.011 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.008 |
lor | -0.007 |
anything | -0.007 |
growth | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
ranger | +0.005 |
Tim | +0.005 |
Sharing | +0.005 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.008 |
reality | -0.008 |
ucer | -0.007 |
sel | -0.007 |
Token | One |
Token ID | 1881 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
hog | +0.015 |
about | +0.014 |
ranger | +0.014 |
ike | +0.014 |
aring | +0.014 |
Neg logit contributions | |
avail | -0.019 |
growth | -0.018 |
lor | -0.016 |
sel | -0.016 |
reality | -0.016 |
Token | fish |
Token ID | 5916 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
hog | +0.009 |
about | +0.009 |
Sharing | +0.009 |
automobiles | +0.009 |
ranger | +0.008 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.008 |
ucer | -0.008 |
awoke | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
about | +0.018 |
hog | +0.018 |
ranger | +0.017 |
automobiles | +0.017 |
Sharing | +0.016 |
Neg logit contributions | |
avail | -0.022 |
lor | -0.022 |
ices | -0.021 |
ucer | -0.021 |
reality | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
hog | +0.025 |
aring | +0.025 |
Sharing | +0.024 |
automobiles | +0.024 |
ranger | +0.023 |
Neg logit contributions | |
avail | -0.018 |
reality | -0.016 |
seas | -0.015 |
P | -0.014 |
awoken | -0.014 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
about | +0.033 |
hog | +0.032 |
Sharing | +0.031 |
automobiles | +0.031 |
meanings | +0.029 |
Neg logit contributions | |
avail | -0.021 |
seas | -0.019 |
reality | -0.018 |
refreshed | -0.017 |
ucer | -0.017 |
Token | y |
Token ID | 88 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ranger | +0.114 |
hog | +0.114 |
about | +0.106 |
moms | +0.106 |
keeper | +0.104 |
Neg logit contributions | |
avail | -0.046 |
ices | -0.041 |
ucer | -0.041 |
cer | -0.040 |
lor | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
hog | +0.018 |
ranger | +0.018 |
moms | +0.018 |
Tim | +0.017 |
about | +0.017 |
Neg logit contributions | |
avail | -0.019 |
lor | -0.018 |
reality | -0.018 |
pen | -0.017 |
suitcase | -0.017 |
Token | His |
Token ID | 2399 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
hog | +0.008 |
about | +0.008 |
aring | +0.008 |
ranger | +0.008 |
ike | +0.007 |
Neg logit contributions | |
avail | -0.010 |
growth | -0.009 |
lor | -0.008 |
valleys | -0.008 |
Avery | -0.008 |
Token | name |
Token ID | 1438 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
about | +0.002 |
hog | +0.002 |
Sharing | +0.002 |
aring | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
avail | -0.002 |
suitcase | -0.002 |
reality | -0.002 |
lor | -0.002 |
seas | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
hog | +0.019 |
aring | +0.018 |
about | +0.018 |
ranger | +0.018 |
ooters | +0.017 |
Neg logit contributions | |
avail | -0.021 |
lor | -0.020 |
awoke | -0.019 |
reality | -0.019 |
growth | -0.018 |
Token | castle |
Token ID | 16669 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
avail | +0.008 |
reality | +0.007 |
lor | +0.006 |
suitcase | +0.006 |
growth | +0.006 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
ranger | -0.007 |
Tim | -0.007 |
Sharing | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.014 |
reality | +0.014 |
growth | +0.012 |
ucer | +0.012 |
Neg logit contributions | |
about | -0.011 |
hog | -0.010 |
Tim | -0.010 |
ranger | -0.010 |
Sharing | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
hog | +0.019 |
aring | +0.018 |
ike | +0.018 |
ranger | +0.018 |
about | +0.018 |
Neg logit contributions | |
avail | -0.019 |
growth | -0.016 |
Beck | -0.015 |
Avery | -0.015 |
reality | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.013 |
reality | +0.013 |
Beck | +0.013 |
awoke | +0.013 |
Neg logit contributions | |
aring | -0.013 |
about | -0.013 |
hog | -0.013 |
Sharing | -0.012 |
automobiles | -0.012 |
Token | very |
Token ID | 845 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
hog | +0.010 |
about | +0.010 |
ranger | +0.009 |
Sharing | +0.009 |
aring | +0.009 |
Neg logit contributions | |
avail | -0.018 |
reality | -0.017 |
lor | -0.016 |
Beck | -0.015 |
Elsa | -0.015 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
about | +0.021 |
hog | +0.019 |
Sharing | +0.018 |
ranger | +0.018 |
automobiles | +0.018 |
Neg logit contributions | |
avail | -0.027 |
reality | -0.024 |
Beck | -0.023 |
sie | -0.023 |
Avery | -0.022 |
Token | y |
Token ID | 88 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
hog | +0.107 |
ranger | +0.107 |
about | +0.101 |
Tim | +0.099 |
moms | +0.096 |
Neg logit contributions | |
avail | -0.060 |
reality | -0.053 |
lor | -0.053 |
ucer | -0.050 |
ices | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
ooters | +0.013 |
disl | +0.013 |
hog | +0.013 |
ranger | +0.013 |
moms | +0.013 |
Neg logit contributions | |
reality | -0.022 |
avail | -0.022 |
lor | -0.021 |
suitcase | -0.020 |
pen | -0.019 |
Token | always |
Token ID | 1464 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
hog | +0.006 |
aring | +0.005 |
ranger | +0.005 |
about | +0.005 |
Sharing | +0.005 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.007 |
veil | -0.006 |
sie | -0.006 |
Avery | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.003 |
ucer | +0.003 |
lor | +0.003 |
sel | +0.003 |
Neg logit contributions | |
hog | -0.002 |
about | -0.002 |
ranger | -0.002 |
automobiles | -0.002 |
Sharing | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.011 |
anything | +0.011 |
Beck | +0.010 |
growth | +0.010 |
Neg logit contributions | |
hog | -0.007 |
Sharing | -0.006 |
ike | -0.006 |
aring | -0.006 |
ranger | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
about | +0.012 |
hog | +0.012 |
ranger | +0.011 |
Sharing | +0.010 |
Tim | +0.010 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.013 |
lor | -0.012 |
ucer | -0.011 |
suitcase | -0.011 |
Token | But |
Token ID | 887 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
hog | +0.015 |
about | +0.014 |
aring | +0.014 |
asuring | +0.013 |
ike | +0.012 |
Neg logit contributions | |
avail | -0.020 |
suitcase | -0.015 |
lor | -0.015 |
aire | -0.014 |
neath | -0.014 |
Token | Billy |
Token ID | 15890 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
avail | +0.009 |
reality | +0.007 |
suitcase | +0.006 |
anything | +0.006 |
ucer | +0.006 |
Neg logit contributions | |
hog | -0.004 |
aring | -0.004 |
about | -0.003 |
ranger | -0.003 |
ike | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
about | +0.006 |
hog | +0.006 |
ooters | +0.006 |
Sharing | +0.006 |
automobiles | +0.006 |
Neg logit contributions | |
avail | -0.006 |
awoke | -0.005 |
lor | -0.004 |
pen | -0.004 |
suitcase | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
hog | +0.019 |
uddy | +0.017 |
automobiles | +0.017 |
trucks | +0.017 |
meanings | +0.017 |
Neg logit contributions | |
avail | -0.026 |
reality | -0.023 |
awoken | -0.021 |
anything | -0.021 |
Elsa | -0.021 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
about | +0.029 |
hog | +0.029 |
automobiles | +0.028 |
trucks | +0.027 |
meanings | +0.026 |
Neg logit contributions | |
avail | -0.037 |
P | -0.030 |
reality | -0.030 |
sie | -0.029 |
Elsa | -0.028 |
Token | y |
Token ID | 88 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
hog | +0.110 |
ranger | +0.108 |
about | +0.104 |
moms | +0.101 |
Tim | +0.100 |
Neg logit contributions | |
avail | -0.060 |
lor | -0.048 |
ucer | -0.048 |
reality | -0.047 |
sel | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
moms | +0.013 |
hog | +0.013 |
ranger | +0.012 |
disl | +0.012 |
sed | +0.012 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.018 |
lor | -0.017 |
pen | -0.017 |
suitcase | -0.017 |
Token | always |
Token ID | 1464 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
about | +0.012 |
hog | +0.012 |
aring | +0.012 |
Sharing | +0.012 |
neys | +0.011 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.011 |
sie | -0.010 |
P | -0.010 |
drift | -0.010 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
avail | +0.009 |
reality | +0.007 |
ucer | +0.007 |
lor | +0.006 |
sel | +0.006 |
Neg logit contributions | |
hog | -0.006 |
about | -0.006 |
ranger | -0.006 |
automobiles | -0.005 |
Sharing | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
avail | +0.005 |
anything | +0.005 |
reality | +0.004 |
ease | +0.004 |
any | +0.004 |
Neg logit contributions | |
hog | -0.004 |
aring | -0.003 |
ike | -0.003 |
uddy | -0.003 |
anda | -0.003 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.011 |
lor | +0.010 |
Beck | +0.010 |
growth | +0.009 |
Neg logit contributions | |
about | -0.011 |
hog | -0.010 |
ranger | -0.010 |
Tim | -0.010 |
Sharing | -0.009 |
Token | cheered |
Token ID | 34767 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
avail | +0.029 |
reality | +0.027 |
lor | +0.026 |
sel | +0.024 |
ucer | +0.024 |
Neg logit contributions | |
about | -0.024 |
hog | -0.023 |
ranger | -0.022 |
Tim | -0.022 |
Sharing | -0.021 |
Token | happily |
Token ID | 18177 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.024 |
reality | +0.023 |
growth | +0.021 |
ucer | +0.021 |
Neg logit contributions | |
about | -0.014 |
hog | -0.012 |
Tim | -0.012 |
ranger | -0.012 |
: | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
avail | +0.023 |
lor | +0.020 |
reality | +0.020 |
growth | +0.018 |
Beck | +0.018 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
ranger | -0.011 |
Tim | -0.010 |
: | -0.010 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.002 |
ranger | +0.002 |
trucks | +0.002 |
Tim | +0.002 |
Neg logit contributions | |
avail | -0.004 |
lor | -0.004 |
reality | -0.003 |
Beck | -0.003 |
growth | -0.003 |
Token | Mon |
Token ID | 9069 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
avail | +0.019 |
reality | +0.016 |
lor | +0.015 |
sel | +0.014 |
suitcase | +0.014 |
Neg logit contributions | |
about | -0.016 |
Tim | -0.015 |
hog | -0.015 |
: | -0.015 |
ranger | -0.014 |
Token | ica |
Token ID | 3970 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
about | +0.100 |
Sharing | +0.089 |
hog | +0.087 |
ranger | +0.084 |
aring | +0.081 |
Neg logit contributions | |
avail | -0.091 |
lor | -0.081 |
reality | -0.071 |
arse | -0.069 |
pen | -0.063 |
Token | had |
Token ID | 550 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
about | +0.016 |
hog | +0.015 |
ranger | +0.015 |
Sharing | +0.014 |
aring | +0.014 |
Neg logit contributions | |
avail | -0.032 |
lor | -0.031 |
reality | -0.030 |
sel | -0.029 |
growth | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.015 |
ucer | +0.014 |
growth | +0.014 |
Neg logit contributions | |
about | -0.014 |
Tim | -0.012 |
: | -0.011 |
hog | -0.011 |
ranger | -0.011 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
avail | +0.004 |
reality | +0.004 |
lor | +0.003 |
suitcase | +0.003 |
Beck | +0.003 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
Sharing | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
about | +0.002 |
Tim | +0.002 |
hog | +0.002 |
Sharing | +0.002 |
ranger | +0.002 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
lor | -0.003 |
suitcase | -0.003 |
sel | -0.003 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
about | +0.017 |
aring | +0.016 |
hog | +0.016 |
Sharing | +0.015 |
olded | +0.015 |
Neg logit contributions | |
avail | -0.018 |
suitcase | -0.016 |
reality | -0.016 |
veil | -0.016 |
valley | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
Tim | +0.005 |
ranger | +0.005 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.008 |
reality | -0.008 |
ucer | -0.007 |
suitcase | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
hog | +0.005 |
about | +0.005 |
aring | +0.005 |
ranger | +0.005 |
ike | +0.005 |
Neg logit contributions | |
avail | -0.008 |
growth | -0.007 |
reality | -0.007 |
sel | -0.007 |
lor | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.002 |
reality | +0.002 |
growth | +0.002 |
P | +0.002 |
Neg logit contributions | |
about | -0.002 |
aring | -0.002 |
hog | -0.002 |
Sharing | -0.002 |
automobiles | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
hog | +0.010 |
aring | +0.010 |
Sharing | +0.010 |
ranger | +0.009 |
about | +0.009 |
Neg logit contributions | |
avail | -0.011 |
reality | -0.010 |
anything | -0.009 |
suitcase | -0.009 |
Avery | -0.009 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
about | +0.023 |
hog | +0.022 |
automobiles | +0.022 |
Sharing | +0.021 |
ranger | +0.020 |
Neg logit contributions | |
avail | -0.023 |
reality | -0.019 |
Avery | -0.019 |
sel | -0.018 |
sie | -0.018 |
Token | y |
Token ID | 88 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ranger | +0.111 |
hog | +0.110 |
about | +0.105 |
Tim | +0.100 |
moms | +0.100 |
Neg logit contributions | |
avail | -0.053 |
ucer | -0.048 |
reality | -0.047 |
lor | -0.045 |
cer | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
disl | +0.014 |
ooters | +0.014 |
moms | +0.014 |
hog | +0.014 |
ranger | +0.014 |
Neg logit contributions | |
reality | -0.018 |
avail | -0.018 |
lor | -0.018 |
suitcase | -0.016 |
pen | -0.016 |
Token | always |
Token ID | 1464 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
aring | +0.007 |
hog | +0.007 |
about | +0.007 |
Sharing | +0.006 |
automobiles | +0.006 |
Neg logit contributions | |
avail | -0.008 |
reality | -0.007 |
veil | -0.007 |
suitcase | -0.007 |
sie | -0.007 |
Token | told |
Token ID | 1297 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.003 |
ucer | +0.003 |
awoke | +0.003 |
sel | +0.003 |
Neg logit contributions | |
hog | -0.003 |
about | -0.003 |
ranger | -0.002 |
automobiles | -0.002 |
uddy | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
hog | +0.004 |
Sharing | +0.004 |
aring | +0.004 |
ranger | +0.004 |
uddy | +0.004 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
anything | -0.003 |
growth | -0.003 |
lor | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
avail | +0.020 |
lor | +0.018 |
reality | +0.018 |
ucer | +0.016 |
suitcase | +0.016 |
Neg logit contributions | |
about | -0.010 |
hog | -0.010 |
ranger | -0.009 |
Tim | -0.009 |
Sharing | -0.008 |
Token | this |
Token ID | 428 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
hog | +0.040 |
aring | +0.040 |
about | +0.039 |
ranger | +0.037 |
Sharing | +0.036 |
Neg logit contributions | |
avail | -0.051 |
anything | -0.042 |
reality | -0.040 |
Avery | -0.038 |
veil | -0.037 |
Token | big |
Token ID | 1263 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
hog | +0.027 |
about | +0.025 |
ranger | +0.025 |
Tim | +0.024 |
Sharing | +0.024 |
Neg logit contributions | |
avail | -0.040 |
reality | -0.036 |
lor | -0.036 |
veil | -0.032 |
suitcase | -0.031 |
Token | dog |
Token ID | 3290 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.007 |
Sharing | +0.006 |
ranger | +0.006 |
aring | +0.006 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.010 |
suitcase | -0.009 |
lor | -0.009 |
veil | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
hog | +0.007 |
about | +0.007 |
ranger | +0.007 |
Sharing | +0.007 |
moms | +0.006 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.008 |
lor | -0.007 |
awoke | -0.007 |
suitcase | -0.007 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
hog | +0.015 |
about | +0.014 |
ranger | +0.014 |
automobiles | +0.013 |
asuring | +0.013 |
Neg logit contributions | |
avail | -0.020 |
reality | -0.017 |
lor | -0.016 |
outer | -0.016 |
anything | -0.016 |
Token | y |
Token ID | 88 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
hog | +0.107 |
ranger | +0.105 |
about | +0.099 |
Tim | +0.097 |
owner | +0.095 |
Neg logit contributions | |
avail | -0.064 |
ucer | -0.055 |
lor | -0.052 |
reality | -0.048 |
sel | -0.046 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
hog | +0.003 |
about | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.003 |
lor | -0.003 |
reality | -0.003 |
ucer | -0.003 |
suitcase | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
hog | +0.015 |
about | +0.014 |
aring | +0.014 |
ranger | +0.013 |
asuring | +0.012 |
Neg logit contributions | |
avail | -0.024 |
Elsa | -0.019 |
Beck | -0.019 |
Avery | -0.019 |
growth | -0.018 |
Token | did |
Token ID | 750 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
about | +0.016 |
hog | +0.016 |
aring | +0.015 |
ranger | +0.014 |
Sharing | +0.014 |
Neg logit contributions | |
avail | -0.022 |
lor | -0.018 |
reality | -0.018 |
sel | -0.018 |
Beck | -0.017 |
Token | not |
Token ID | 407 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
hog | +0.007 |
about | +0.006 |
ranger | +0.005 |
Sharing | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
avail | -0.034 |
reality | -0.031 |
lor | -0.030 |
anything | -0.028 |
growth | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
about | +0.044 |
hog | +0.044 |
ranger | +0.042 |
moms | +0.039 |
aring | +0.039 |
Neg logit contributions | |
avail | -0.042 |
reality | -0.036 |
lor | -0.035 |
Beck | -0.034 |
awoke | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
about | +0.005 |
: | +0.004 |
Tim | +0.004 |
owner | +0.003 |
hog | +0.003 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.007 |
lor | -0.007 |
growth | -0.006 |
sel | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
about | +0.023 |
hog | +0.022 |
ranger | +0.021 |
: | +0.020 |
Sharing | +0.019 |
Neg logit contributions | |
avail | -0.031 |
reality | -0.027 |
lor | -0.026 |
Beck | -0.024 |
growth | -0.024 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
about | +0.009 |
hog | +0.008 |
Sharing | +0.008 |
aring | +0.008 |
ike | +0.007 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.011 |
lor | -0.011 |
suitcase | -0.010 |
growth | -0.010 |
Token | in |
Token ID | 259 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
about | +0.040 |
Tim | +0.036 |
ranger | +0.036 |
hog | +0.036 |
: | +0.035 |
Neg logit contributions | |
avail | -0.018 |
lor | -0.018 |
reality | -0.017 |
ucer | -0.015 |
Beck | -0.014 |
Token | oc |
Token ID | 420 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
about | +0.068 |
Tim | +0.062 |
Sharing | +0.061 |
hog | +0.060 |
olds | +0.059 |
Neg logit contributions | |
lor | -0.026 |
awoke | -0.018 |
Beck | -0.018 |
reality | -0.017 |
ucer | -0.016 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
about | +0.120 |
Tim | +0.094 |
exciting | +0.092 |
not | +0.090 |
ooters | +0.090 |
Neg logit contributions | |
lor | -0.071 |
avail | -0.069 |
sel | -0.051 |
growth | -0.050 |
ucer | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
about | +0.033 |
hog | +0.032 |
automobiles | +0.031 |
ooters | +0.031 |
Sharing | +0.031 |
Neg logit contributions | |
lor | -0.048 |
awoke | -0.046 |
reality | -0.045 |
avail | -0.043 |
sel | -0.043 |
Token | not |
Token ID | 407 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
avail | +0.005 |
lor | +0.005 |
reality | +0.005 |
growth | +0.004 |
suitcase | +0.004 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
Tim | -0.002 |
ranger | -0.002 |
: | -0.002 |
Token | troubled |
Token ID | 17840 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
growth | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
Sharing | -0.003 |
Token | anymore |
Token ID | 7471 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
hog | +0.011 |
about | +0.010 |
ranger | +0.010 |
Tim | +0.010 |
Sharing | +0.010 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.013 |
lor | -0.012 |
growth | -0.011 |
suitcase | -0.011 |
Token | go |
Token ID | 467 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
avail | +0.055 |
lor | +0.049 |
reality | +0.049 |
ucer | +0.045 |
sel | +0.045 |
Neg logit contributions | |
about | -0.036 |
Tim | -0.032 |
hog | -0.030 |
ranger | -0.029 |
: | -0.029 |
Token | ." |
Token ID | 526 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
avail | +0.008 |
lor | +0.007 |
reality | +0.007 |
Beck | +0.006 |
growth | +0.006 |
Neg logit contributions | |
about | -0.004 |
Tim | -0.003 |
hog | -0.003 |
ranger | -0.003 |
: | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.006 |
ranger | +0.006 |
trucks | +0.006 |
aring | +0.005 |
Neg logit contributions | |
avail | -0.009 |
lor | -0.008 |
Beck | -0.008 |
reality | -0.008 |
Avery | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.016 |
Beck | +0.015 |
Elsa | +0.015 |
Neg logit contributions | |
about | -0.011 |
hog | -0.010 |
ranger | -0.009 |
Tim | -0.009 |
trucks | -0.009 |
Token | He |
Token ID | 1544 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
avail | +0.013 |
lor | +0.011 |
reality | +0.011 |
Beck | +0.010 |
Elsa | +0.010 |
Neg logit contributions | |
about | -0.017 |
hog | -0.015 |
Tim | -0.015 |
ranger | -0.015 |
: | -0.014 |
Token | unh |
Token ID | 14274 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
about | +0.037 |
hog | +0.035 |
Tim | +0.034 |
Sharing | +0.034 |
ranger | +0.033 |
Neg logit contributions | |
avail | -0.040 |
lor | -0.036 |
reality | -0.035 |
suitcase | -0.033 |
growth | -0.032 |
Token | ooks |
Token ID | 31085 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
about | +0.093 |
Tim | +0.086 |
elephant | +0.083 |
trucks | +0.080 |
hog | +0.080 |
Neg logit contributions | |
avail | -0.084 |
lor | -0.074 |
sel | -0.065 |
ucer | -0.063 |
cer | -0.058 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
about | +0.019 |
hog | +0.018 |
ranger | +0.017 |
Sharing | +0.016 |
Tim | +0.016 |
Neg logit contributions | |
avail | -0.043 |
lor | -0.038 |
reality | -0.038 |
growth | -0.036 |
sel | -0.035 |
Token | from |
Token ID | 422 |
Feature activation | -4.49e-04 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
Tim | +0.005 |
ranger | +0.005 |
: | +0.005 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.008 |
Beck | -0.008 |
ucer | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
about | +0.001 |
hog | +0.001 |
ranger | +0.001 |
Sharing | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
avail | -0.001 |
reality | -0.001 |
lor | -0.001 |
growth | -0.001 |
suitcase | -0.001 |
Token | zip |
Token ID | 19974 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.012 |
reality | +0.012 |
sel | +0.011 |
growth | +0.011 |
Neg logit contributions | |
about | -0.014 |
hog | -0.013 |
ranger | -0.013 |
Tim | -0.013 |
: | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.006 |
reality | +0.006 |
Beck | +0.006 |
growth | +0.006 |
Neg logit contributions | |
hog | -0.006 |
about | -0.006 |
ranger | -0.005 |
trucks | -0.005 |
Tim | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
avail | +0.019 |
lor | +0.017 |
reality | +0.017 |
Beck | +0.015 |
growth | +0.015 |
Neg logit contributions | |
about | -0.018 |
hog | -0.017 |
ranger | -0.016 |
Tim | -0.016 |
Sharing | -0.015 |
Token | end |
Token ID | 886 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
avail | +0.005 |
reality | +0.004 |
lor | +0.004 |
suitcase | +0.004 |
Beck | +0.004 |
Neg logit contributions | |
about | -0.005 |
hog | -0.004 |
Tim | -0.004 |
Sharing | -0.004 |
ranger | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
hog | +0.031 |
automobiles | +0.029 |
ranger | +0.029 |
Sharing | +0.029 |
Tim | +0.029 |
Neg logit contributions | |
avail | -0.027 |
reality | -0.025 |
lor | -0.023 |
Beck | -0.021 |
outer | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
avail | +0.031 |
lor | +0.027 |
reality | +0.027 |
suitcase | +0.025 |
sel | +0.025 |
Neg logit contributions | |
about | -0.012 |
Tim | -0.010 |
hog | -0.009 |
Sharing | -0.009 |
ranger | -0.009 |
Token | Mon |
Token ID | 9069 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
avail | +0.022 |
reality | +0.019 |
lor | +0.017 |
sel | +0.017 |
arse | +0.016 |
Neg logit contributions | |
about | -0.016 |
Tim | -0.015 |
: | -0.015 |
hog | -0.014 |
Sharing | -0.013 |
Token | key |
Token ID | 2539 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
about | +0.104 |
Sharing | +0.095 |
hog | +0.092 |
ranger | +0.089 |
aring | +0.085 |
Neg logit contributions | |
avail | -0.085 |
lor | -0.074 |
reality | -0.065 |
arse | -0.060 |
suitcase | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
about | +0.033 |
hog | +0.031 |
ranger | +0.030 |
Sharing | +0.029 |
automobiles | +0.028 |
Neg logit contributions | |
avail | -0.054 |
lor | -0.051 |
reality | -0.049 |
sel | -0.047 |
awoke | -0.047 |
Token | very |
Token ID | 845 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.014 |
lor | +0.013 |
Beck | +0.012 |
suitcase | +0.012 |
Neg logit contributions | |
about | -0.013 |
hog | -0.013 |
ranger | -0.012 |
Sharing | -0.011 |
Tim | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
avail | +0.004 |
reality | +0.004 |
Avery | +0.003 |
suitcase | +0.003 |
Beck | +0.003 |
Neg logit contributions | |
hog | -0.003 |
about | -0.003 |
ranger | -0.003 |
Sharing | -0.003 |
automobiles | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
avail | +0.011 |
reality | +0.009 |
lor | +0.009 |
suitcase | +0.009 |
sel | +0.008 |
Neg logit contributions | |
hog | -0.007 |
ranger | -0.006 |
about | -0.006 |
Sharing | -0.006 |
Tim | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
avail | +0.010 |
reality | +0.009 |
sel | +0.009 |
suitcase | +0.009 |
lor | +0.009 |
Neg logit contributions | |
about | -0.010 |
hog | -0.009 |
ranger | -0.009 |
Sharing | -0.009 |
aring | -0.008 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
about | +0.008 |
hog | +0.007 |
ranger | +0.007 |
Tim | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.008 |
lor | -0.008 |
sel | -0.007 |
suitcase | -0.007 |
Token | an |
Token ID | 281 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
hog | +0.022 |
about | +0.021 |
ranger | +0.020 |
Tim | +0.020 |
Sharing | +0.019 |
Neg logit contributions | |
avail | -0.023 |
reality | -0.020 |
lor | -0.020 |
suitcase | -0.018 |
growth | -0.017 |
Token | important |
Token ID | 1593 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
hog | +0.031 |
ranger | +0.031 |
Tim | +0.029 |
Sharing | +0.028 |
o | +0.028 |
Neg logit contributions | |
avail | -0.058 |
reality | -0.056 |
lor | -0.046 |
ices | -0.046 |
outer | -0.045 |
Token | lesson |
Token ID | 11483 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
about | +0.028 |
hog | +0.027 |
Tim | +0.026 |
ranger | +0.025 |
Sharing | +0.024 |
Neg logit contributions | |
avail | -0.048 |
reality | -0.042 |
lor | -0.042 |
suitcase | -0.038 |
ucer | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
hog | +0.015 |
ranger | +0.013 |
about | +0.013 |
Tim | +0.013 |
elephant | +0.012 |
Neg logit contributions | |
avail | -0.028 |
lor | -0.025 |
reality | -0.025 |
sel | -0.022 |
suitcase | -0.022 |
Token | with |
Token ID | 4480 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
about | +0.070 |
Tim | +0.066 |
ranger | +0.065 |
trucks | +0.065 |
hog | +0.064 |
Neg logit contributions | |
lor | -0.095 |
avail | -0.095 |
reality | -0.086 |
ucer | -0.084 |
sel | -0.084 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
about | +0.012 |
hog | +0.012 |
ranger | +0.011 |
Tim | +0.010 |
Sharing | +0.010 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.013 |
lor | -0.013 |
growth | -0.012 |
sel | -0.012 |
Token | work |
Token ID | 670 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
about | +0.029 |
hog | +0.026 |
ranger | +0.025 |
Tim | +0.025 |
: | +0.024 |
Neg logit contributions | |
avail | -0.039 |
lor | -0.035 |
reality | -0.034 |
growth | -0.031 |
ucer | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-04 |
Pos logit contributions | |
hog | +0.033 |
ranger | +0.032 |
about | +0.031 |
Tim | +0.031 |
elephant | +0.030 |
Neg logit contributions | |
avail | -0.053 |
reality | -0.048 |
lor | -0.047 |
sel | -0.043 |
suitcase | -0.043 |
Token | determination |
Token ID | 12123 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
ranger | +0.000 |
Tim | +0.000 |
Sharing | +0.000 |
Neg logit contributions | |
avail | -0.000 |
reality | -0.000 |
lor | -0.000 |
sel | -0.000 |
growth | -0.000 |
Token | little |
Token ID | 1310 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
about | +0.025 |
hog | +0.024 |
ranger | +0.024 |
Sharing | +0.022 |
Tim | +0.022 |
Neg logit contributions | |
avail | -0.022 |
reality | -0.018 |
lor | -0.018 |
Beck | -0.016 |
suitcase | -0.016 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
avail | +0.015 |
reality | +0.013 |
lor | +0.012 |
suitcase | +0.012 |
Beck | +0.012 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
Sharing | -0.010 |
ranger | -0.010 |
aring | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.006 |
lor | -0.005 |
reality | -0.005 |
growth | -0.005 |
Beck | -0.005 |
Token | feeling |
Token ID | 4203 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
about | +0.011 |
Tim | +0.009 |
hog | +0.009 |
ranger | +0.009 |
: | +0.008 |
Neg logit contributions | |
avail | -0.020 |
lor | -0.018 |
reality | -0.018 |
ucer | -0.017 |
sel | -0.016 |
Token | very |
Token ID | 845 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.013 |
reality | +0.013 |
ucer | +0.012 |
growth | +0.012 |
Neg logit contributions | |
about | -0.006 |
hog | -0.005 |
Tim | -0.005 |
ranger | -0.005 |
: | -0.005 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
about | +0.012 |
hog | +0.011 |
ranger | +0.011 |
Tim | +0.011 |
Sharing | +0.010 |
Neg logit contributions | |
avail | -0.020 |
lor | -0.018 |
reality | -0.018 |
growth | -0.016 |
ucer | -0.016 |
Token | y |
Token ID | 88 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
about | +0.096 |
hog | +0.095 |
ranger | +0.093 |
Tim | +0.089 |
Sharing | +0.087 |
Neg logit contributions | |
avail | -0.077 |
lor | -0.066 |
reality | -0.066 |
ucer | -0.061 |
sel | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
about | +0.003 |
ranger | +0.003 |
hog | +0.003 |
Tim | +0.003 |
moms | +0.003 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
lor | -0.003 |
suitcase | -0.003 |
sel | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
hog | +0.008 |
ranger | +0.007 |
aring | +0.007 |
about | +0.007 |
ike | +0.007 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.005 |
Avery | -0.005 |
growth | -0.005 |
Beck | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
avail | +0.003 |
P | +0.003 |
awoke | +0.003 |
reality | +0.003 |
Beck | +0.003 |
Neg logit contributions | |
hog | -0.004 |
ranger | -0.004 |
aring | -0.003 |
about | -0.003 |
ooters | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
avail | +0.004 |
reality | +0.004 |
anything | +0.004 |
Avery | +0.003 |
veil | +0.003 |
Neg logit contributions | |
hog | -0.003 |
aring | -0.003 |
ranger | -0.002 |
ike | -0.002 |
uddy | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
avail | +0.020 |
lor | +0.019 |
reality | +0.018 |
sel | +0.017 |
suitcase | +0.016 |
Neg logit contributions | |
about | -0.013 |
hog | -0.012 |
Tim | -0.012 |
Sharing | -0.012 |
ranger | -0.012 |
Token | saved |
Token ID | 7448 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.002 |
ranger | +0.002 |
Tim | +0.002 |
Sharing | +0.002 |
Neg logit contributions | |
avail | -0.004 |
lor | -0.003 |
reality | -0.003 |
growth | -0.003 |
sel | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
ranger | +0.013 |
Sharing | +0.013 |
Tim | +0.013 |
Neg logit contributions | |
avail | -0.018 |
reality | -0.015 |
lor | -0.015 |
growth | -0.013 |
Beck | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
about | +0.016 |
hog | +0.015 |
ranger | +0.015 |
Tim | +0.014 |
Sharing | +0.014 |
Neg logit contributions | |
avail | -0.023 |
reality | -0.021 |
lor | -0.021 |
suitcase | -0.018 |
sel | -0.018 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
about | +0.020 |
hog | +0.019 |
ranger | +0.017 |
trucks | +0.016 |
aring | +0.016 |
Neg logit contributions | |
avail | -0.030 |
lor | -0.028 |
reality | -0.027 |
growth | -0.026 |
Beck | -0.025 |
Token | Charl |
Token ID | 24453 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.010 |
lor | +0.010 |
sel | +0.009 |
suitcase | +0.009 |
Neg logit contributions | |
about | -0.006 |
Tim | -0.005 |
hog | -0.005 |
: | -0.005 |
ranger | -0.005 |
Token | otte |
Token ID | 11404 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
about | +0.116 |
hog | +0.104 |
ranger | +0.104 |
Tim | +0.102 |
Sharing | +0.099 |
Neg logit contributions | |
avail | -0.070 |
lor | -0.061 |
reality | -0.056 |
Beck | -0.050 |
Elsa | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
about | +0.025 |
hog | +0.023 |
ranger | +0.022 |
Sharing | +0.021 |
Tim | +0.020 |
Neg logit contributions | |
avail | -0.041 |
lor | -0.039 |
reality | -0.037 |
suitcase | -0.036 |
sel | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | +2.59e-04 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.004 |
growth | -0.004 |
Beck | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.30e-04 |
Pos logit contributions | |
avail | +0.001 |
lor | +0.001 |
reality | +0.001 |
suitcase | +0.001 |
growth | +0.001 |
Neg logit contributions | |
about | -0.000 |
hog | -0.000 |
ranger | -0.000 |
Tim | -0.000 |
Sharing | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
hog | +0.001 |
about | +0.001 |
ranger | +0.001 |
Sharing | +0.001 |
aring | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
lor | -0.002 |
suitcase | -0.001 |
awoke | -0.001 |
Token | princess |
Token ID | 21752 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
ranger | +0.000 |
Tim | +0.000 |
Sharing | +0.000 |
Neg logit contributions | |
avail | -0.001 |
reality | -0.001 |
lor | -0.000 |
suitcase | -0.000 |
Beck | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
avail | +0.010 |
lor | +0.009 |
reality | +0.009 |
growth | +0.008 |
ucer | +0.008 |
Neg logit contributions | |
about | -0.004 |
hog | -0.004 |
ranger | -0.004 |
Tim | -0.004 |
Sharing | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
about | +0.008 |
hog | +0.007 |
Tim | +0.007 |
ranger | +0.006 |
Sharing | +0.006 |
Neg logit contributions | |
avail | -0.014 |
lor | -0.012 |
reality | -0.012 |
suitcase | -0.011 |
ucer | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -7.94e-03 |
Pos logit contributions | |
avail | +0.020 |
lor | +0.018 |
reality | +0.018 |
Beck | +0.017 |
growth | +0.017 |
Neg logit contributions | |
about | -0.009 |
hog | -0.008 |
ranger | -0.008 |
Tim | -0.008 |
Sharing | -0.007 |
Token | very |
Token ID | 845 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
about | +0.009 |
hog | +0.008 |
ranger | +0.008 |
Tim | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.019 |
lor | -0.017 |
reality | -0.017 |
Beck | -0.016 |
suitcase | -0.016 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
about | +0.021 |
hog | +0.019 |
ranger | +0.018 |
Sharing | +0.018 |
Tim | +0.018 |
Neg logit contributions | |
avail | -0.029 |
reality | -0.025 |
lor | -0.025 |
Beck | -0.024 |
Elsa | -0.024 |
Token | y |
Token ID | 88 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
hog | +0.101 |
ranger | +0.101 |
about | +0.100 |
Tim | +0.095 |
Sharing | +0.090 |
Neg logit contributions | |
avail | -0.065 |
lor | -0.056 |
reality | -0.056 |
ucer | -0.054 |
sel | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -7.86e-03 |
Pos logit contributions | |
Tim | +0.015 |
hog | +0.014 |
ranger | +0.014 |
about | +0.014 |
ooters | +0.014 |
Neg logit contributions | |
avail | -0.018 |
reality | -0.018 |
lor | -0.018 |
suitcase | -0.016 |
sel | -0.015 |
Token | always |
Token ID | 1464 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
hog | +0.009 |
about | +0.009 |
ranger | +0.009 |
aring | +0.009 |
automobiles | +0.008 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.013 |
Avery | -0.013 |
Elsa | -0.013 |
veil | -0.013 |
Token | told |
Token ID | 1297 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
hog | +0.002 |
about | +0.002 |
ranger | +0.001 |
automobiles | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
lor | -0.002 |
ucer | -0.002 |
Beck | -0.002 |
Token | everyone |
Token ID | 2506 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
hog | +0.017 |
ranger | +0.015 |
Sharing | +0.015 |
aring | +0.015 |
ike | +0.015 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.011 |
anything | -0.010 |
veil | -0.010 |
lor | -0.010 |
Token | always |
Token ID | 1464 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
hog | +0.018 |
ranger | +0.018 |
about | +0.017 |
automobiles | +0.016 |
Sharing | +0.016 |
Neg logit contributions | |
avail | -0.017 |
reality | -0.014 |
ucer | -0.013 |
drift | -0.013 |
sel | -0.012 |
Token | have |
Token ID | 423 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
avail | +0.007 |
reality | +0.006 |
lor | +0.006 |
drift | +0.005 |
suitcase | +0.005 |
Neg logit contributions | |
hog | -0.007 |
about | -0.006 |
ranger | -0.006 |
Sharing | -0.006 |
: | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
about | +0.008 |
hog | +0.008 |
ranger | +0.007 |
Tim | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.007 |
lor | -0.007 |
suitcase | -0.007 |
growth | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.023 |
reality | +0.022 |
growth | +0.020 |
suitcase | +0.020 |
Neg logit contributions | |
about | -0.016 |
hog | -0.015 |
ranger | -0.014 |
Tim | -0.014 |
Sharing | -0.014 |
Token | so |
Token ID | 523 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
avail | +0.008 |
reality | +0.008 |
Beck | +0.007 |
lor | +0.007 |
ucer | +0.007 |
Neg logit contributions | |
hog | -0.007 |
ranger | -0.006 |
about | -0.006 |
uddy | -0.006 |
Sharing | -0.005 |
Token | nos |
Token ID | 43630 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Sharing | +0.002 |
Mark | +0.002 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
ucer | -0.003 |
sie | -0.003 |
Beck | -0.003 |
Token | y |
Token ID | 88 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
ranger | +0.107 |
about | +0.107 |
hog | +0.103 |
Tim | +0.099 |
not | +0.098 |
Neg logit contributions | |
avail | -0.060 |
lor | -0.049 |
reality | -0.045 |
ices | -0.042 |
ucer | -0.042 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
hog | +0.013 |
about | +0.012 |
Sharing | +0.012 |
ranger | +0.012 |
Tim | +0.011 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.014 |
lor | -0.014 |
suitcase | -0.012 |
ucer | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
about | +0.029 |
hog | +0.028 |
ranger | +0.027 |
aring | +0.026 |
trucks | +0.025 |
Neg logit contributions | |
avail | -0.030 |
lor | -0.026 |
Elsa | -0.026 |
Beck | -0.026 |
growth | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
hog | +0.011 |
about | +0.011 |
ranger | +0.011 |
trucks | +0.010 |
automobiles | +0.010 |
Neg logit contributions | |
avail | -0.014 |
lor | -0.013 |
Beck | -0.012 |
reality | -0.012 |
Elsa | -0.012 |
Token | Amy |
Token ID | 40797 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
about | +0.012 |
trucks | +0.010 |
hog | +0.010 |
automobiles | +0.010 |
ranger | +0.010 |
Neg logit contributions | |
avail | -0.007 |
lor | -0.007 |
Beck | -0.006 |
Elsa | -0.006 |
P | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
about | +0.008 |
Sharing | +0.008 |
hog | +0.008 |
ranger | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
avail | -0.015 |
lor | -0.015 |
reality | -0.014 |
suitcase | -0.013 |
ucer | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
ucer | +0.005 |
growth | +0.005 |
Neg logit contributions | |
about | -0.006 |
hog | -0.005 |
Tim | -0.005 |
ranger | -0.005 |
Sharing | -0.005 |
Token | straw |
Token ID | 14787 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.007 |
ranger | +0.006 |
Tim | +0.006 |
: | +0.006 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.008 |
reality | -0.008 |
growth | -0.008 |
sel | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.013 |
reality | +0.013 |
suitcase | +0.012 |
sel | +0.012 |
Neg logit contributions | |
about | -0.007 |
Sharing | -0.006 |
ranger | -0.006 |
Tim | -0.006 |
hog | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
about | +0.002 |
Tim | +0.002 |
hog | +0.002 |
ranger | +0.002 |
Sharing | +0.001 |
Neg logit contributions | |
avail | -0.004 |
lor | -0.004 |
reality | -0.004 |
suitcase | -0.004 |
sel | -0.004 |
Token | Sp |
Token ID | 4561 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
avail | +0.015 |
reality | +0.013 |
lor | +0.012 |
sel | +0.011 |
arse | +0.011 |
Neg logit contributions | |
about | -0.013 |
Tim | -0.012 |
: | -0.012 |
hog | -0.011 |
ranger | -0.011 |
Token | ike |
Token ID | 522 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
ranger | +0.086 |
about | +0.084 |
Tim | +0.082 |
hog | +0.082 |
trucks | +0.080 |
Neg logit contributions | |
lor | -0.084 |
avail | -0.078 |
reality | -0.075 |
ices | -0.072 |
ucer | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
about | +0.032 |
hog | +0.029 |
ranger | +0.029 |
automobiles | +0.028 |
Sharing | +0.028 |
Neg logit contributions | |
avail | -0.046 |
lor | -0.044 |
awoke | -0.043 |
reality | -0.043 |
growth | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
avail | +0.020 |
reality | +0.017 |
lor | +0.017 |
suitcase | +0.015 |
Beck | +0.015 |
Neg logit contributions | |
hog | -0.015 |
about | -0.015 |
ranger | -0.015 |
Sharing | -0.013 |
Tim | -0.013 |
Token | puppy |
Token ID | 26188 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
avail | +0.030 |
reality | +0.027 |
lor | +0.024 |
suitcase | +0.024 |
Beck | +0.024 |
Neg logit contributions | |
about | -0.026 |
hog | -0.023 |
ranger | -0.022 |
Sharing | -0.021 |
Tim | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.49e-04 |
Pos logit contributions | |
avail | +0.006 |
reality | +0.006 |
lor | +0.006 |
suitcase | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.005 |
ranger | -0.005 |
hog | -0.005 |
moms | -0.005 |
disl | -0.005 |
Token | nut |
Token ID | 6701 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.002 |
reality | +0.002 |
Beck | +0.001 |
growth | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Tim | -0.001 |
: | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
about | +0.009 |
hog | +0.009 |
Sharing | +0.009 |
ranger | +0.009 |
Tim | +0.008 |
Neg logit contributions | |
avail | -0.011 |
lor | -0.010 |
reality | -0.009 |
ucer | -0.009 |
sel | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -9.47e-04 |
Pos logit contributions | |
about | +0.010 |
hog | +0.010 |
ranger | +0.009 |
trucks | +0.009 |
elephant | +0.009 |
Neg logit contributions | |
avail | -0.016 |
lor | -0.014 |
growth | -0.014 |
reality | -0.013 |
suitcase | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
about | +0.001 |
hog | +0.001 |
ranger | +0.001 |
Tim | +0.001 |
Sharing | +0.001 |
Neg logit contributions | |
avail | -0.002 |
lor | -0.002 |
reality | -0.002 |
growth | -0.002 |
ucer | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +9.15e-04 |
Pos logit contributions | |
avail | +0.003 |
lor | +0.003 |
reality | +0.002 |
Beck | +0.002 |
Elsa | +0.002 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
Tim | -0.002 |
trucks | -0.002 |
Token | Sp |
Token ID | 4561 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.001 |
reality | +0.001 |
Beck | +0.001 |
Elsa | +0.001 |
Neg logit contributions | |
about | -0.002 |
hog | -0.001 |
Tim | -0.001 |
ranger | -0.001 |
Sharing | -0.001 |
Token | ike |
Token ID | 522 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
about | +0.046 |
Tim | +0.043 |
ranger | +0.039 |
trucks | +0.038 |
automobiles | +0.037 |
Neg logit contributions | |
lor | -0.124 |
avail | -0.120 |
reality | -0.113 |
ucer | -0.113 |
ices | -0.110 |
Token | looked |
Token ID | 3114 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
about | +0.031 |
Sharing | +0.031 |
automobiles | +0.029 |
ooters | +0.028 |
ranger | +0.028 |
Neg logit contributions | |
avail | -0.024 |
lor | -0.023 |
awoke | -0.022 |
Beck | -0.022 |
growth | -0.021 |
Token | around |
Token ID | 1088 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.011 |
suitcase | +0.011 |
awoke | +0.010 |
further | +0.010 |
Neg logit contributions | |
Sharing | -0.015 |
ranger | -0.015 |
moms | -0.015 |
uddy | -0.014 |
hog | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
hog | +0.010 |
Sharing | +0.010 |
aring | +0.010 |
automobiles | +0.009 |
about | +0.009 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.017 |
growth | -0.016 |
valleys | -0.016 |
suitcase | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
avail | +0.005 |
reality | +0.004 |
Beck | +0.004 |
valleys | +0.004 |
Avery | +0.003 |
Neg logit contributions | |
about | -0.006 |
automobiles | -0.006 |
Sharing | -0.006 |
hog | -0.006 |
aring | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
Tim | +0.003 |
ranger | +0.003 |
Sharing | +0.002 |
Neg logit contributions | |
avail | -0.006 |
lor | -0.005 |
reality | -0.005 |
growth | -0.005 |
sel | -0.005 |
Token | Her |
Token ID | 2332 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
aring | +0.005 |
ranger | +0.005 |
asuring | +0.005 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
Beck | -0.007 |
Elsa | -0.007 |
reality | -0.007 |
Token | friend |
Token ID | 1545 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
Sharing | +0.014 |
trucks | +0.013 |
ranger | +0.013 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.015 |
lor | -0.015 |
suitcase | -0.014 |
Beck | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
hog | +0.006 |
neys | +0.006 |
ooters | +0.006 |
ranger | +0.006 |
about | +0.006 |
Neg logit contributions | |
avail | -0.006 |
awoke | -0.005 |
Beck | -0.005 |
aire | -0.005 |
Avery | -0.004 |
Token | being |
Token ID | 852 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
hog | +0.013 |
meanings | +0.012 |
aring | +0.012 |
uddy | +0.012 |
ooters | +0.012 |
Neg logit contributions | |
avail | -0.017 |
reality | -0.015 |
Elsa | -0.014 |
Beck | -0.014 |
Avery | -0.014 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
about | +0.023 |
hog | +0.022 |
ranger | +0.020 |
: | +0.019 |
Sharing | +0.019 |
Neg logit contributions | |
avail | -0.044 |
reality | -0.039 |
lor | -0.038 |
Beck | -0.037 |
Elsa | -0.037 |
Token | y |
Token ID | 88 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
hog | +0.111 |
ranger | +0.110 |
moms | +0.104 |
about | +0.101 |
Tim | +0.100 |
Neg logit contributions | |
avail | -0.048 |
ucer | -0.043 |
lor | -0.039 |
cer | -0.039 |
reality | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
ranger | +0.009 |
moms | +0.009 |
hog | +0.009 |
disl | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.015 |
lor | -0.014 |
suitcase | -0.014 |
ices | -0.013 |
Token | telling |
Token ID | 5149 |
Feature activation | +9.28e-04 |
Pos logit contributions | |
about | +0.011 |
hog | +0.011 |
aring | +0.011 |
uddy | +0.010 |
ranger | +0.010 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.011 |
ucer | -0.011 |
eling | -0.010 |
sie | -0.010 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.07e-04 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
anything | +0.001 |
Avery | +0.001 |
Beck | +0.001 |
Neg logit contributions | |
hog | -0.002 |
ranger | -0.002 |
about | -0.002 |
uddy | -0.002 |
Sharing | -0.002 |
Token | what |
Token ID | 644 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
lor | +0.001 |
anything | +0.001 |
ucer | +0.001 |
Neg logit contributions | |
hog | -0.000 |
ranger | -0.000 |
about | -0.000 |
driver | -0.000 |
Sharing | -0.000 |
Token | around |
Token ID | 1088 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
avail | +0.023 |
reality | +0.020 |
lor | +0.020 |
growth | +0.019 |
sel | +0.019 |
Neg logit contributions | |
about | -0.012 |
hog | -0.011 |
ranger | -0.011 |
Sharing | -0.010 |
Tim | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
about | +0.008 |
hog | +0.007 |
ranger | +0.007 |
Sharing | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.011 |
lor | -0.011 |
growth | -0.010 |
Beck | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.003 |
ucer | +0.003 |
reality | +0.003 |
sel | +0.003 |
Neg logit contributions | |
about | -0.002 |
Tim | -0.002 |
ranger | -0.002 |
hog | -0.002 |
: | -0.002 |
Token | water |
Token ID | 1660 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
avail | +0.021 |
lor | +0.018 |
reality | +0.018 |
growth | +0.016 |
suitcase | +0.016 |
Neg logit contributions | |
about | -0.019 |
hog | -0.018 |
ranger | -0.017 |
Tim | -0.017 |
Sharing | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-04 |
Pos logit contributions | |
avail | +0.008 |
lor | +0.007 |
reality | +0.007 |
sel | +0.006 |
suitcase | +0.006 |
Neg logit contributions | |
about | -0.005 |
hog | -0.005 |
ranger | -0.005 |
Tim | -0.005 |
Sharing | -0.004 |
Token | When |
Token ID | 1649 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
avail | +0.000 |
lor | +0.000 |
reality | +0.000 |
growth | +0.000 |
Beck | +0.000 |
Neg logit contributions | |
about | -0.000 |
hog | -0.000 |
ranger | -0.000 |
Tim | -0.000 |
trucks | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
avail | +0.062 |
lor | +0.061 |
sel | +0.055 |
reality | +0.054 |
ucer | +0.053 |
Neg logit contributions | |
Tim | -0.046 |
about | -0.045 |
ranger | -0.040 |
: | -0.038 |
hog | -0.038 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.004 |
reality | +0.004 |
growth | +0.003 |
ucer | +0.003 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
: | -0.003 |
Token | up |
Token ID | 510 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.005 |
Tim | +0.005 |
Sharing | +0.005 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.006 |
lor | -0.006 |
suitcase | -0.005 |
Beck | -0.005 |
Token | again |
Token ID | 757 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.003 |
lor | +0.003 |
suitcase | +0.003 |
growth | +0.003 |
Neg logit contributions | |
about | -0.002 |
hog | -0.001 |
ranger | -0.001 |
Sharing | -0.001 |
Tim | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.006 |
Tim | +0.005 |
ranger | +0.005 |
: | +0.005 |
Neg logit contributions | |
avail | -0.018 |
lor | -0.017 |
reality | -0.016 |
growth | -0.015 |
ucer | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.023 |
reality | +0.023 |
growth | +0.021 |
sel | +0.021 |
Neg logit contributions | |
about | -0.014 |
hog | -0.013 |
ranger | -0.012 |
Tim | -0.012 |
Sharing | -0.011 |
Token | their |
Token ID | 511 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
avail | +0.025 |
lor | +0.024 |
reality | +0.022 |
ucer | +0.021 |
growth | +0.021 |
Neg logit contributions | |
about | -0.012 |
Tim | -0.010 |
ranger | -0.009 |
hog | -0.009 |
: | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
aring | +0.013 |
Sharing | +0.013 |
ike | +0.012 |
Neg logit contributions | |
avail | -0.018 |
suitcase | -0.016 |
reality | -0.016 |
veil | -0.015 |
ucer | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
avail | +0.028 |
lor | +0.024 |
reality | +0.024 |
suitcase | +0.022 |
sel | +0.022 |
Neg logit contributions | |
about | -0.021 |
hog | -0.020 |
ranger | -0.019 |
Tim | -0.018 |
Sharing | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.010 |
growth | +0.010 |
Avery | +0.010 |
suitcase | +0.010 |
Neg logit contributions | |
hog | -0.007 |
about | -0.006 |
ranger | -0.006 |
aring | -0.006 |
elephant | -0.006 |
Token | held |
Token ID | 2714 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
lor | -0.003 |
sel | -0.003 |
suitcase | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
avail | +0.068 |
lor | +0.059 |
reality | +0.058 |
growth | +0.053 |
sel | +0.053 |
Neg logit contributions | |
about | -0.048 |
hog | -0.044 |
ranger | -0.043 |
Tim | -0.042 |
Sharing | -0.040 |
Token | letter |
Token ID | 3850 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.006 |
reality | -0.005 |
lor | -0.005 |
suitcase | -0.005 |
growth | -0.004 |
Token | tightly |
Token ID | 17707 |
Feature activation | +3.44e-04 |
Pos logit contributions | |
avail | +0.009 |
suitcase | +0.008 |
sel | +0.008 |
reality | +0.008 |
ucer | +0.008 |
Neg logit contributions | |
Sharing | -0.005 |
disl | -0.005 |
about | -0.005 |
hog | -0.005 |
Tim | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
suitcase | +0.001 |
lor | +0.001 |
sel | +0.001 |
Neg logit contributions | |
hog | -0.000 |
ranger | -0.000 |
about | -0.000 |
Sharing | -0.000 |
aring | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
avail | +0.031 |
reality | +0.027 |
lor | +0.026 |
growth | +0.026 |
Avery | +0.025 |
Neg logit contributions | |
hog | -0.016 |
about | -0.015 |
ranger | -0.014 |
aring | -0.013 |
elephant | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
hog | +0.008 |
ranger | +0.007 |
about | +0.007 |
ike | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.008 |
reality | -0.007 |
lor | -0.007 |
suitcase | -0.006 |
Avery | -0.006 |
Token | want |
Token ID | 765 |
Feature activation | -7.55e-05 |
Pos logit contributions | |
avail | +0.035 |
lor | +0.031 |
reality | +0.030 |
growth | +0.028 |
sel | +0.027 |
Neg logit contributions | |
about | -0.024 |
hog | -0.022 |
ranger | -0.021 |
Tim | -0.021 |
Sharing | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
hog | +0.000 |
about | +0.000 |
ranger | +0.000 |
Sharing | +0.000 |
aring | +0.000 |
Neg logit contributions | |
avail | -0.000 |
lor | -0.000 |
reality | -0.000 |
growth | -0.000 |
suitcase | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
Beck | +0.006 |
ucer | +0.006 |
Neg logit contributions | |
about | -0.005 |
Tim | -0.005 |
ranger | -0.005 |
hog | -0.005 |
: | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-05 |
Pos logit contributions | |
avail | +0.005 |
lor | +0.004 |
reality | +0.004 |
growth | +0.004 |
Beck | +0.004 |
Neg logit contributions | |
about | -0.002 |
Tim | -0.002 |
hog | -0.002 |
ranger | -0.002 |
: | -0.002 |
Token | When |
Token ID | 1649 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
ranger | +0.000 |
: | +0.000 |
Tim | +0.000 |
Neg logit contributions | |
avail | -0.000 |
lor | -0.000 |
reality | -0.000 |
suitcase | -0.000 |
growth | -0.000 |
Token | can |
Token ID | 460 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
avail | +0.094 |
lor | +0.089 |
sel | +0.083 |
Beck | +0.083 |
reality | +0.082 |
Neg logit contributions | |
about | -0.043 |
Tim | -0.042 |
not | -0.035 |
ranger | -0.034 |
trucks | -0.034 |
Token | we |
Token ID | 356 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
avail | +0.037 |
reality | +0.034 |
lor | +0.034 |
sel | +0.031 |
ucer | +0.031 |
Neg logit contributions | |
about | -0.019 |
Tim | -0.019 |
hog | -0.017 |
ranger | -0.017 |
: | -0.016 |
Token | go |
Token ID | 467 |
Feature activation | +4.37e-03 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.004 |
reality | +0.004 |
suitcase | +0.003 |
growth | +0.003 |
Neg logit contributions | |
about | -0.005 |
hog | -0.004 |
ranger | -0.004 |
Tim | -0.004 |
Sharing | -0.004 |
Token | ?" |
Token ID | 1701 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
avail | +0.011 |
lor | +0.010 |
reality | +0.009 |
growth | +0.009 |
Beck | +0.009 |
Neg logit contributions | |
about | -0.005 |
Tim | -0.005 |
hog | -0.004 |
ranger | -0.004 |
: | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.005 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.009 |
reality | -0.008 |
growth | -0.008 |
suitcase | -0.008 |
Token | Y |
Token ID | 56 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
about | +0.018 |
hog | +0.017 |
Tim | +0.017 |
Sharing | +0.016 |
ranger | +0.016 |
Neg logit contributions | |
avail | -0.022 |
reality | -0.019 |
lor | -0.018 |
suitcase | -0.018 |
ucer | -0.017 |
Token | ay |
Token ID | 323 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.002 |
Tim | +0.002 |
ranger | +0.002 |
: | +0.002 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.003 |
lor | -0.003 |
growth | -0.003 |
Beck | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
avail | +0.011 |
reality | +0.010 |
lor | +0.009 |
growth | +0.009 |
Beck | +0.009 |
Neg logit contributions | |
about | -0.007 |
hog | -0.007 |
Tim | -0.007 |
ranger | -0.006 |
: | -0.006 |
Token | what |
Token ID | 644 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
hog | +0.008 |
about | +0.008 |
ranger | +0.008 |
Tim | +0.007 |
Sharing | +0.007 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.009 |
suitcase | -0.008 |
Avery | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
avail | +0.037 |
lor | +0.033 |
reality | +0.031 |
growth | +0.030 |
sel | +0.030 |
Neg logit contributions | |
about | -0.025 |
Tim | -0.020 |
: | -0.020 |
hog | -0.020 |
Sharing | -0.019 |
Token | I |
Token ID | 314 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
avail | +0.041 |
lor | +0.036 |
reality | +0.036 |
growth | +0.033 |
ucer | +0.033 |
Neg logit contributions | |
about | -0.026 |
hog | -0.023 |
Tim | -0.023 |
ranger | -0.022 |
: | -0.021 |
Token | wear |
Token ID | 5806 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
avail | +0.067 |
lor | +0.059 |
reality | +0.057 |
growth | +0.053 |
ucer | +0.052 |
Neg logit contributions | |
about | -0.050 |
hog | -0.044 |
Tim | -0.043 |
ranger | -0.042 |
: | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
avail | +0.048 |
lor | +0.043 |
reality | +0.043 |
suitcase | +0.039 |
sel | +0.039 |
Neg logit contributions | |
about | -0.027 |
hog | -0.026 |
ranger | -0.024 |
Tim | -0.023 |
Sharing | -0.022 |
Token | my |
Token ID | 616 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
about | +0.015 |
Tim | +0.013 |
: | +0.012 |
hog | +0.012 |
ranger | +0.012 |
Neg logit contributions | |
avail | -0.023 |
lor | -0.020 |
reality | -0.020 |
growth | -0.019 |
ucer | -0.019 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
avail | +0.015 |
reality | +0.013 |
lor | +0.012 |
suitcase | +0.012 |
veil | +0.011 |
Neg logit contributions | |
about | -0.012 |
hog | -0.012 |
ranger | -0.011 |
Sharing | -0.011 |
Tim | -0.011 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
avail | +0.030 |
lor | +0.026 |
reality | +0.026 |
suitcase | +0.023 |
sel | +0.023 |
Neg logit contributions | |
about | -0.025 |
hog | -0.024 |
ranger | -0.023 |
Tim | -0.023 |
Sharing | -0.022 |
Token | smile |
Token ID | 8212 |
Feature activation | +6.69e-04 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.014 |
ucer | +0.014 |
sel | +0.014 |
Neg logit contributions | |
about | -0.021 |
Tim | -0.018 |
hog | -0.018 |
ranger | -0.018 |
: | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
lor | +0.001 |
suitcase | +0.001 |
sel | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Tim | -0.001 |
Sharing | -0.001 |
Token | g |
Token ID | 308 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.014 |
lor | +0.014 |
growth | +0.012 |
suitcase | +0.012 |
Neg logit contributions | |
about | -0.013 |
hog | -0.013 |
ranger | -0.012 |
Tim | -0.012 |
Sharing | -0.011 |
Token | iggle |
Token ID | 24082 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ranger | +0.032 |
hog | +0.031 |
about | +0.030 |
trucks | +0.028 |
Sharing | +0.028 |
Neg logit contributions | |
avail | -0.022 |
reality | -0.018 |
lor | -0.017 |
ices | -0.015 |
growth | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +6.43e-04 |
Pos logit contributions | |
avail | +0.039 |
lor | +0.035 |
reality | +0.034 |
growth | +0.031 |
ucer | +0.031 |
Neg logit contributions | |
about | -0.025 |
hog | -0.023 |
ranger | -0.022 |
Tim | -0.021 |
Sharing | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
avail | +0.001 |
lor | +0.001 |
reality | +0.001 |
growth | +0.001 |
sel | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Tim | -0.001 |
: | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
avail | +0.072 |
reality | +0.063 |
lor | +0.060 |
suitcase | +0.057 |
sel | +0.055 |
Neg logit contributions | |
about | -0.058 |
hog | -0.053 |
Tim | -0.052 |
ranger | -0.051 |
Sharing | -0.051 |
Token | Bob |
Token ID | 5811 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
hog | +0.029 |
aring | +0.028 |
ranger | +0.028 |
trucks | +0.027 |
automobiles | +0.027 |
Neg logit contributions | |
lor | -0.028 |
avail | -0.028 |
growth | -0.026 |
awoke | -0.024 |
valleys | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | -7.41e-05 |
Pos logit contributions | |
awoke | +0.005 |
lor | +0.005 |
avail | +0.005 |
reality | +0.004 |
Beck | +0.004 |
Neg logit contributions | |
about | -0.005 |
automobiles | -0.005 |
hog | -0.005 |
Sharing | -0.005 |
ranger | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
Tim | +0.000 |
ranger | +0.000 |
Sharing | +0.000 |
Neg logit contributions | |
avail | -0.000 |
reality | -0.000 |
lor | -0.000 |
suitcase | -0.000 |
growth | -0.000 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
avail | +0.013 |
awoke | +0.012 |
reality | +0.012 |
lor | +0.012 |
Beck | +0.012 |
Neg logit contributions | |
Sharing | -0.013 |
hog | -0.013 |
about | -0.012 |
automobiles | -0.012 |
ranger | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.003 |
reality | +0.003 |
Beck | +0.003 |
growth | +0.003 |
Neg logit contributions | |
about | -0.004 |
Sharing | -0.004 |
hog | -0.004 |
ranger | -0.003 |
Tim | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
avail | +0.013 |
lor | +0.011 |
reality | +0.011 |
suitcase | +0.010 |
ucer | +0.010 |
Neg logit contributions | |
about | -0.007 |
Sharing | -0.006 |
hog | -0.006 |
Tim | -0.006 |
aring | -0.006 |
Token | investigate |
Token ID | 9161 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
about | +0.008 |
Tim | +0.008 |
ranger | +0.007 |
Mark | +0.007 |
hog | +0.007 |
Neg logit contributions | |
avail | -0.009 |
lor | -0.008 |
reality | -0.008 |
sel | -0.007 |
ucer | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -3.48e-04 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.003 |
lor | +0.003 |
suitcase | +0.002 |
growth | +0.002 |
Neg logit contributions | |
hog | -0.001 |
Sharing | -0.001 |
ranger | -0.001 |
about | -0.001 |
moms | -0.001 |
Token | found |
Token ID | 1043 |
Feature activation | +8.58e-03 |
Pos logit contributions | |
about | +0.001 |
Tim | +0.000 |
ranger | +0.000 |
hog | +0.000 |
: | +0.000 |
Neg logit contributions | |
avail | -0.001 |
lor | -0.001 |
reality | -0.001 |
suitcase | -0.001 |
ucer | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
avail | +0.018 |
lor | +0.016 |
reality | +0.016 |
suitcase | +0.014 |
Elsa | +0.014 |
Neg logit contributions | |
about | -0.014 |
Tim | -0.013 |
hog | -0.012 |
ranger | -0.012 |
: | -0.011 |
Token | strange |
Token ID | 6283 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
avail | +0.013 |
reality | +0.011 |
lor | +0.011 |
suitcase | +0.010 |
ucer | +0.010 |
Neg logit contributions | |
about | -0.009 |
hog | -0.008 |
Tim | -0.008 |
Sharing | -0.008 |
ranger | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.002 |
lor | +0.002 |
suitcase | +0.002 |
veil | +0.002 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
Sharing | -0.002 |
Tim | -0.002 |
ranger | -0.002 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
avail | +0.059 |
lor | +0.051 |
reality | +0.051 |
suitcase | +0.046 |
growth | +0.045 |
Neg logit contributions | |
about | -0.048 |
hog | -0.044 |
Tim | -0.042 |
ranger | -0.042 |
Sharing | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-04 |
Pos logit contributions | |
avail | +0.047 |
reality | +0.041 |
lor | +0.041 |
growth | +0.038 |
Beck | +0.038 |
Neg logit contributions | |
about | -0.026 |
hog | -0.024 |
Tim | -0.022 |
ranger | -0.022 |
: | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
avail | +0.000 |
growth | +0.000 |
lor | +0.000 |
aire | +0.000 |
Avery | +0.000 |
Neg logit contributions | |
about | -0.000 |
moms | -0.000 |
automobiles | -0.000 |
ike | -0.000 |
trucks | -0.000 |
Token | crane |
Token ID | 41175 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
about | +0.002 |
Sharing | +0.002 |
aring | +0.002 |
hog | +0.002 |
uddy | +0.002 |
Neg logit contributions | |
avail | -0.003 |
reality | -0.003 |
valleys | -0.003 |
suitcase | -0.003 |
sel | -0.003 |
Token | knew |
Token ID | 2993 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
about | +0.032 |
Sharing | +0.030 |
Tim | +0.030 |
ranger | +0.029 |
automobiles | +0.028 |
Neg logit contributions | |
lor | -0.035 |
reality | -0.033 |
avail | -0.033 |
awoke | -0.032 |
growth | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
hog | +0.006 |
ranger | +0.005 |
about | +0.005 |
Sharing | +0.005 |
aring | +0.005 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.013 |
lor | -0.012 |
anything | -0.011 |
growth | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +7.70e-04 |
Pos logit contributions | |
about | +0.035 |
ranger | +0.035 |
hog | +0.035 |
Sharing | +0.034 |
Tim | +0.033 |
Neg logit contributions | |
avail | -0.043 |
reality | -0.040 |
lor | -0.040 |
awoke | -0.037 |
Beck | -0.036 |
Token | better |
Token ID | 1365 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
avail | +0.002 |
reality | +0.002 |
lor | +0.002 |
Beck | +0.001 |
sel | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Tim | -0.001 |
Sharing | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
Tim | +0.005 |
ranger | +0.005 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.017 |
lor | -0.017 |
ucer | -0.016 |
growth | -0.015 |
Token | use |
Token ID | 779 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
sel | +0.006 |
ucer | +0.006 |
Neg logit contributions | |
about | -0.007 |
hog | -0.006 |
Tim | -0.006 |
ranger | -0.006 |
: | -0.006 |
Token | its |
Token ID | 663 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
about | +0.013 |
hog | +0.013 |
ranger | +0.013 |
Tim | +0.012 |
Sharing | +0.012 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.014 |
lor | -0.013 |
growth | -0.012 |
suitcase | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | -7.88e-04 |
Pos logit contributions | |
about | +0.018 |
hog | +0.017 |
Sharing | +0.017 |
Tim | +0.016 |
ranger | +0.016 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.014 |
lor | -0.014 |
suitcase | -0.012 |
growth | -0.012 |
Token | ak |
Token ID | 461 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
about | +0.001 |
hog | +0.001 |
Tim | +0.001 |
ranger | +0.001 |
: | +0.001 |
Neg logit contributions | |
avail | -0.002 |
lor | -0.001 |
reality | -0.001 |
growth | -0.001 |
suitcase | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
avail | +0.008 |
reality | +0.008 |
lor | +0.008 |
sel | +0.007 |
suitcase | +0.007 |
Neg logit contributions | |
about | -0.004 |
hog | -0.004 |
Tim | -0.004 |
ranger | -0.004 |
Sharing | -0.003 |
Token | feathers |
Token ID | 27400 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
avail | +0.006 |
reality | +0.005 |
lor | +0.005 |
growth | +0.005 |
sel | +0.005 |
Neg logit contributions | |
about | -0.006 |
hog | -0.005 |
ranger | -0.005 |
Sharing | -0.005 |
Tim | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
avail | +0.041 |
lor | +0.039 |
sel | +0.037 |
reality | +0.037 |
ucer | +0.036 |
Neg logit contributions | |
ranger | -0.022 |
hog | -0.022 |
about | -0.021 |
Sharing | -0.021 |
Tim | -0.021 |
Token | were |
Token ID | 547 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
avail | +0.015 |
reality | +0.013 |
lor | +0.013 |
growth | +0.012 |
sel | +0.012 |
Neg logit contributions | |
about | -0.013 |
hog | -0.012 |
ranger | -0.011 |
Sharing | -0.011 |
aring | -0.011 |
Token | singing |
Token ID | 13777 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
avail | +0.020 |
reality | +0.019 |
lor | +0.017 |
Beck | +0.017 |
sel | +0.016 |
Neg logit contributions | |
hog | -0.014 |
ranger | -0.014 |
Sharing | -0.014 |
aring | -0.013 |
about | -0.013 |
Token | songs |
Token ID | 7259 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
avail | +0.041 |
reality | +0.038 |
lor | +0.037 |
Beck | +0.034 |
sel | +0.034 |
Neg logit contributions | |
about | -0.028 |
hog | -0.027 |
ranger | -0.027 |
Sharing | -0.026 |
Tim | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
avail | +0.026 |
lor | +0.024 |
reality | +0.024 |
sel | +0.022 |
suitcase | +0.021 |
Neg logit contributions | |
hog | -0.021 |
ranger | -0.020 |
Tim | -0.020 |
about | -0.019 |
Sharing | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
avail | +0.039 |
reality | +0.033 |
lor | +0.033 |
growth | +0.030 |
Beck | +0.029 |
Neg logit contributions | |
about | -0.034 |
hog | -0.032 |
ranger | -0.031 |
Tim | -0.030 |
Sharing | -0.029 |
Token | music |
Token ID | 2647 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
about | +0.009 |
hog | +0.009 |
Tim | +0.008 |
ranger | +0.008 |
Sharing | +0.008 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.010 |
lor | -0.010 |
Beck | -0.009 |
sel | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
avail | +0.024 |
reality | +0.021 |
lor | +0.021 |
sel | +0.019 |
suitcase | +0.019 |
Neg logit contributions | |
about | -0.018 |
hog | -0.017 |
ranger | -0.016 |
Tim | -0.016 |
Sharing | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.013 |
lor | +0.013 |
growth | +0.012 |
Beck | +0.012 |
Neg logit contributions | |
about | -0.012 |
hog | -0.012 |
ranger | -0.011 |
Tim | -0.011 |
Sharing | -0.010 |
Token | wind |
Token ID | 2344 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
avail | +0.008 |
reality | +0.007 |
lor | +0.007 |
Beck | +0.007 |
valleys | +0.006 |
Neg logit contributions | |
about | -0.008 |
hog | -0.007 |
Tim | -0.007 |
ranger | -0.007 |
Sharing | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
about | +0.017 |
hog | +0.015 |
ranger | +0.014 |
Tim | +0.014 |
Sharing | +0.013 |
Neg logit contributions | |
avail | -0.033 |
lor | -0.030 |
reality | -0.029 |
growth | -0.027 |
ucer | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
about | +0.011 |
hog | +0.009 |
Tim | +0.009 |
ranger | +0.009 |
: | +0.008 |
Neg logit contributions | |
avail | -0.024 |
lor | -0.021 |
reality | -0.021 |
sel | -0.019 |
suitcase | -0.019 |
Token | In |
Token ID | 818 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.002 |
lor | +0.002 |
suitcase | +0.002 |
sel | +0.002 |
Neg logit contributions | |
about | -0.002 |
Tim | -0.002 |
hog | -0.002 |
ranger | -0.002 |
: | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-04 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.006 |
reality | +0.005 |
sel | +0.005 |
ucer | +0.005 |
Neg logit contributions | |
about | -0.003 |
Tim | -0.002 |
ranger | -0.002 |
: | -0.002 |
hog | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
ranger | +0.000 |
Tim | +0.000 |
Sharing | +0.000 |
Neg logit contributions | |
avail | -0.000 |
lor | -0.000 |
reality | -0.000 |
sel | -0.000 |
growth | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
ranger | +0.013 |
Tim | +0.012 |
Sharing | +0.012 |
Neg logit contributions | |
avail | -0.030 |
lor | -0.027 |
reality | -0.026 |
ucer | -0.025 |
suitcase | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
avail | +0.014 |
lor | +0.014 |
reality | +0.013 |
sel | +0.012 |
growth | +0.012 |
Neg logit contributions | |
about | -0.005 |
Tim | -0.004 |
Tom | -0.003 |
not | -0.003 |
hog | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.013 |
reality | +0.013 |
growth | +0.012 |
ucer | +0.012 |
Neg logit contributions | |
about | -0.011 |
hog | -0.010 |
Tim | -0.010 |
ranger | -0.010 |
Sharing | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +6.39e-04 |
Pos logit contributions | |
about | +0.027 |
hog | +0.024 |
Tim | +0.024 |
ranger | +0.023 |
: | +0.022 |
Neg logit contributions | |
avail | -0.030 |
lor | -0.026 |
reality | -0.026 |
sel | -0.023 |
ucer | -0.023 |
Token | man |
Token ID | 582 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
lor | +0.001 |
suitcase | +0.001 |
ucer | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
Tim | -0.001 |
Sharing | -0.001 |
ranger | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +5.08e-03 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.014 |
reality | +0.014 |
growth | +0.013 |
sel | +0.013 |
Neg logit contributions | |
about | -0.007 |
hog | -0.006 |
ranger | -0.006 |
Tim | -0.006 |
: | -0.005 |
Token | two |
Token ID | 734 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
avail | +0.019 |
reality | +0.016 |
lor | +0.016 |
sel | +0.015 |
growth | +0.014 |
Neg logit contributions | |
hog | -0.018 |
about | -0.018 |
ranger | -0.017 |
aring | -0.016 |
Sharing | -0.016 |
Token | large |
Token ID | 1588 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
avail | +0.026 |
reality | +0.023 |
sel | +0.022 |
lor | +0.022 |
suitcase | +0.021 |
Neg logit contributions | |
hog | -0.021 |
about | -0.021 |
ranger | -0.020 |
Sharing | -0.019 |
Tim | -0.019 |
Token | pizz |
Token ID | 38748 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
avail | +0.014 |
reality | +0.011 |
suitcase | +0.011 |
sel | +0.011 |
lor | +0.011 |
Neg logit contributions | |
about | -0.011 |
hog | -0.011 |
ranger | -0.010 |
Sharing | -0.009 |
Tim | -0.009 |
Token | as |
Token ID | 292 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
avail | +0.029 |
lor | +0.027 |
reality | +0.026 |
sel | +0.025 |
ucer | +0.025 |
Neg logit contributions | |
about | -0.019 |
hog | -0.017 |
Tim | -0.017 |
ranger | -0.017 |
Sharing | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
avail | +0.025 |
reality | +0.023 |
lor | +0.022 |
sel | +0.022 |
suitcase | +0.021 |
Neg logit contributions | |
about | -0.016 |
hog | -0.016 |
Sharing | -0.015 |
ranger | -0.015 |
Tim | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
avail | +0.003 |
lor | +0.002 |
reality | +0.002 |
growth | +0.002 |
Beck | +0.002 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
Tim | -0.002 |
Sharing | -0.002 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
avail | +0.004 |
sel | +0.004 |
reality | +0.004 |
awoke | +0.003 |
suitcase | +0.003 |
Neg logit contributions | |
hog | -0.005 |
aring | -0.005 |
about | -0.005 |
Sharing | -0.005 |
ranger | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
avail | +0.024 |
reality | +0.020 |
sel | +0.019 |
lor | +0.019 |
growth | +0.018 |
Neg logit contributions | |
hog | -0.021 |
aring | -0.020 |
ranger | -0.020 |
about | -0.020 |
uddy | -0.018 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
avail | +0.004 |
reality | +0.004 |
sel | +0.003 |
lor | +0.003 |
growth | +0.003 |
Neg logit contributions | |
hog | -0.003 |
about | -0.003 |
aring | -0.003 |
ranger | -0.003 |
Sharing | -0.003 |
Token | until |
Token ID | 1566 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
avail | +0.024 |
reality | +0.021 |
lor | +0.019 |
sel | +0.019 |
growth | +0.018 |
Neg logit contributions | |
hog | -0.018 |
ranger | -0.017 |
about | -0.017 |
aring | -0.017 |
Sharing | -0.015 |
Token | there |
Token ID | 612 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
lor | +0.064 |
avail | +0.063 |
reality | +0.056 |
ucer | +0.055 |
arse | +0.055 |
Neg logit contributions | |
about | -0.032 |
Tim | -0.030 |
: | -0.027 |
ranger | -0.024 |
not | -0.024 |
Token | together |
Token ID | 1978 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.006 |
lor | -0.005 |
reality | -0.005 |
suitcase | -0.004 |
growth | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
hog | +0.017 |
ranger | +0.017 |
about | +0.015 |
Tim | +0.015 |
aring | +0.015 |
Neg logit contributions | |
avail | -0.022 |
reality | -0.019 |
lor | -0.018 |
growth | -0.017 |
sel | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
about | +0.026 |
hog | +0.025 |
ranger | +0.024 |
aring | +0.023 |
old | +0.021 |
Neg logit contributions | |
avail | -0.033 |
growth | -0.029 |
lor | -0.028 |
Beck | -0.027 |
ices | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
about | +0.003 |
hog | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.005 |
Beck | -0.005 |
growth | -0.004 |
Token | His |
Token ID | 6653 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
avail | +0.003 |
lor | +0.002 |
reality | +0.002 |
Beck | +0.002 |
growth | +0.002 |
Neg logit contributions | |
about | -0.003 |
hog | -0.003 |
ranger | -0.002 |
Tim | -0.002 |
Sharing | -0.002 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
avail | +0.008 |
reality | +0.007 |
suitcase | +0.007 |
veil | +0.006 |
Elsa | +0.006 |
Neg logit contributions | |
about | -0.007 |
Sharing | -0.006 |
hog | -0.006 |
aring | -0.006 |
ards | -0.005 |
Token | then |
Token ID | 788 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
hog | +0.011 |
ranger | +0.011 |
about | +0.011 |
Sharing | +0.010 |
aring | +0.010 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.012 |
sel | -0.011 |
awoke | -0.011 |
lor | -0.011 |
Token | offered |
Token ID | 4438 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.010 |
lor | +0.009 |
sel | +0.009 |
suitcase | +0.009 |
Neg logit contributions | |
about | -0.009 |
hog | -0.009 |
ranger | -0.008 |
Sharing | -0.008 |
aring | -0.008 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
hog | +0.011 |
aring | +0.010 |
Sharing | +0.010 |
ranger | +0.010 |
about | +0.010 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.011 |
anything | -0.011 |
ease | -0.010 |
growth | -0.010 |
Token | something |
Token ID | 1223 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.004 |
reality | +0.003 |
sel | +0.003 |
suitcase | +0.003 |
Neg logit contributions | |
hog | -0.004 |
about | -0.004 |
ranger | -0.004 |
Sharing | -0.003 |
Tim | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
hog | +0.025 |
automobiles | +0.025 |
Sharing | +0.025 |
ranger | +0.024 |
ller | +0.023 |
Neg logit contributions | |
avail | -0.036 |
reality | -0.035 |
anything | -0.031 |
suitcase | -0.030 |
lor | -0.029 |
Token | make |
Token ID | 787 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
avail | +0.031 |
lor | +0.030 |
reality | +0.027 |
ucer | +0.025 |
Beck | +0.025 |
Neg logit contributions | |
about | -0.019 |
Tim | -0.018 |
ranger | -0.016 |
hog | -0.016 |
: | -0.015 |
Token | sure |
Token ID | 1654 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
avail | +0.015 |
lor | +0.014 |
reality | +0.013 |
ucer | +0.013 |
growth | +0.013 |
Neg logit contributions | |
about | -0.010 |
Tim | -0.009 |
ranger | -0.007 |
not | -0.007 |
old | -0.007 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
avail | +0.017 |
reality | +0.015 |
lor | +0.014 |
suitcase | +0.013 |
ucer | +0.013 |
Neg logit contributions | |
hog | -0.014 |
about | -0.013 |
ranger | -0.013 |
Sharing | -0.012 |
aring | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
about | +0.015 |
hog | +0.014 |
ranger | +0.014 |
Tim | +0.013 |
Sharing | +0.013 |
Neg logit contributions | |
avail | -0.024 |
reality | -0.021 |
lor | -0.021 |
suitcase | -0.019 |
sel | -0.019 |
Token | sparkling |
Token ID | 39072 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
about | +0.006 |
hog | +0.005 |
ranger | +0.005 |
Tim | +0.005 |
Sharing | +0.005 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.009 |
suitcase | -0.008 |
ucer | -0.008 |
Token | clean |
Token ID | 3424 |
Feature activation | +7.36e-05 |
Pos logit contributions | |
avail | +0.023 |
lor | +0.021 |
reality | +0.020 |
growth | +0.019 |
Beck | +0.019 |
Neg logit contributions | |
about | -0.012 |
hog | -0.010 |
Tim | -0.010 |
ranger | -0.010 |
: | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
avail | +0.000 |
lor | +0.000 |
reality | +0.000 |
growth | +0.000 |
Beck | +0.000 |
Neg logit contributions | |
about | -0.000 |
hog | -0.000 |
Tim | -0.000 |
ranger | -0.000 |
: | -0.000 |
Token | After |
Token ID | 2293 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
about | +0.010 |
hog | +0.010 |
ranger | +0.010 |
trucks | +0.009 |
elephant | +0.009 |
Neg logit contributions | |
avail | -0.013 |
lor | -0.012 |
growth | -0.012 |
reality | -0.012 |
Beck | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
avail | +0.005 |
lor | +0.004 |
reality | +0.004 |
growth | +0.004 |
suitcase | +0.004 |
Neg logit contributions | |
about | -0.004 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
Sharing | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e-04 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.009 |
suitcase | -0.008 |
Beck | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
avail | +0.002 |
reality | +0.001 |
lor | +0.001 |
suitcase | +0.001 |
growth | +0.001 |
Neg logit contributions | |
about | -0.001 |
hog | -0.001 |
ranger | -0.001 |
Sharing | -0.001 |
: | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
about | +0.021 |
hog | +0.020 |
Sharing | +0.019 |
ranger | +0.019 |
Tim | +0.019 |
Neg logit contributions | |
avail | -0.021 |
reality | -0.018 |
lor | -0.017 |
suitcase | -0.016 |
growth | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.015 |
lor | +0.014 |
suitcase | +0.014 |
growth | +0.013 |
Neg logit contributions | |
hog | -0.017 |
ranger | -0.016 |
about | -0.016 |
Sharing | -0.015 |
Tim | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.48e-03 |
Pos logit contributions | |
avail | +0.007 |
lor | +0.006 |
reality | +0.006 |
growth | +0.006 |
Beck | +0.006 |
Neg logit contributions | |
about | -0.005 |
hog | -0.004 |
ranger | -0.004 |
trucks | -0.004 |
elephant | -0.004 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
avail | +0.010 |
reality | +0.008 |
lor | +0.008 |
sel | +0.007 |
arse | +0.007 |
Neg logit contributions | |
about | -0.011 |
Tim | -0.010 |
: | -0.010 |
hog | -0.010 |
ranger | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -9.56e-05 |
Pos logit contributions | |
about | +0.022 |
hog | +0.021 |
ranger | +0.020 |
Tim | +0.019 |
Sharing | +0.019 |
Neg logit contributions | |
avail | -0.033 |
lor | -0.030 |
reality | -0.029 |
growth | -0.027 |
sel | -0.027 |
Token | Sam |
Token ID | 3409 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
about | +0.000 |
Tim | +0.000 |
hog | +0.000 |
ranger | +0.000 |
: | +0.000 |
Neg logit contributions | |
avail | -0.000 |
lor | -0.000 |
reality | -0.000 |
sel | -0.000 |
ucer | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +2.62e-03 |
Pos logit contributions | |
about | +0.013 |
hog | +0.012 |
Tim | +0.012 |
ranger | +0.012 |
Sharing | +0.011 |
Neg logit contributions | |
avail | -0.020 |
lor | -0.017 |
reality | -0.017 |
ucer | -0.015 |
growth | -0.015 |
Token | brothers |
Token ID | 9397 |
Feature activation | +8.30e-03 |
Pos logit contributions | |
avail | +0.006 |
lor | +0.005 |
reality | +0.005 |
suitcase | +0.005 |
Beck | +0.004 |
Neg logit contributions | |
about | -0.004 |
hog | -0.003 |
ranger | -0.003 |
Tim | -0.003 |
Sharing | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.011 |
lor | +0.011 |
suitcase | +0.010 |
sel | +0.010 |
Neg logit contributions | |
hog | -0.014 |
about | -0.014 |
ranger | -0.014 |
Tim | -0.013 |
uddy | -0.013 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
hog | +0.003 |
about | +0.003 |
ranger | +0.003 |
aring | +0.003 |
automobiles | +0.003 |
Neg logit contributions | |
avail | -0.006 |
reality | -0.006 |
sel | -0.005 |
Beck | -0.005 |
awoke | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
hog | +0.017 |
aring | +0.016 |
ike | +0.015 |
Sharing | +0.014 |
uddy | +0.014 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.018 |
outer | -0.017 |
anything | -0.017 |
suitcase | -0.016 |
Token | away |
Token ID | 1497 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
avail | +0.025 |
lor | +0.019 |
reality | +0.019 |
sel | +0.018 |
suitcase | +0.017 |
Neg logit contributions | |
about | -0.033 |
hog | -0.031 |
Sharing | -0.030 |
aring | -0.030 |
ranger | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
about | +0.016 |
hog | +0.015 |
Sharing | +0.015 |
automobiles | +0.015 |
Tim | +0.015 |
Neg logit contributions | |
avail | -0.023 |
reality | -0.020 |
lor | -0.019 |
sel | -0.018 |
ucer | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.006 |
ranger | +0.006 |
: | +0.005 |
Tim | +0.005 |
Neg logit contributions | |
avail | -0.011 |
lor | -0.010 |
reality | -0.010 |
Beck | -0.009 |
growth | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
lor | +0.004 |
avail | +0.004 |
awoke | +0.004 |
reality | +0.003 |
sel | +0.003 |
Neg logit contributions | |
about | -0.005 |
automobiles | -0.004 |
hog | -0.004 |
Sharing | -0.004 |
ooters | -0.004 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
hog | +0.010 |
trucks | +0.009 |
about | +0.009 |
ranger | +0.009 |
automobiles | +0.009 |
Neg logit contributions | |
avail | -0.015 |
reality | -0.014 |
lor | -0.013 |
Elsa | -0.012 |
Beck | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
hog | +0.008 |
ranger | +0.007 |
trucks | +0.007 |
Sharing | +0.007 |
automobiles | +0.007 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.014 |
lor | -0.013 |
suitcase | -0.012 |
anything | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
hog | +0.024 |
about | +0.023 |
aring | +0.022 |
ranger | +0.021 |
uddy | +0.021 |
Neg logit contributions | |
avail | -0.034 |
reality | -0.029 |
lor | -0.026 |
Elsa | -0.026 |
anything | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
avail | +0.014 |
reality | +0.011 |
lor | +0.010 |
Beck | +0.010 |
Avery | +0.010 |
Neg logit contributions | |
hog | -0.015 |
about | -0.015 |
ranger | -0.014 |
aring | -0.014 |
trucks | -0.014 |
Token | knew |
Token ID | 2993 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
automobiles | +0.006 |
trucks | +0.005 |
ooters | +0.005 |
about | +0.005 |
aring | +0.005 |
Neg logit contributions | |
avail | -0.004 |
reality | -0.004 |
awoke | -0.004 |
lor | -0.004 |
Beck | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
about | +0.010 |
hog | +0.010 |
ranger | +0.009 |
Sharing | +0.009 |
aring | +0.009 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
lor | -0.009 |
Beck | -0.008 |
suitcase | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
about | +0.012 |
hog | +0.012 |
trucks | +0.011 |
ranger | +0.011 |
automobiles | +0.011 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.012 |
lor | -0.012 |
sel | -0.011 |
awoke | -0.011 |
Token | because |
Token ID | 780 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
hog | +0.026 |
about | +0.025 |
ranger | +0.024 |
Sharing | +0.022 |
aring | +0.022 |
Neg logit contributions | |
avail | -0.034 |
reality | -0.030 |
lor | -0.028 |
suitcase | -0.026 |
growth | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
hog | +0.019 |
about | +0.019 |
aring | +0.017 |
ranger | +0.017 |
Sharing | +0.017 |
Neg logit contributions | |
avail | -0.021 |
reality | -0.018 |
lor | -0.016 |
suitcase | -0.016 |
growth | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
about | +0.020 |
Sharing | +0.020 |
aring | +0.019 |
hog | +0.019 |
ranger | +0.019 |
Neg logit contributions | |
avail | -0.020 |
reality | -0.017 |
lor | -0.016 |
awoke | -0.016 |
suitcase | -0.016 |
Token | too |
Token ID | 1165 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
hog | +0.014 |
Sharing | +0.013 |
aring | +0.012 |
ranger | +0.012 |
uddy | +0.011 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.017 |
anything | -0.015 |
drift | -0.014 |
suitcase | -0.014 |
Token | high |
Token ID | 1029 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
hog | +0.007 |
about | +0.007 |
Sharing | +0.007 |
ranger | +0.006 |
elephant | +0.006 |
Neg logit contributions | |
avail | -0.010 |
reality | -0.009 |
ucer | -0.008 |
lor | -0.008 |
suitcase | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
about | +0.028 |
hog | +0.027 |
ranger | +0.025 |
Tim | +0.024 |
Sharing | +0.024 |
Neg logit contributions | |
avail | -0.044 |
lor | -0.038 |
reality | -0.038 |
sel | -0.035 |
suitcase | -0.035 |
Token | The |
Token ID | 383 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
about | +0.009 |
ranger | +0.008 |
hog | +0.008 |
aring | +0.008 |
elephant | +0.007 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
growth | -0.007 |
aire | -0.007 |
Beck | -0.007 |
Token | two |
Token ID | 734 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
avail | +0.012 |
lor | +0.011 |
reality | +0.011 |
suitcase | +0.010 |
sel | +0.010 |
Neg logit contributions | |
about | -0.008 |
hog | -0.008 |
Tim | -0.007 |
ranger | -0.007 |
Sharing | -0.007 |
Token | people |
Token ID | 661 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
avail | +0.078 |
reality | +0.068 |
lor | +0.067 |
suitcase | +0.062 |
sel | +0.062 |
Neg logit contributions | |
about | -0.054 |
hog | -0.050 |
ranger | -0.047 |
Sharing | -0.047 |
Tim | -0.046 |
Token | kept |
Token ID | 4030 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
Sharing | +0.004 |
ranger | +0.004 |
hog | +0.004 |
about | +0.003 |
disl | +0.003 |
Neg logit contributions | |
avail | -0.003 |
suitcase | -0.003 |
reality | -0.003 |
awoke | -0.003 |
sie | -0.003 |
Token | looking |
Token ID | 2045 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
hog | +0.009 |
about | +0.009 |
ranger | +0.008 |
Sharing | +0.008 |
aring | +0.008 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.007 |
suitcase | -0.007 |
arse | -0.007 |
drift | -0.007 |
Token | worried |
Token ID | 7960 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
hog | +0.013 |
Sharing | +0.012 |
aring | +0.012 |
uddy | +0.011 |
meanings | +0.011 |
Neg logit contributions | |
avail | -0.016 |
reality | -0.013 |
Beck | -0.013 |
awoken | -0.013 |
veil | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
hog | +0.010 |
ranger | +0.009 |
elephant | +0.009 |
sed | +0.009 |
uddy | +0.009 |
Neg logit contributions | |
avail | -0.009 |
reality | -0.008 |
anything | -0.008 |
iece | -0.007 |
drift | -0.007 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
hog | +0.018 |
about | +0.017 |
Sharing | +0.016 |
ranger | +0.016 |
Tim | +0.015 |
Neg logit contributions | |
avail | -0.027 |
reality | -0.023 |
suitcase | -0.022 |
drift | -0.022 |
lor | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
hog | +0.026 |
about | +0.025 |
ranger | +0.024 |
Tim | +0.023 |
Sharing | +0.022 |
Neg logit contributions | |
avail | -0.027 |
reality | -0.023 |
lor | -0.022 |
iece | -0.021 |
sel | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -6.43e-03 |
Pos logit contributions | |
avail | +0.030 |
lor | +0.027 |
reality | +0.026 |
Beck | +0.025 |
growth | +0.025 |
Neg logit contributions | |
about | -0.016 |
hog | -0.015 |
ranger | -0.013 |
aring | -0.012 |
elephant | -0.012 |
Token | sc |
Token ID | 629 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
about | +0.009 |
hog | +0.009 |
Sharing | +0.008 |
ranger | +0.008 |
aring | +0.008 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.011 |
lor | -0.011 |
suitcase | -0.011 |
sel | -0.010 |
Token | olded |
Token ID | 48959 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
about | +0.036 |
elephant | +0.033 |
hog | +0.033 |
Sharing | +0.033 |
old | +0.033 |
Neg logit contributions | |
lor | -0.044 |
ucer | -0.044 |
avail | -0.042 |
sel | -0.041 |
arse | -0.040 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.005 |
Sharing | +0.004 |
aring | +0.004 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.010 |
lor | -0.010 |
suitcase | -0.010 |
growth | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
hog | +0.009 |
ranger | +0.007 |
Sharing | +0.007 |
about | +0.007 |
Tim | +0.007 |
Neg logit contributions | |
lor | -0.014 |
avail | -0.014 |
reality | -0.014 |
suitcase | -0.014 |
sel | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
hog | +0.012 |
about | +0.011 |
Sharing | +0.010 |
aring | +0.010 |
ranger | +0.010 |
Neg logit contributions | |
avail | -0.019 |
reality | -0.017 |
Avery | -0.015 |
sel | -0.015 |
growth | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
avail | +0.012 |
reality | +0.011 |
suitcase | +0.011 |
lor | +0.011 |
ices | +0.010 |
Neg logit contributions | |
hog | -0.011 |
ranger | -0.010 |
Sharing | -0.010 |
about | -0.010 |
ller | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
avail | +0.016 |
reality | +0.014 |
suitcase | +0.013 |
sel | +0.013 |
lor | +0.013 |
Neg logit contributions | |
about | -0.015 |
hog | -0.014 |
Sharing | -0.014 |
ranger | -0.014 |
aring | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
avail | +0.014 |
reality | +0.013 |
lor | +0.012 |
suitcase | +0.011 |
sel | +0.011 |
Neg logit contributions | |
hog | -0.012 |
about | -0.011 |
ranger | -0.011 |
Sharing | -0.010 |
automobiles | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
hog | +0.016 |
about | +0.014 |
ranger | +0.013 |
automobiles | +0.013 |
trucks | +0.013 |
Neg logit contributions | |
avail | -0.025 |
reality | -0.024 |
Avery | -0.024 |
lor | -0.023 |
suitcase | -0.023 |
Token | Thank |
Token ID | 10449 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
about | +0.019 |
hog | +0.017 |
ranger | +0.016 |
Tim | +0.016 |
: | +0.016 |
Neg logit contributions | |
avail | -0.016 |
lor | -0.014 |
reality | -0.013 |
Beck | -0.012 |
growth | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
about | +0.008 |
hog | +0.007 |
ranger | +0.007 |
Tim | +0.007 |
Sharing | +0.006 |
Neg logit contributions | |
avail | -0.010 |
lor | -0.009 |
reality | -0.008 |
growth | -0.008 |
sel | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
about | +0.022 |
hog | +0.020 |
ranger | +0.019 |
Tim | +0.018 |
Sharing | +0.018 |
Neg logit contributions | |
avail | -0.045 |
lor | -0.041 |
reality | -0.041 |
suitcase | -0.037 |
sel | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
hog | +0.051 |
about | +0.050 |
ranger | +0.045 |
Sharing | +0.042 |
aring | +0.042 |
Neg logit contributions | |
avail | -0.063 |
reality | -0.056 |
lor | -0.054 |
growth | -0.049 |
Beck | -0.049 |
Token | juice |
Token ID | 13135 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
about | +0.011 |
hog | +0.010 |
Sharing | +0.010 |
Tim | +0.010 |
ranger | +0.010 |
Neg logit contributions | |
avail | -0.012 |
reality | -0.011 |
lor | -0.010 |
suitcase | -0.010 |
veil | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
about | +0.004 |
hog | +0.003 |
Sharing | +0.003 |
ranger | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.004 |
reality | -0.004 |
suitcase | -0.004 |
ucer | -0.004 |
Token | toast |
Token ID | 27805 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
hog | +0.021 |
about | +0.020 |
aring | +0.019 |
ike | +0.018 |
uddy | +0.018 |
Neg logit contributions | |
avail | -0.021 |
reality | -0.019 |
lor | -0.016 |
suitcase | -0.016 |
ucer | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.005 |
lor | -0.005 |
reality | -0.005 |
ucer | -0.004 |
suitcase | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
hog | +0.012 |
Sharing | +0.011 |
uddy | +0.011 |
ranger | +0.011 |
automobiles | +0.010 |
Neg logit contributions | |
avail | -0.014 |
reality | -0.013 |
lor | -0.012 |
ease | -0.012 |
valleys | -0.012 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
hog | +0.014 |
about | +0.014 |
uddy | +0.014 |
trucks | +0.014 |
automobiles | +0.014 |
Neg logit contributions | |
reality | -0.011 |
refreshed | -0.011 |
avail | -0.011 |
valleys | -0.011 |
drift | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
hog | +0.013 |
ranger | +0.012 |
Sharing | +0.012 |
driver | +0.011 |
owner | +0.011 |
Neg logit contributions | |
avail | -0.022 |
reality | -0.019 |
lor | -0.018 |
anything | -0.017 |
ices | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
about | +0.013 |
hog | +0.013 |
ranger | +0.012 |
aring | +0.012 |
owner | +0.011 |
Neg logit contributions | |
avail | -0.018 |
growth | -0.016 |
reality | -0.016 |
valleys | -0.015 |
Avery | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
Sharing | +0.004 |
aring | +0.004 |
ranger | +0.004 |
Neg logit contributions | |
avail | -0.005 |
reality | -0.004 |
sel | -0.004 |
awoke | -0.004 |
sie | -0.004 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
about | +0.025 |
hog | +0.024 |
ranger | +0.024 |
Sharing | +0.023 |
automobiles | +0.022 |
Neg logit contributions | |
avail | -0.030 |
reality | -0.028 |
awoke | -0.027 |
sel | -0.026 |
lor | -0.026 |
Token | swimming |
Token ID | 14899 |
Feature activation | -9.11e-04 |
Pos logit contributions | |
hog | +0.053 |
aring | +0.049 |
ranger | +0.047 |
Sharing | +0.047 |
driver | +0.047 |
Neg logit contributions | |
avail | -0.043 |
reality | -0.039 |
anything | -0.036 |
valleys | -0.033 |
outer | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -4.45e-03 |
Pos logit contributions | |
about | +0.001 |
Sharing | +0.001 |
hog | +0.001 |
aring | +0.001 |
ranger | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.002 |
valleys | -0.002 |
lor | -0.002 |
suitcase | -0.002 |
Token | drinking |
Token ID | 7722 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
about | +0.007 |
hog | +0.007 |
ranger | +0.006 |
aring | +0.006 |
owner | +0.006 |
Neg logit contributions | |
avail | -0.008 |
reality | -0.007 |
valleys | -0.007 |
ease | -0.006 |
drift | -0.006 |
Token | from |
Token ID | 422 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
avail | +0.010 |
reality | +0.009 |
lor | +0.008 |
suitcase | +0.008 |
growth | +0.008 |
Neg logit contributions | |
about | -0.010 |
hog | -0.010 |
ranger | -0.009 |
Sharing | -0.009 |
Tim | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
about | +0.019 |
hog | +0.018 |
ranger | +0.017 |
Tim | +0.016 |
Sharing | +0.016 |
Neg logit contributions | |
avail | -0.025 |
reality | -0.021 |
lor | -0.021 |
growth | -0.019 |
suitcase | -0.019 |
Token | One |
Token ID | 1881 |
Feature activation | -6.00e-05 |
Pos logit contributions | |
avail | +0.004 |
lor | +0.003 |
reality | +0.003 |
growth | +0.003 |
Beck | +0.003 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
aring | -0.002 |
trucks | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
about | +0.000 |
hog | +0.000 |
Sharing | +0.000 |
ranger | +0.000 |
aring | +0.000 |
Neg logit contributions | |
avail | -0.000 |
reality | -0.000 |
lor | -0.000 |
suitcase | -0.000 |
growth | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +8.70e-04 |
Pos logit contributions | |
avail | +0.044 |
lor | +0.040 |
reality | +0.039 |
ucer | +0.036 |
growth | +0.036 |
Neg logit contributions | |
about | -0.019 |
Tim | -0.016 |
hog | -0.016 |
ranger | -0.015 |
: | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +4.42e-05 |
Pos logit contributions | |
avail | +0.002 |
lor | +0.002 |
reality | +0.002 |
growth | +0.002 |
sel | +0.002 |
Neg logit contributions | |
about | -0.001 |
Tim | -0.001 |
hog | -0.001 |
ranger | -0.001 |
: | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
avail | +0.000 |
lor | +0.000 |
reality | +0.000 |
ucer | +0.000 |
growth | +0.000 |
Neg logit contributions | |
about | -0.000 |
Tim | -0.000 |
hog | -0.000 |
ranger | -0.000 |
: | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
about | +0.004 |
hog | +0.004 |
ranger | +0.003 |
Tim | +0.003 |
Sharing | +0.003 |
Neg logit contributions | |
avail | -0.009 |
lor | -0.008 |
reality | -0.008 |
growth | -0.008 |
suitcase | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
about | +0.044 |
Tim | +0.042 |
ranger | +0.035 |
Mark | +0.035 |
not | +0.034 |
Neg logit contributions | |
avail | -0.072 |
lor | -0.072 |
ucer | -0.067 |
reality | -0.065 |
sel | -0.064 |
Token | walk |
Token ID | 2513 |
Feature activation | -4.89e-03 |
Pos logit contributions | |
about | +0.040 |
hog | +0.038 |
Tim | +0.038 |
ranger | +0.037 |
: | +0.035 |
Neg logit contributions | |
avail | -0.035 |
lor | -0.030 |
reality | -0.028 |
growth | -0.026 |
sel | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
about | +0.005 |
hog | +0.005 |
ranger | +0.004 |
Tim | +0.004 |
Sharing | +0.004 |
Neg logit contributions | |
avail | -0.012 |
lor | -0.011 |
reality | -0.011 |
suitcase | -0.010 |
sel | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | +5.28e-04 |
Pos logit contributions | |
about | +0.006 |
Tim | +0.005 |
hog | +0.005 |
ranger | +0.005 |
: | +0.005 |
Neg logit contributions | |
avail | -0.008 |
lor | -0.007 |
reality | -0.007 |
sel | -0.006 |
growth | -0.006 |
Token | cane |
Token ID | 33009 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
avail | +0.001 |
reality | +0.001 |
lor | +0.001 |
suitcase | +0.001 |
veil | +0.001 |
Neg logit contributions | |
about | -0.001 |
Sharing | -0.001 |
hog | -0.001 |
aring | -0.001 |
ranger | -0.001 |
Token | Tom |
Token ID | 13787 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
avail | +0.011 |
lor | +0.010 |
reality | +0.010 |
Beck | +0.009 |
Elsa | +0.009 |
Neg logit contributions | |
about | -0.011 |
hog | -0.011 |
Tim | -0.010 |
ranger | -0.010 |
elephant | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
about | +0.011 |
Sharing | +0.011 |
automobiles | +0.010 |
ooters | +0.010 |
hog | +0.010 |
Neg logit contributions | |
lor | -0.012 |
awoke | -0.012 |
sel | -0.012 |
avail | -0.011 |
reality | -0.011 |
Token | Peter |
Token ID | 5613 |
Feature activation | -9.91e-04 |
Pos logit contributions | |
avail | +0.017 |
reality | +0.014 |
lor | +0.013 |
Beck | +0.013 |
growth | +0.012 |
Neg logit contributions | |
about | -0.015 |
hog | -0.014 |
ranger | -0.013 |
Sharing | -0.013 |
aring | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
about | +0.002 |
hog | +0.002 |
ranger | +0.002 |
Sharing | +0.002 |
Tim | +0.001 |
Neg logit contributions | |
avail | -0.002 |
reality | -0.001 |
lor | -0.001 |
sel | -0.001 |
awoke | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
hog | +0.005 |
Sharing | +0.005 |
ranger | +0.005 |
about | +0.005 |
aring | +0.005 |
Neg logit contributions | |
avail | -0.007 |
reality | -0.007 |
lor | -0.006 |
suitcase | -0.006 |
ease | -0.006 |
Token | impressed |
Token ID | 12617 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
about | +0.026 |
hog | +0.025 |
automobiles | +0.025 |
Sharing | +0.024 |
trucks | +0.023 |
Neg logit contributions | |
avail | -0.028 |
reality | -0.027 |
Beck | -0.023 |
sie | -0.023 |
sel | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
hog | +0.057 |
sed | +0.057 |
disl | +0.056 |
ooters | +0.056 |
uddy | +0.055 |
Neg logit contributions | |
avail | -0.053 |
cer | -0.045 |
reality | -0.044 |
lor | -0.043 |
over | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -6.28e-04 |
Pos logit contributions | |
hog | +0.026 |
ranger | +0.024 |
aring | +0.023 |
about | +0.023 |
o | +0.022 |
Neg logit contributions | |
avail | -0.030 |
reality | -0.027 |
growth | -0.024 |
suitcase | -0.023 |
ease | -0.023 |
Token | man |
Token ID | 582 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
about | +0.001 |
hog | +0.001 |
Sharing | +0.001 |
Tim | +0.001 |
: | +0.001 |
Neg logit contributions | |
avail | -0.001 |
reality | -0.001 |
suitcase | -0.001 |
lor | -0.001 |
sel | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
avail | +0.003 |
reality | +0.003 |
lor | +0.003 |
sel | +0.003 |
suitcase | +0.003 |
Neg logit contributions | |
about | -0.002 |
hog | -0.002 |
ranger | -0.002 |
Tim | -0.002 |
Sharing | -0.002 |
Token | good |
Token ID | 922 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
about | +0.012 |
hog | +0.012 |
Tim | +0.012 |
Sharing | +0.012 |
ranger | +0.011 |
Neg logit contributions | |
avail | -0.013 |
reality | -0.012 |
suitcase | -0.011 |
lor | -0.011 |
growth | -0.010 |