TOP ACTIVATIONS
MAX = 4.983

together . They played hop sc ot ch and picked more
love . They played hop sc ot ch , jumped rope
day , they play hop sc ot ch . They draw
She played tag and hop sc ot ch and pretended to
They started to play hop sc ot ch and had lots
. Barry enjoyed playing hop sc ot ch with them so
would play tag , hop sc ot ch , and many
and - seek and hop sc ot ch . Then ,
also played tag and hop sc ot ch . They laughed
play a game of hop sc ot ch , but it
group of girls playing hop sc ot ch . They joined
a big , pink elephant stuffed animal . He had never
hide and seek , hop sc ot ch and much more
a big , pink elephant stuffed animal . He had never
. You can play hop sc ot ch again . But
. He smiled as he stuffed them into his backpack .
pieces of chocolate . They stuffed them in their mouths and
shelves , old blankets and stuffed animals . She worked and
Inside were all kinds of stuffed animals , games , humor
know , right ? Micro sc opes are amazing . They

MIN ACTIVATIONS
MIN = -3.865

place of peace and content ment . One
stopped and froze in amaz ment , watching the bright colours
: " Measure ment complete . Height : 90
we might break the st alks ." L ily
looked through the ey ep iece . He saw the tiny
fingers and feel the smooth ness between his fingers and think
, and enjoyed the refresh ment of the cool lake water
run through the tall st alks . One day
slide and looked through the ey ep iece . He saw
rub the magical o int ment on her forehead . She
by singing with others and getting feedback . You can improve
you from losing out or getting into trouble . <|endoftext|> Once
flexible to hold onto the palm branches ." Tim
the hook and throw the line in the water .
rough it was with his palm . Tim
water and feel the cool ness . One day
oy sters and ended up getting sick from eating them .
to 10 out loud and getting ready to freeze .
sense of joy and content ment . After a few moments
clean up his toys before getting out of the tub .

INTERVAL 2.771 - 4.983
CONTAINS 0.011%

serve a picnic to their stuffed animals . They put some
water every day . He named it Buzz .
same clearing , though it hadn 't looked as hurt .
It was a big arc of many colors . It was
it out of blocks and stuffed animals , but it didn

INTERVAL 0.559 - 2.771
CONTAINS 17.593%

His mum said it was time to buy some salt .
, " OK , Mia . No more balancing on the
and Ab bie told everyone about her special exam . They
upon a time , there was a little girl named Jane
from the case . It was glad to be free from

INTERVAL -1.653 - 0.559
CONTAINS 81.903%

" Give it to me , Tom . It
Who is there ?" a voice said . Tom
throw the ball and Rex catches it . They have fun
and apologize when we make mistakes . <|endoftext|> Once upon a
it ." So , Tim decided to help his neighbors .

INTERVAL -3.865 - -1.653
CONTAINS 0.493%

good at balancing on the board . How does he do
Be careful not to hurt yourself again ," said the nurse
his friends about how the big , strong rabbit helped him
and the w affle was feeling very cold . It wanted
ily and Tom held the old man 's hands and led
Token together
Token ID1978
Feature activation+3.31e-01

Pos logit contributions
 Spot+0.004
girls+0.004
 Zip+0.004
 Buddy+0.004
 Max+0.004
Neg logit contributions
 canvas-0.011
line-0.011
 tide-0.011
 pulp-0.011
 product-0.011
Token.
Token ID13
Feature activation-3.81e-01

Pos logit contributions
 Spot+0.011
girls+0.010
 Buddy+0.010
 Zip+0.010
 Wh+0.010
Neg logit contributions
 canvas-0.012
line-0.011
 product-0.011
 tide-0.011
lee-0.011
Token They
Token ID1119
Feature activation-4.99e-01

Pos logit contributions
lee+0.015
 canvas+0.015
line+0.015
 harbor+0.015
 product+0.014
Neg logit contributions
girls-0.010
oof-0.010
uddy-0.009
 Zip-0.009
ver-0.009
Token played
Token ID2826
Feature activation+1.39e+00

Pos logit contributions
 harbor+0.017
 canvas+0.017
lee+0.017
line+0.016
 shell+0.016
Neg logit contributions
uddy-0.016
oof-0.016
girls-0.015
 Zip-0.015
 Johnson-0.015
Token hop
Token ID1725
Feature activation+8.07e-01

Pos logit contributions
 Johnson+0.042
uddy+0.041
 Understand+0.038
girls+0.037
oof+0.036
Neg logit contributions
 harbor-0.049
 shell-0.047
line-0.047
 tide-0.047
 canvas-0.046
Tokensc
Token ID1416
Feature activation+4.98e+00

Pos logit contributions
 Okay+0.030
 OK+0.029
 Understand+0.028
 Deal+0.028
 Johnson+0.028
Neg logit contributions
 harbor-0.024
 shell-0.023
line-0.023
 cliff-0.022
 tide-0.021
Tokenot
Token ID313
Feature activation-8.27e-01

Pos logit contributions
 Spot+0.224
girls+0.219
 Buddy+0.217
 Zip+0.216
 Max+0.213
Neg logit contributions
 canvas-0.111
line-0.107
 product-0.106
 tide-0.103
lee-0.097
Tokench
Token ID354
Feature activation+2.42e+00

Pos logit contributions
 canvas+0.035
line+0.034
 product+0.033
 tide+0.033
lee+0.033
Neg logit contributions
girls-0.019
 Spot-0.019
 Johnson-0.019
 Buddy-0.018
 Monkey-0.017
Token and
Token ID290
Feature activation+6.28e-01

Pos logit contributions
girls+0.066
 Spot+0.066
 Johnson+0.065
 Monkey+0.065
 Buddy+0.062
Neg logit contributions
line-0.089
 canvas-0.088
 product-0.086
 tide-0.085
lee-0.084
Token picked
Token ID6497
Feature activation-5.53e-01

Pos logit contributions
 Deal+0.023
oof+0.023
 Understand+0.023
 OK+0.022
ver+0.022
Neg logit contributions
line-0.018
 canvas-0.018
 harbor-0.017
 shell-0.017
 tide-0.016
Token more
Token ID517
Feature activation-1.06e-01

Pos logit contributions
 canvas+0.018
 tide+0.018
lee+0.018
 shell+0.017
 product+0.017
Neg logit contributions
uddy-0.018
girls-0.018
 Spot-0.017
 Buddy-0.017
 Johnson-0.017
Token love
Token ID1842
Feature activation+4.85e-01

Pos logit contributions
uddy+0.027
girls+0.025
ver+0.025
oof+0.025
isk+0.025
Neg logit contributions
 tide-0.021
 canvas-0.021
 harbor-0.020
 shell-0.020
line-0.020
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
girls+0.014
uddy+0.014
oof+0.014
 Zip+0.014
 Monkey+0.014
Neg logit contributions
 canvas-0.018
line-0.018
 product-0.018
 tide-0.017
 shell-0.017
Token They
Token ID1119
Feature activation-6.59e-01

Pos logit contributions
line+0.013
 canvas+0.013
lee+0.012
 tide+0.012
 product+0.012
Neg logit contributions
girls-0.009
 Spot-0.009
oof-0.008
 Zip-0.008
uddy-0.008
Token played
Token ID2826
Feature activation+1.19e+00

Pos logit contributions
line+0.021
 harbor+0.021
 canvas+0.021
lee+0.020
 tide+0.020
Neg logit contributions
oof-0.023
girls-0.022
uddy-0.022
 Zip-0.022
 Buddy-0.022
Token hop
Token ID1725
Feature activation+5.77e-01

Pos logit contributions
uddy+0.040
 Johnson+0.038
girls+0.037
 Monkey+0.036
oof+0.036
Neg logit contributions
line-0.041
 tide-0.041
 harbor-0.040
 canvas-0.038
 shell-0.037
Tokensc
Token ID1416
Feature activation+4.69e+00

Pos logit contributions
 Okay+0.020
oof+0.020
girls+0.020
 Understand+0.019
 Johnson+0.019
Neg logit contributions
line-0.018
 harbor-0.018
 tide-0.017
 cliff-0.017
 shell-0.017
Tokenot
Token ID313
Feature activation-1.29e+00

Pos logit contributions
 Spot+0.224
girls+0.224
 Buddy+0.218
 Zip+0.218
 Monkey+0.218
Neg logit contributions
 canvas-0.088
 product-0.084
line-0.083
lee-0.078
 tide-0.077
Tokench
Token ID354
Feature activation+2.08e+00

Pos logit contributions
line+0.053
 canvas+0.052
 product+0.051
 tide+0.050
lee+0.050
Neg logit contributions
 Johnson-0.031
girls-0.030
 Spot-0.029
Deal-0.029
 Kitty-0.029
Token,
Token ID11
Feature activation+2.76e-01

Pos logit contributions
 Johnson+0.061
 Monkey+0.060
girls+0.060
 Spot+0.059
Deal+0.057
Neg logit contributions
line-0.075
 canvas-0.071
 tide-0.070
 product-0.070
lee-0.068
Token jumped
Token ID11687
Feature activation-3.13e-01

Pos logit contributions
oof+0.009
girls+0.008
uddy+0.008
 Johnson+0.008
Deal+0.008
Neg logit contributions
line-0.010
 canvas-0.010
 tide-0.010
 harbor-0.009
 shell-0.009
Token rope
Token ID17182
Feature activation+7.22e-01

Pos logit contributions
 tide+0.012
line+0.011
 canvas+0.011
 harbor+0.011
 shell+0.011
Neg logit contributions
girls-0.009
oof-0.009
Deal-0.009
uddy-0.009
 Monkey-0.009
Token day
Token ID1110
Feature activation-3.76e-01

Pos logit contributions
 Spot+0.010
 Buddy+0.009
 Zip+0.009
girls+0.009
 Max+0.009
Neg logit contributions
 canvas-0.018
line-0.018
 product-0.018
 tide-0.018
lee-0.018
Token,
Token ID11
Feature activation-6.32e-01

Pos logit contributions
 canvas+0.016
line+0.016
 product+0.016
 tide+0.015
lee+0.015
Neg logit contributions
 Spot-0.009
girls-0.009
 Buddy-0.009
 Zip-0.009
 Wh-0.008
Token they
Token ID484
Feature activation-6.16e-01

Pos logit contributions
 tide+0.024
 canvas+0.023
line+0.023
 product+0.022
 pumpkin+0.021
Neg logit contributions
girls-0.020
isk-0.018
 Monkey-0.018
uddy-0.018
oof-0.018
Token play
Token ID711
Feature activation+5.65e-01

Pos logit contributions
 product+0.024
 canvas+0.023
line+0.023
lee+0.022
 tide+0.022
Neg logit contributions
 Spot-0.018
 Max-0.017
girls-0.017
 Buddy-0.017
 Zip-0.016
Token hop
Token ID1725
Feature activation+1.04e-02

Pos logit contributions
girls+0.017
 Johnson+0.017
uddy+0.016
 Kitty+0.016
oof+0.015
Neg logit contributions
 canvas-0.021
 tide-0.021
 harbor-0.020
 product-0.020
 shell-0.020
Tokensc
Token ID1416
Feature activation+4.66e+00

Pos logit contributions
 Johnson+0.000
girls+0.000
oof+0.000
 Kitty+0.000
uddy+0.000
Neg logit contributions
 tide-0.000
line-0.000
 harbor-0.000
 shell-0.000
 canvas-0.000
Tokenot
Token ID313
Feature activation-1.49e+00

Pos logit contributions
 Spot+0.204
girls+0.198
 Buddy+0.197
 Zip+0.196
 Max+0.193
Neg logit contributions
 canvas-0.111
line-0.107
 product-0.106
 tide-0.103
lee-0.097
Tokench
Token ID354
Feature activation+1.87e+00

Pos logit contributions
 canvas+0.059
line+0.059
 product+0.058
 tide+0.057
lee+0.055
Neg logit contributions
 Johnson-0.036
girls-0.036
 Spot-0.035
 Kitty-0.034
oof-0.034
Token.
Token ID13
Feature activation-8.05e-02

Pos logit contributions
girls+0.054
 Spot+0.054
 Johnson+0.052
 Monkey+0.052
 Buddy+0.051
Neg logit contributions
line-0.068
 canvas-0.066
 product-0.066
 tide-0.065
lee-0.062
Token They
Token ID1119
Feature activation-4.71e-01

Pos logit contributions
 canvas+0.004
line+0.003
 tide+0.003
 product+0.003
lee+0.003
Neg logit contributions
girls-0.002
 Buddy-0.002
 Spot-0.002
 Monkey-0.002
uddy-0.002
Token draw
Token ID3197
Feature activation-2.05e-01

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.017
 tide+0.017
 harbor+0.017
Neg logit contributions
 Spot-0.014
girls-0.013
 Buddy-0.013
 Zip-0.013
uddy-0.013
Token She
Token ID1375
Feature activation-4.62e-01

Pos logit contributions
 canvas+0.006
 product+0.005
line+0.005
 tide+0.005
lee+0.005
Neg logit contributions
 Spot-0.003
girls-0.003
 Buddy-0.003
 Zip-0.003
 Fl-0.003
Token played
Token ID2826
Feature activation+1.28e+00

Pos logit contributions
 canvas+0.015
lee+0.014
line+0.014
 shell+0.014
 tide+0.014
Neg logit contributions
girls-0.016
 Zip-0.016
uddy-0.015
oof-0.015
 Spot-0.015
Token tag
Token ID7621
Feature activation+2.26e+00

Pos logit contributions
uddy+0.040
 Johnson+0.039
girls+0.038
oof+0.037
 Monkey+0.035
Neg logit contributions
line-0.047
 tide-0.046
 canvas-0.045
 harbor-0.044
 product-0.044
Token and
Token ID290
Feature activation+5.92e-01

Pos logit contributions
 Okay+0.083
oof+0.082
girls+0.082
 Deal+0.081
 Understand+0.081
Neg logit contributions
line-0.065
 shell-0.064
 canvas-0.063
 product-0.061
 harbor-0.061
Token hop
Token ID1725
Feature activation+4.78e-01

Pos logit contributions
uddy+0.021
 Understand+0.021
ver+0.021
 Deal+0.021
oof+0.021
Neg logit contributions
 shell-0.017
line-0.017
 canvas-0.016
 tide-0.016
 shells-0.015
Tokensc
Token ID1416
Feature activation+4.61e+00

Pos logit contributions
oof+0.019
 Okay+0.019
girls+0.018
 Understand+0.018
 Johnson+0.018
Neg logit contributions
line-0.013
 harbor-0.011
 tide-0.011
 shell-0.011
 canvas-0.011
Tokenot
Token ID313
Feature activation-8.61e-01

Pos logit contributions
 Spot+0.209
girls+0.206
 Buddy+0.203
 Zip+0.202
 Max+0.198
Neg logit contributions
 canvas-0.101
line-0.096
 product-0.096
 tide-0.092
lee-0.088
Tokench
Token ID354
Feature activation+2.21e+00

Pos logit contributions
line+0.030
 canvas+0.030
lee+0.029
 tide+0.028
 product+0.027
Neg logit contributions
 Johnson-0.025
Deal-0.024
girls-0.024
oof-0.023
 Monkey-0.023
Token and
Token ID290
Feature activation+4.15e-01

Pos logit contributions
 Enjoy+0.065
 Monkey+0.065
 Johnson+0.065
girls+0.063
Deal+0.062
Neg logit contributions
line-0.078
 canvas-0.072
lee-0.072
 tide-0.070
 product-0.069
Token pretended
Token ID36766
Feature activation+1.28e+00

Pos logit contributions
oof+0.015
uddy+0.014
ver+0.014
 Understand+0.014
girls+0.014
Neg logit contributions
line-0.013
 canvas-0.012
 tide-0.012
 shell-0.012
 harbor-0.011
Token to
Token ID284
Feature activation-1.81e-01

Pos logit contributions
girls+0.043
oof+0.042
uddy+0.040
 Spot+0.039
 Buddy+0.039
Neg logit contributions
 canvas-0.042
line-0.042
 product-0.041
 tide-0.040
lee-0.039
Token They
Token ID1119
Feature activation-8.01e-01

Pos logit contributions
 canvas+0.005
line+0.005
lee+0.005
 product+0.004
 tide+0.004
Neg logit contributions
girls-0.003
 Zip-0.003
 Spot-0.003
oof-0.003
 Buddy-0.003
Token started
Token ID2067
Feature activation-7.08e-01

Pos logit contributions
 canvas+0.030
line+0.029
 product+0.028
 tide+0.028
lee+0.028
Neg logit contributions
 Spot-0.024
girls-0.024
 Zip-0.023
 Buddy-0.023
oof-0.023
Token to
Token ID284
Feature activation-6.72e-01

Pos logit contributions
 canvas+0.034
line+0.033
 product+0.033
 tide+0.033
lee+0.032
Neg logit contributions
 Spot-0.014
girls-0.013
 Buddy-0.013
 Zip-0.013
 Max-0.012
Token play
Token ID711
Feature activation+7.48e-01

Pos logit contributions
 canvas+0.023
line+0.020
 tide+0.020
 product+0.020
 harbor+0.020
Neg logit contributions
uddy-0.023
oof-0.022
 Spot-0.022
girls-0.022
 Zip-0.021
Token hop
Token ID1725
Feature activation+1.09e-01

Pos logit contributions
uddy+0.021
 Johnson+0.020
oof+0.020
girls+0.020
 Monkey+0.019
Neg logit contributions
 canvas-0.029
line-0.029
 tide-0.028
 harbor-0.028
 product-0.028
Tokensc
Token ID1416
Feature activation+4.47e+00

Pos logit contributions
oof+0.004
 Johnson+0.004
 Enjoy+0.004
girls+0.004
 Okay+0.004
Neg logit contributions
line-0.003
 harbor-0.003
 tide-0.003
 cliff-0.003
 shell-0.003
Tokenot
Token ID313
Feature activation-1.37e+00

Pos logit contributions
 Spot+0.201
girls+0.197
 Buddy+0.195
 Zip+0.194
 Max+0.191
Neg logit contributions
 canvas-0.099
line-0.095
 product-0.095
 tide-0.091
lee-0.087
Tokench
Token ID354
Feature activation+1.73e+00

Pos logit contributions
 canvas+0.056
line+0.055
 product+0.054
 tide+0.054
lee+0.052
Neg logit contributions
 Johnson-0.032
girls-0.032
 Spot-0.031
oof-0.030
 Monkey-0.030
Token and
Token ID290
Feature activation-7.43e-02

Pos logit contributions
girls+0.049
 Spot+0.049
 Monkey+0.049
 Johnson+0.048
 Enjoy+0.047
Neg logit contributions
line-0.063
 canvas-0.061
 product-0.059
 tide-0.059
lee-0.057
Token had
Token ID550
Feature activation-1.28e+00

Pos logit contributions
line+0.002
 canvas+0.002
 tide+0.002
 shell+0.002
 harbor+0.002
Neg logit contributions
oof-0.003
uddy-0.003
Deal-0.003
 Johnson-0.003
 Understand-0.002
Token lots
Token ID6041
Feature activation+3.51e-01

Pos logit contributions
 canvas+0.047
 tide+0.046
lee+0.045
 product+0.045
 harbor+0.045
Neg logit contributions
uddy-0.036
girls-0.036
oof-0.034
 Monkey-0.034
 Johnson-0.033
Token.
Token ID13
Feature activation+3.88e-02

Pos logit contributions
line+0.062
 canvas+0.060
 product+0.058
 harbor+0.056
lee+0.055
Neg logit contributions
oof-0.053
 Zip-0.052
 Spot-0.052
 Wh-0.051
girls-0.051
Token Barry
Token ID14488
Feature activation+7.63e-01

Pos logit contributions
girls+0.001
oof+0.001
 losers+0.001
Deal+0.001
isk+0.001
Neg logit contributions
lee-0.001
 harbor-0.001
line-0.001
 canvas-0.001
 pumpkin-0.001
Token enjoyed
Token ID8359
Feature activation+2.75e-01

Pos logit contributions
oof+0.024
 Spot+0.024
 Enjoy+0.024
 Zip+0.024
girls+0.024
Neg logit contributions
lee-0.026
line-0.023
 shell-0.023
 product-0.023
 harbor-0.023
Token playing
Token ID2712
Feature activation+1.01e+00

Pos logit contributions
uddy+0.010
girls+0.009
oof+0.009
ver+0.009
Deal+0.008
Neg logit contributions
line-0.009
 product-0.009
 tide-0.009
lee-0.009
 canvas-0.009
Token hop
Token ID1725
Feature activation+3.57e-01

Pos logit contributions
uddy+0.035
 Johnson+0.033
girls+0.032
oof+0.032
ver+0.031
Neg logit contributions
line-0.033
 tide-0.033
 canvas-0.033
 harbor-0.032
 product-0.032
Tokensc
Token ID1416
Feature activation+4.42e+00

Pos logit contributions
 Okay+0.012
 Johnson+0.012
girls+0.012
oof+0.012
 OK+0.012
Neg logit contributions
line-0.012
 harbor-0.011
 tide-0.011
 shell-0.011
 canvas-0.010
Tokenot
Token ID313
Feature activation-1.53e+00

Pos logit contributions
girls+0.209
 Spot+0.208
 Buddy+0.203
 Zip+0.202
 Monkey+0.202
Neg logit contributions
 canvas-0.085
line-0.083
 product-0.083
lee-0.078
 tide-0.075
Tokench
Token ID354
Feature activation+1.72e+00

Pos logit contributions
line+0.058
 canvas+0.057
 product+0.055
lee+0.055
 tide+0.054
Neg logit contributions
 Johnson-0.041
girls-0.040
Deal-0.039
 Kitty-0.038
 Spot-0.038
Token with
Token ID351
Feature activation+4.36e-01

Pos logit contributions
 Johnson+0.054
 Monkey+0.051
girls+0.050
 Enjoy+0.050
 Spot+0.050
Neg logit contributions
line-0.061
 tide-0.055
 canvas-0.055
 product-0.055
lee-0.054
Token them
Token ID606
Feature activation-3.53e-01

Pos logit contributions
Deal+0.016
ver+0.016
uddy+0.015
oof+0.015
ll+0.015
Neg logit contributions
lee-0.014
 tide-0.014
 shell-0.014
 shells-0.013
 harbor-0.013
Token so
Token ID523
Feature activation-3.89e-01

Pos logit contributions
line+0.011
 shell+0.010
 canvas+0.010
 harbor+0.010
 tide+0.009
Neg logit contributions
oof-0.013
 Enjoy-0.012
Deal-0.012
 Understand-0.012
 Johnson-0.012
Token would
Token ID561
Feature activation+7.32e-01

Pos logit contributions
 canvas+0.010
 product+0.009
 tide+0.009
line+0.009
 harbor+0.009
Neg logit contributions
girls-0.008
 Zip-0.007
 Spot-0.007
oof-0.007
 Buddy-0.007
Token play
Token ID711
Feature activation+9.61e-01

Pos logit contributions
girls+0.023
 Spot+0.023
 Buddy+0.022
uddy+0.022
 Zip+0.022
Neg logit contributions
 canvas-0.027
line-0.026
 product-0.025
 tide-0.025
 harbor-0.025
Token tag
Token ID7621
Feature activation+1.75e+00

Pos logit contributions
girls+0.033
uddy+0.032
 Johnson+0.032
 Kitty+0.029
oof+0.029
Neg logit contributions
 canvas-0.032
line-0.032
 product-0.031
 tide-0.031
 harbor-0.030
Token,
Token ID11
Feature activation+5.78e-01

Pos logit contributions
 Okay+0.067
 Johnson+0.067
girls+0.066
uddy+0.066
 Deal+0.065
Neg logit contributions
line-0.049
 tide-0.046
 shell-0.045
 canvas-0.045
 product-0.044
Token hop
Token ID1725
Feature activation+1.46e-01

Pos logit contributions
uddy+0.021
oof+0.021
girls+0.021
ver+0.021
 Johnson+0.020
Neg logit contributions
 canvas-0.018
line-0.018
 tide-0.017
 shell-0.016
 harbor-0.016
Tokensc
Token ID1416
Feature activation+4.35e+00

Pos logit contributions
 Johnson+0.005
 Okay+0.005
 OK+0.005
oof+0.005
girls+0.005
Neg logit contributions
line-0.004
 harbor-0.004
 tide-0.004
 shell-0.004
 canvas-0.004
Tokenot
Token ID313
Feature activation-1.48e+00

Pos logit contributions
 Spot+0.191
girls+0.186
 Buddy+0.185
 Zip+0.184
 Max+0.181
Neg logit contributions
 canvas-0.102
line-0.098
 product-0.097
 tide-0.095
lee-0.089
Tokench
Token ID354
Feature activation+1.71e+00

Pos logit contributions
 canvas+0.061
line+0.060
 product+0.058
 tide+0.057
lee+0.057
Neg logit contributions
 Johnson-0.035
girls-0.035
 Spot-0.034
Deal-0.033
 Zip-0.033
Token,
Token ID11
Feature activation+2.58e-01

Pos logit contributions
girls+0.044
 Johnson+0.043
 Spot+0.042
 Monkey+0.042
 Buddy+0.040
Neg logit contributions
line-0.067
 canvas-0.066
 product-0.064
 tide-0.064
lee-0.062
Token and
Token ID290
Feature activation+2.69e-01

Pos logit contributions
girls+0.007
oof+0.007
uddy+0.007
 Spot+0.007
 Buddy+0.006
Neg logit contributions
line-0.011
 canvas-0.011
 tide-0.010
 product-0.010
 shell-0.010
Token many
Token ID867
Feature activation-3.23e-01

Pos logit contributions
oof+0.010
uddy+0.009
girls+0.009
 Johnson+0.009
Deal+0.009
Neg logit contributions
 canvas-0.009
line-0.009
 tide-0.008
 shell-0.008
 product-0.008
Tokenand
Token ID392
Feature activation+2.48e+00

Pos logit contributions
 Spot+0.036
girls+0.035
 Buddy+0.034
 Zip+0.033
 Max+0.033
Neg logit contributions
 canvas-0.052
line-0.052
 product-0.050
 tide-0.049
lee-0.048
Token-
Token ID12
Feature activation+2.26e+00

Pos logit contributions
 Spot+0.073
 Buddy+0.071
girls+0.069
 Zip+0.069
 Fl+0.068
Neg logit contributions
 canvas-0.096
 tide-0.093
line-0.093
 product-0.093
 harbor-0.089
Tokenseek
Token ID36163
Feature activation+9.96e-01

Pos logit contributions
 Spot+0.067
girls+0.065
 Buddy+0.064
 Max+0.064
 Monkey+0.063
Neg logit contributions
line-0.085
 canvas-0.081
 product-0.077
lee-0.074
 tide-0.072
Token and
Token ID290
Feature activation+1.34e-01

Pos logit contributions
girls+0.037
oof+0.037
uddy+0.037
 Monkey+0.036
 Johnson+0.035
Neg logit contributions
line-0.027
 canvas-0.027
 tide-0.026
 harbor-0.026
 product-0.025
Token hop
Token ID1725
Feature activation+7.84e-02

Pos logit contributions
ver+0.005
 Deal+0.005
oof+0.005
uddy+0.005
 Understand+0.005
Neg logit contributions
 shell-0.004
line-0.003
 canvas-0.003
 harbor-0.003
 tide-0.003
Tokensc
Token ID1416
Feature activation+4.33e+00

Pos logit contributions
 Johnson+0.003
 Okay+0.003
 Deal+0.003
oof+0.003
 Understand+0.003
Neg logit contributions
line-0.002
 harbor-0.002
 shell-0.002
 tide-0.002
 cliff-0.002
Tokenot
Token ID313
Feature activation-1.06e+00

Pos logit contributions
 Spot+0.190
girls+0.186
 Buddy+0.184
 Zip+0.183
 Max+0.180
Neg logit contributions
 canvas-0.101
line-0.098
 product-0.097
 tide-0.094
lee-0.089
Tokench
Token ID354
Feature activation+1.76e+00

Pos logit contributions
 canvas+0.036
line+0.035
lee+0.035
 product+0.034
 tide+0.033
Neg logit contributions
 Johnson-0.031
girls-0.029
Deal-0.029
oof-0.029
 Spot-0.028
Token.
Token ID13
Feature activation-2.45e-02

Pos logit contributions
 Monkey+0.053
 Johnson+0.053
 Enjoy+0.052
girls+0.052
 Spot+0.052
Neg logit contributions
line-0.060
 canvas-0.058
lee-0.056
 product-0.056
 tide-0.055
Token Then
Token ID3244
Feature activation-9.68e-03

Pos logit contributions
lee+0.001
 harbor+0.001
 canvas+0.001
line+0.001
 product+0.001
Neg logit contributions
girls-0.001
oof-0.001
ver-0.001
 ever-0.001
Deal-0.001
Token,
Token ID11
Feature activation-4.13e-01

Pos logit contributions
 canvas+0.000
 product+0.000
line+0.000
 tide+0.000
 harbor+0.000
Neg logit contributions
girls-0.000
oof-0.000
uddy-0.000
 Spot-0.000
 Zip-0.000
Token also
Token ID635
Feature activation+4.66e-02

Pos logit contributions
 Spot+0.000
girls+0.000
 Buddy+0.000
 Zip+0.000
 Max+0.000
Neg logit contributions
 canvas-0.000
line-0.000
 product-0.000
 tide-0.000
lee-0.000
Token played
Token ID2826
Feature activation+6.19e-01

Pos logit contributions
 Spot+0.001
girls+0.001
 Buddy+0.001
 Zip+0.001
 Max+0.001
Neg logit contributions
 canvas-0.002
line-0.002
 product-0.002
 tide-0.002
lee-0.002
Token tag
Token ID7621
Feature activation+1.63e+00

Pos logit contributions
uddy+0.018
 Johnson+0.017
girls+0.017
 Spot+0.017
oof+0.016
Neg logit contributions
 canvas-0.024
 tide-0.024
 harbor-0.023
 shell-0.023
 product-0.023
Token and
Token ID290
Feature activation-1.53e-01

Pos logit contributions
 Understand+0.055
oof+0.055
 Deal+0.054
 Okay+0.053
 OK+0.053
Neg logit contributions
 canvas-0.054
 shell-0.054
 harbor-0.054
line-0.053
 pumpkin-0.052
Token hop
Token ID1725
Feature activation+1.28e-02

Pos logit contributions
 canvas+0.005
 shell+0.004
lee+0.004
 pumpkin+0.004
 pulp+0.004
Neg logit contributions
 Understand-0.006
ver-0.006
 Deal-0.006
uddy-0.005
 If-0.005
Tokensc
Token ID1416
Feature activation+4.24e+00

Pos logit contributions
oof+0.000
 Understand+0.000
 Johnson+0.000
 Okay+0.000
 OK+0.000
Neg logit contributions
line-0.000
 harbor-0.000
 tide-0.000
 shell-0.000
 canvas-0.000
Tokenot
Token ID313
Feature activation-1.48e+00

Pos logit contributions
 Spot+0.195
girls+0.193
 Buddy+0.189
 Zip+0.188
 Monkey+0.186
Neg logit contributions
 canvas-0.090
 product-0.086
line-0.085
lee-0.081
 tide-0.080
Tokench
Token ID354
Feature activation+1.74e+00

Pos logit contributions
 canvas+0.058
line+0.056
lee+0.055
 product+0.055
 tide+0.054
Neg logit contributions
 Johnson-0.038
girls-0.037
 Spot-0.037
Deal-0.036
oof-0.036
Token.
Token ID13
Feature activation-4.59e-01

Pos logit contributions
 Spot+0.050
 Monkey+0.049
girls+0.049
 Johnson+0.048
 Enjoy+0.047
Neg logit contributions
line-0.063
 canvas-0.063
 product-0.061
lee-0.060
 tide-0.060
Token They
Token ID1119
Feature activation-3.20e-01

Pos logit contributions
lee+0.017
 canvas+0.017
line+0.017
 tide+0.016
 harbor+0.016
Neg logit contributions
girls-0.012
Deal-0.012
 losers-0.012
oof-0.012
 ever-0.012
Token laughed
Token ID13818
Feature activation+3.08e-01

Pos logit contributions
 canvas+0.011
line+0.010
 shell+0.010
 harbor+0.010
lee+0.010
Neg logit contributions
oof-0.011
uddy-0.010
girls-0.010
 Johnson-0.010
 Spot-0.010
Token play
Token ID711
Feature activation+9.12e-01

Pos logit contributions
 canvas+0.007
line+0.007
 tide+0.007
 product+0.007
 harbor+0.006
Neg logit contributions
girls-0.007
 Spot-0.007
 Zip-0.006
 Buddy-0.006
uddy-0.006
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
girls+0.024
 Spot+0.024
uddy+0.023
 Zip+0.023
 Buddy+0.022
Neg logit contributions
 canvas-0.037
line-0.036
 product-0.036
 tide-0.036
 harbor-0.034
Token game
Token ID983
Feature activation+6.26e-01

Pos logit contributions
 Spot+0.027
girls+0.026
 Buddy+0.026
 Zip+0.025
 Fl+0.025
Neg logit contributions
 canvas-0.045
line-0.044
 product-0.044
 tide-0.043
lee-0.042
Token of
Token ID286
Feature activation+1.28e+00

Pos logit contributions
girls+0.017
 Spot+0.017
 Buddy+0.016
 Zip+0.016
oof+0.015
Neg logit contributions
 canvas-0.025
line-0.025
 product-0.024
 tide-0.024
 harbor-0.023
Token hop
Token ID1725
Feature activation-1.67e-01

Pos logit contributions
uddy+0.035
 Johnson+0.031
ver+0.031
girls+0.031
oof+0.030
Neg logit contributions
 canvas-0.053
 tide-0.053
 shell-0.050
 cliff-0.050
line-0.050
Tokensc
Token ID1416
Feature activation+4.24e+00

Pos logit contributions
line+0.006
 tide+0.006
 harbor+0.005
 shell+0.005
 canvas+0.005
Neg logit contributions
girls-0.005
 Johnson-0.005
oof-0.005
uddy-0.005
 Monkey-0.005
Tokenot
Token ID313
Feature activation-1.98e+00

Pos logit contributions
 Spot+0.178
 Buddy+0.173
oof+0.172
 Zip+0.170
 Fl+0.169
Neg logit contributions
 canvas-0.109
line-0.105
 product-0.104
 tide-0.103
 harbor-0.097
Tokench
Token ID354
Feature activation+1.43e+00

Pos logit contributions
 canvas+0.090
line+0.089
 product+0.088
 tide+0.087
lee+0.085
Neg logit contributions
 Spot-0.040
girls-0.040
 Buddy-0.038
 Zip-0.037
 Johnson-0.037
Token,
Token ID11
Feature activation+6.22e-03

Pos logit contributions
 Spot+0.038
girls+0.037
 Buddy+0.036
 Zip+0.036
 Monkey+0.035
Neg logit contributions
 canvas-0.056
line-0.056
 product-0.055
 tide-0.055
lee-0.053
Token but
Token ID475
Feature activation-7.54e-01

Pos logit contributions
girls+0.000
oof+0.000
uddy+0.000
 Spot+0.000
 Zip+0.000
Neg logit contributions
line-0.000
 canvas-0.000
 tide-0.000
 harbor-0.000
 shell-0.000
Token it
Token ID340
Feature activation+8.51e-01

Pos logit contributions
 canvas+0.018
line+0.018
 shell+0.017
 tide+0.016
 harbor+0.016
Neg logit contributions
girls-0.035
uddy-0.033
oof-0.033
 Enjoy-0.032
 Hero-0.030
Token group
Token ID1448
Feature activation-1.05e+00

Pos logit contributions
girls+0.017
oof+0.016
 Zip+0.015
uddy+0.015
 Spot+0.015
Neg logit contributions
 canvas-0.013
 product-0.012
 shell-0.012
 tide-0.012
 harbor-0.012
Token of
Token ID286
Feature activation+2.06e+00

Pos logit contributions
 canvas+0.047
line+0.046
 product+0.045
 tide+0.045
lee+0.044
Neg logit contributions
 Spot-0.024
girls-0.023
 Buddy-0.023
 Zip-0.023
 Max-0.022
Token girls
Token ID4813
Feature activation-8.15e-01

Pos logit contributions
uddy+0.083
ver+0.077
oof+0.077
isk+0.077
 Johnson+0.077
Neg logit contributions
 tide-0.059
 canvas-0.058
 harbor-0.056
 shell-0.054
 waves-0.053
Token playing
Token ID2712
Feature activation+7.90e-01

Pos logit contributions
 canvas+0.032
line+0.031
 product+0.031
 tide+0.031
lee+0.030
Neg logit contributions
 Spot-0.023
girls-0.022
 Buddy-0.022
 Zip-0.021
 Max-0.021
Token hop
Token ID1725
Feature activation-1.79e-01

Pos logit contributions
uddy+0.027
 Johnson+0.025
 Kitty+0.024
oof+0.024
girls+0.024
Neg logit contributions
line-0.024
 canvas-0.024
 product-0.024
 tide-0.023
 shell-0.023
Tokensc
Token ID1416
Feature activation+4.23e+00

Pos logit contributions
line+0.007
 harbor+0.007
 tide+0.007
 shell+0.006
 canvas+0.006
Neg logit contributions
 Johnson-0.005
 Kitty-0.005
oof-0.005
girls-0.005
 Monkey-0.005
Tokenot
Token ID313
Feature activation-1.78e+00

Pos logit contributions
 Spot+0.178
girls+0.174
 Buddy+0.172
 Zip+0.171
 Max+0.168
Neg logit contributions
 canvas-0.107
line-0.103
 product-0.102
 tide-0.100
lee-0.094
Tokench
Token ID354
Feature activation+1.71e+00

Pos logit contributions
 canvas+0.072
line+0.071
 product+0.070
 tide+0.069
lee+0.068
Neg logit contributions
 Johnson-0.042
girls-0.041
 Spot-0.040
 Kitty-0.040
oof-0.039
Token.
Token ID13
Feature activation-1.50e-01

Pos logit contributions
 Monkey+0.055
 Spot+0.055
girls+0.054
 Johnson+0.054
 Buddy+0.053
Neg logit contributions
line-0.056
 canvas-0.054
 tide-0.053
 product-0.053
lee-0.051
Token They
Token ID1119
Feature activation-3.21e-01

Pos logit contributions
 canvas+0.006
lee+0.006
line+0.006
 product+0.006
 harbor+0.006
Neg logit contributions
girls-0.004
oof-0.004
 Zip-0.004
uddy-0.004
 Spot-0.003
Token joined
Token ID5399
Feature activation+2.14e-01

Pos logit contributions
 harbor+0.010
line+0.010
lee+0.010
 shell+0.010
 canvas+0.010
Neg logit contributions
oof-0.011
uddy-0.011
 Johnson-0.010
girls-0.010
 Zip-0.010
Token a
Token ID257
Feature activation+7.42e-01

Pos logit contributions
girls+0.040
uddy+0.040
oof+0.037
Deal+0.037
 Buddy+0.036
Neg logit contributions
 canvas-0.056
 tide-0.056
 product-0.056
 shell-0.054
line-0.053
Token big
Token ID1263
Feature activation-7.50e-01

Pos logit contributions
girls+0.029
 Spot+0.028
 Zip+0.028
 Buddy+0.028
oof+0.027
Neg logit contributions
 canvas-0.022
 product-0.021
 tide-0.021
line-0.020
 harbor-0.020
Token,
Token ID11
Feature activation+1.71e-01

Pos logit contributions
 canvas+0.026
 product+0.025
line+0.025
 tide+0.024
 harbor+0.023
Neg logit contributions
 Spot-0.025
girls-0.024
 Buddy-0.024
 Zip-0.024
uddy-0.023
Token pink
Token ID11398
Feature activation+1.23e-01

Pos logit contributions
girls+0.007
 Spot+0.007
uddy+0.007
 Buddy+0.007
 Zip+0.007
Neg logit contributions
 canvas-0.005
 product-0.004
 tide-0.004
line-0.004
 shell-0.004
Token elephant
Token ID20950
Feature activation+9.68e-01

Pos logit contributions
 Spot+0.004
girls+0.004
 Buddy+0.004
 Zip+0.004
 Max+0.004
Neg logit contributions
 canvas-0.004
 product-0.004
line-0.004
 tide-0.004
 harbor-0.004
Token stuffed
Token ID22259
Feature activation+4.22e+00

Pos logit contributions
 Spot+0.026
 Buddy+0.025
girls+0.025
 Zip+0.024
 Max+0.024
Neg logit contributions
 canvas-0.040
line-0.039
 product-0.039
 tide-0.038
lee-0.037
Token animal
Token ID5044
Feature activation+1.89e+00

Pos logit contributions
ver+0.149
 OK+0.144
uddy+0.137
 Deal+0.137
Deal+0.136
Neg logit contributions
 pumpkin-0.135
lee-0.131
 shell-0.129
 canvas-0.127
line-0.121
Token.
Token ID13
Feature activation-4.14e-01

Pos logit contributions
 Spot+0.054
girls+0.054
 Buddy+0.052
 Zip+0.052
oof+0.051
Neg logit contributions
 canvas-0.072
 product-0.070
line-0.070
 tide-0.068
lee-0.066
Token He
Token ID679
Feature activation-5.39e-01

Pos logit contributions
 canvas+0.017
line+0.017
 product+0.016
lee+0.016
 tide+0.016
Neg logit contributions
girls-0.011
oof-0.010
 Zip-0.010
 Spot-0.010
uddy-0.010
Token had
Token ID550
Feature activation-1.89e-01

Pos logit contributions
 canvas+0.016
lee+0.016
 product+0.015
 shell+0.015
line+0.015
Neg logit contributions
girls-0.020
 Spot-0.019
oof-0.019
uddy-0.018
 Zip-0.018
Token never
Token ID1239
Feature activation+1.21e+00

Pos logit contributions
 canvas+0.008
 product+0.008
lee+0.008
 shell+0.008
line+0.008
Neg logit contributions
girls-0.005
uddy-0.004
Deal-0.004
oof-0.004
 Buddy-0.004
Token hide
Token ID7808
Feature activation+1.80e+00

Pos logit contributions
uddy+0.023
oof+0.022
Deal+0.021
 Johnson+0.021
 Finally+0.021
Neg logit contributions
line-0.024
 canvas-0.023
 tide-0.023
 harbor-0.023
 shell-0.023
Token and
Token ID290
Feature activation+5.26e-01

Pos logit contributions
uddy+0.054
 Monkey+0.053
oof+0.053
girls+0.052
 Zip+0.052
Neg logit contributions
line-0.066
 canvas-0.066
lee-0.064
 shell-0.063
 tide-0.062
Token seek
Token ID5380
Feature activation+8.89e-02

Pos logit contributions
uddy+0.019
ver+0.018
oof+0.018
isk+0.017
girls+0.017
Neg logit contributions
 canvas-0.017
line-0.017
 tide-0.017
 shell-0.016
 harbor-0.016
Token,
Token ID11
Feature activation-3.40e-03

Pos logit contributions
uddy+0.003
oof+0.003
 Monkey+0.003
 Wh+0.003
girls+0.003
Neg logit contributions
 canvas-0.003
line-0.003
 product-0.003
 harbor-0.003
 tide-0.003
Token hop
Token ID1725
Feature activation-3.39e-02

Pos logit contributions
line+0.000
 canvas+0.000
 tide+0.000
 harbor+0.000
 shell+0.000
Neg logit contributions
uddy-0.000
oof-0.000
girls-0.000
 Monkey-0.000
 Johnson-0.000
Tokensc
Token ID1416
Feature activation+4.17e+00

Pos logit contributions
line+0.001
 harbor+0.001
 tide+0.001
 canvas+0.001
 shell+0.001
Neg logit contributions
oof-0.001
girls-0.001
Deal-0.001
 Johnson-0.001
 Monkey-0.001
Tokenot
Token ID313
Feature activation-1.49e+00

Pos logit contributions
 Spot+0.188
girls+0.186
 Buddy+0.183
 Zip+0.182
 Max+0.179
Neg logit contributions
 canvas-0.092
line-0.088
 product-0.087
 tide-0.084
lee-0.081
Tokench
Token ID354
Feature activation+1.80e+00

Pos logit contributions
 canvas+0.055
line+0.055
lee+0.053
 tide+0.052
 product+0.052
Neg logit contributions
 Johnson-0.041
Deal-0.040
girls-0.039
oof-0.038
 Spot-0.037
Token and
Token ID290
Feature activation+3.00e-01

Pos logit contributions
 Johnson+0.051
girls+0.051
 Monkey+0.051
 Spot+0.050
 Enjoy+0.049
Neg logit contributions
line-0.066
 canvas-0.064
 tide-0.062
lee-0.061
 product-0.061
Token much
Token ID881
Feature activation-3.99e-01

Pos logit contributions
oof+0.010
uddy+0.010
ver+0.010
girls+0.010
 Johnson+0.010
Neg logit contributions
 canvas-0.010
 tide-0.010
line-0.010
 shell-0.009
 harbor-0.009
Token more
Token ID517
Feature activation+2.08e-01

Pos logit contributions
 canvas+0.014
 tide+0.013
line+0.013
 product+0.013
 harbor+0.012
Neg logit contributions
girls-0.013
 Spot-0.013
oof-0.013
uddy-0.013
 Zip-0.012
Token a
Token ID257
Feature activation+7.36e-01

Pos logit contributions
girls+0.041
uddy+0.040
oof+0.038
Deal+0.037
 Buddy+0.036
Neg logit contributions
 tide-0.055
 canvas-0.055
 product-0.055
 shell-0.053
 harbor-0.052
Token big
Token ID1263
Feature activation-7.53e-01

Pos logit contributions
girls+0.029
 Spot+0.028
 Zip+0.027
 Buddy+0.027
oof+0.027
Neg logit contributions
 canvas-0.022
 product-0.021
 tide-0.020
line-0.020
 harbor-0.019
Token,
Token ID11
Feature activation+1.47e-01

Pos logit contributions
 canvas+0.026
 product+0.025
line+0.025
 tide+0.024
 harbor+0.023
Neg logit contributions
 Spot-0.025
girls-0.025
 Buddy-0.024
 Zip-0.024
uddy-0.023
Token pink
Token ID11398
Feature activation+1.03e-01

Pos logit contributions
girls+0.006
uddy+0.006
 Spot+0.006
 Buddy+0.006
 Zip+0.006
Neg logit contributions
 canvas-0.004
 product-0.004
 tide-0.004
line-0.004
 shell-0.003
Token elephant
Token ID20950
Feature activation+9.46e-01

Pos logit contributions
 Spot+0.003
girls+0.003
 Buddy+0.003
 Zip+0.003
 Max+0.003
Neg logit contributions
 canvas-0.004
 product-0.003
line-0.003
 tide-0.003
 harbor-0.003
Token stuffed
Token ID22259
Feature activation+4.17e+00

Pos logit contributions
 Spot+0.025
 Buddy+0.024
girls+0.024
 Zip+0.024
 Max+0.023
Neg logit contributions
 canvas-0.039
line-0.038
 product-0.038
 tide-0.038
lee-0.036
Token animal
Token ID5044
Feature activation+1.85e+00

Pos logit contributions
ver+0.147
 OK+0.143
uddy+0.136
Deal+0.135
 Deal+0.135
Neg logit contributions
 pumpkin-0.133
lee-0.130
 shell-0.128
 canvas-0.126
line-0.120
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
 Spot+0.053
girls+0.053
 Buddy+0.051
 Zip+0.051
oof+0.050
Neg logit contributions
 canvas-0.070
 product-0.068
line-0.068
 tide-0.066
lee-0.065
Token He
Token ID679
Feature activation-5.38e-01

Pos logit contributions
 canvas+0.017
line+0.016
 product+0.016
 tide+0.016
lee+0.016
Neg logit contributions
girls-0.010
oof-0.010
 Zip-0.009
 Spot-0.009
uddy-0.009
Token had
Token ID550
Feature activation-2.12e-01

Pos logit contributions
 canvas+0.016
lee+0.016
 product+0.015
 shell+0.015
line+0.015
Neg logit contributions
girls-0.020
 Spot-0.019
oof-0.019
 Zip-0.018
uddy-0.018
Token never
Token ID1239
Feature activation+1.18e+00

Pos logit contributions
 canvas+0.009
 product+0.009
lee+0.009
 shell+0.009
line+0.009
Neg logit contributions
girls-0.005
uddy-0.005
Deal-0.005
 Buddy-0.005
oof-0.005
Token.
Token ID13
Feature activation+3.39e-01

Pos logit contributions
 canvas+0.005
line+0.005
 tide+0.004
 product+0.004
 pumpkin+0.004
Neg logit contributions
uddy-0.007
 Kenny-0.007
 Zip-0.007
 Monkey-0.007
 Buddy-0.007
Token You
Token ID921
Feature activation-2.58e-01

Pos logit contributions
girls+0.010
uddy+0.009
ll+0.009
isk+0.009
ver+0.009
Neg logit contributions
 canvas-0.012
line-0.011
 tide-0.011
rys-0.011
 product-0.011
Token can
Token ID460
Feature activation+4.33e-01

Pos logit contributions
 canvas+0.010
 tide+0.009
 shell+0.009
line+0.009
 harbor+0.009
Neg logit contributions
uddy-0.007
 Zip-0.007
girls-0.007
 Spot-0.007
 Johnson-0.007
Token play
Token ID711
Feature activation+7.47e-01

Pos logit contributions
girls+0.013
 Zip+0.012
 Spot+0.012
uddy+0.012
 Buddy+0.012
Neg logit contributions
 canvas-0.016
line-0.015
 tide-0.015
 harbor-0.015
 product-0.015
Token hop
Token ID1725
Feature activation-2.53e-01

Pos logit contributions
uddy+0.027
 Johnson+0.025
girls+0.024
ver+0.023
 Kenny+0.023
Neg logit contributions
 canvas-0.024
 shell-0.023
 product-0.023
line-0.023
 tide-0.023
Tokensc
Token ID1416
Feature activation+4.11e+00

Pos logit contributions
line+0.008
 harbor+0.008
 shell+0.008
 tide+0.008
 canvas+0.007
Neg logit contributions
 Johnson-0.009
uddy-0.008
 Kenny-0.008
girls-0.008
 Monkey-0.008
Tokenot
Token ID313
Feature activation-1.90e+00

Pos logit contributions
 Spot+0.191
girls+0.190
 Buddy+0.187
 Monkey+0.186
 Johnson+0.185
Neg logit contributions
 canvas-0.083
 product-0.078
line-0.077
lee-0.072
 tide-0.072
Tokench
Token ID354
Feature activation+1.55e+00

Pos logit contributions
 canvas+0.082
line+0.081
 tide+0.079
 product+0.079
lee+0.076
Neg logit contributions
 Spot-0.042
 Johnson-0.042
girls-0.041
 Buddy-0.040
 Kitty-0.040
Token again
Token ID757
Feature activation+8.98e-01

Pos logit contributions
 Spot+0.043
girls+0.042
 Buddy+0.041
 Johnson+0.041
 Monkey+0.041
Neg logit contributions
 canvas-0.058
line-0.058
 tide-0.057
 product-0.057
lee-0.054
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
uddy+0.029
girls+0.028
 Spot+0.028
 Zip+0.028
 Buddy+0.028
Neg logit contributions
 canvas-0.032
line-0.031
 product-0.030
 tide-0.029
 shell-0.029
Token But
Token ID887
Feature activation-2.70e-01

Pos logit contributions
ll+0.008
girls+0.008
 Johnson+0.007
isk+0.007
uddy+0.007
Neg logit contributions
 canvas-0.010
line-0.010
rys-0.010
 tide-0.009
 harbor-0.009
Token.
Token ID13
Feature activation-3.31e-01

Pos logit contributions
 Spot+0.035
girls+0.034
 Zip+0.034
 Buddy+0.034
oof+0.034
Neg logit contributions
line-0.045
 canvas-0.044
 product-0.043
 tide-0.042
lee-0.041
Token He
Token ID679
Feature activation-1.28e-01

Pos logit contributions
 canvas+0.016
 product+0.015
line+0.015
 tide+0.015
lee+0.014
Neg logit contributions
 Spot-0.007
girls-0.007
 Buddy-0.006
 Zip-0.006
 Max-0.006
Token smiled
Token ID13541
Feature activation+1.90e-01

Pos logit contributions
 canvas+0.004
 product+0.004
 tide+0.004
line+0.004
lee+0.004
Neg logit contributions
girls-0.004
 Zip-0.004
 Spot-0.004
 Buddy-0.004
uddy-0.004
Token as
Token ID355
Feature activation-7.91e-02

Pos logit contributions
 Spot+0.004
girls+0.004
 Buddy+0.004
 Zip+0.004
 Max+0.004
Neg logit contributions
 canvas-0.009
line-0.008
 product-0.008
 tide-0.008
lee-0.008
Token he
Token ID339
Feature activation+6.78e-01

Pos logit contributions
 canvas+0.003
 product+0.003
line+0.003
 tide+0.003
lee+0.003
Neg logit contributions
 Spot-0.002
 Buddy-0.002
 Zip-0.002
 Max-0.002
girls-0.002
Token stuffed
Token ID22259
Feature activation+4.08e+00

Pos logit contributions
 Spot+0.024
 Zip+0.024
 Buddy+0.024
girls+0.024
uddy+0.023
Neg logit contributions
 canvas-0.020
 product-0.020
lee-0.020
line-0.020
 tide-0.019
Token them
Token ID606
Feature activation+1.03e+00

Pos logit contributions
 OK+0.150
 Deal+0.146
uddy+0.141
 Okay+0.140
ver+0.138
Neg logit contributions
lee-0.127
line-0.123
 shells-0.122
 shell-0.121
 tides-0.118
Token into
Token ID656
Feature activation+2.92e-01

Pos logit contributions
oof+0.033
 Zip+0.032
girls+0.032
uddy+0.031
 Buddy+0.031
Neg logit contributions
line-0.039
 canvas-0.037
 product-0.035
 harbor-0.035
lee-0.035
Token his
Token ID465
Feature activation+1.41e-01

Pos logit contributions
girls+0.009
 Spot+0.008
uddy+0.008
 Buddy+0.008
 Zip+0.008
Neg logit contributions
 canvas-0.011
 product-0.011
line-0.011
 tide-0.011
lee-0.010
Token backpack
Token ID22526
Feature activation+8.41e-01

Pos logit contributions
 Spot+0.005
girls+0.005
 Buddy+0.005
 Zip+0.005
 Wh+0.005
Neg logit contributions
 canvas-0.004
 product-0.004
line-0.004
 tide-0.004
lee-0.004
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
girls+0.029
oof+0.028
 Zip+0.028
 Buddy+0.027
 Spot+0.027
Neg logit contributions
line-0.031
 canvas-0.029
 product-0.027
 shell-0.026
 harbor-0.026
Token pieces
Token ID5207
Feature activation-7.62e-01

Pos logit contributions
line+0.003
 canvas+0.003
 harbor+0.003
lee+0.003
 tide+0.003
Neg logit contributions
 Spot-0.002
 Fl-0.001
 Max-0.001
girls-0.001
 Buddy-0.001
Token of
Token ID286
Feature activation+1.92e+00

Pos logit contributions
 canvas+0.032
 product+0.031
 tide+0.030
line+0.030
lee+0.029
Neg logit contributions
 Spot-0.020
girls-0.019
 Buddy-0.018
 Zip-0.018
 Max-0.018
Token chocolate
Token ID11311
Feature activation+5.89e-01

Pos logit contributions
girls+0.066
uddy+0.065
 Zip+0.061
 Buddy+0.061
 Monkey+0.061
Neg logit contributions
 canvas-0.066
 product-0.065
 tide-0.062
 pumpkin-0.061
line-0.061
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
 Spot+0.017
girls+0.017
 Buddy+0.017
 Zip+0.016
 Fl+0.016
Neg logit contributions
 canvas-0.022
line-0.022
 product-0.022
 tide-0.021
lee-0.021
Token They
Token ID1119
Feature activation-3.73e-01

Pos logit contributions
girls+0.005
 Spot+0.005
 Buddy+0.005
 Zip+0.005
oof+0.005
Neg logit contributions
 canvas-0.008
line-0.008
 product-0.008
 tide-0.008
lee-0.008
Token stuffed
Token ID22259
Feature activation+4.07e+00

Pos logit contributions
 canvas+0.012
line+0.012
 product+0.011
 tide+0.011
 shell+0.011
Neg logit contributions
 Zip-0.013
girls-0.013
oof-0.013
 Buddy-0.013
uddy-0.013
Token them
Token ID606
Feature activation+5.63e-01

Pos logit contributions
uddy+0.156
ver+0.151
 OK+0.150
Deal+0.143
girls+0.142
Neg logit contributions
 pumpkin-0.119
 pulp-0.112
 canvas-0.110
lee-0.108
 product-0.107
Token in
Token ID287
Feature activation+9.41e-02

Pos logit contributions
girls+0.017
oof+0.017
uddy+0.017
 Zip+0.017
 Buddy+0.016
Neg logit contributions
 canvas-0.021
 product-0.020
line-0.020
 pumpkin-0.020
 shell-0.019
Token their
Token ID511
Feature activation+9.73e-02

Pos logit contributions
girls+0.003
uddy+0.003
Deal+0.003
oof+0.003
 Buddy+0.003
Neg logit contributions
 product-0.003
 canvas-0.003
 shell-0.003
 pumpkin-0.003
line-0.003
Token mouths
Token ID28552
Feature activation+5.18e-01

Pos logit contributions
girls+0.004
 Spot+0.004
 Zip+0.004
 Buddy+0.004
uddy+0.004
Neg logit contributions
 canvas-0.003
 product-0.003
line-0.003
 tide-0.003
lee-0.003
Token and
Token ID290
Feature activation+3.83e-01

Pos logit contributions
girls+0.015
 Buddy+0.015
 Zip+0.015
uddy+0.014
oof+0.014
Neg logit contributions
line-0.021
 canvas-0.020
 product-0.020
 tide-0.019
 shell-0.019
Token shelves
Token ID20726
Feature activation-3.93e-01

Pos logit contributions
 Spot+0.015
girls+0.014
 Buddy+0.014
 Zip+0.014
 Fl+0.014
Neg logit contributions
 canvas-0.017
line-0.016
 product-0.016
 tide-0.016
lee-0.015
Token,
Token ID11
Feature activation+4.72e-01

Pos logit contributions
line+0.016
 canvas+0.015
 product+0.015
 tide+0.014
lee+0.014
Neg logit contributions
oof-0.012
girls-0.012
 Spot-0.011
 Buddy-0.011
 Zip-0.011
Token old
Token ID1468
Feature activation-8.75e-01

Pos logit contributions
 Spot+0.011
girls+0.011
 Zip+0.011
 Buddy+0.011
oof+0.010
Neg logit contributions
 canvas-0.021
line-0.020
 product-0.020
 tide-0.020
lee-0.019
Token blankets
Token ID34794
Feature activation+1.34e+00

Pos logit contributions
 canvas+0.029
 product+0.028
line+0.027
lee+0.026
 tide+0.026
Neg logit contributions
 Spot-0.031
 Zip-0.030
oof-0.030
girls-0.030
 Buddy-0.029
Token and
Token ID290
Feature activation+6.77e-02

Pos logit contributions
oof+0.041
girls+0.040
 Zip+0.038
 Spot+0.038
 Buddy+0.037
Neg logit contributions
line-0.053
 canvas-0.051
 product-0.048
 harbor-0.047
 tide-0.047
Token stuffed
Token ID22259
Feature activation+4.07e+00

Pos logit contributions
 Spot+0.002
girls+0.002
 Zip+0.002
uddy+0.002
oof+0.002
Neg logit contributions
 canvas-0.002
 product-0.002
line-0.002
 tide-0.002
lee-0.002
Token animals
Token ID4695
Feature activation+1.16e-01

Pos logit contributions
ver+0.161
oof+0.159
 OK+0.156
uddy+0.156
Deal+0.155
Neg logit contributions
lee-0.109
 canvas-0.109
 product-0.105
 pans-0.104
 floors-0.102
Token.
Token ID13
Feature activation-4.89e-01

Pos logit contributions
oof+0.004
 Spot+0.004
 Zip+0.004
 Buddy+0.004
girls+0.004
Neg logit contributions
line-0.004
 canvas-0.004
 product-0.004
 harbor-0.003
 shell-0.003
Token She
Token ID1375
Feature activation-7.38e-01

Pos logit contributions
 canvas+0.016
line+0.015
lee+0.015
 product+0.014
 harbor+0.013
Neg logit contributions
oof-0.018
girls-0.018
 losers-0.016
uddy-0.016
 ever-0.015
Token worked
Token ID3111
Feature activation+1.11e+00

Pos logit contributions
 canvas+0.025
 product+0.025
line+0.024
lee+0.023
 tide+0.023
Neg logit contributions
 Spot-0.025
girls-0.025
 Zip-0.024
 Buddy-0.024
oof-0.024
Token and
Token ID290
Feature activation+4.36e-01

Pos logit contributions
girls+0.036
oof+0.034
 Spot+0.033
uddy+0.032
 Enjoy+0.031
Neg logit contributions
 product-0.043
 canvas-0.040
lee-0.039
line-0.039
 tide-0.036
Token Inside
Token ID14384
Feature activation+4.14e-01

Pos logit contributions
 canvas+0.014
line+0.014
 product+0.014
lee+0.014
 tide+0.013
Neg logit contributions
girls-0.009
oof-0.008
 Spot-0.008
 Zip-0.008
 Wh-0.008
Token were
Token ID547
Feature activation+7.20e-01

Pos logit contributions
girls+0.013
oof+0.012
 Zip+0.012
 Spot+0.012
 Wh+0.012
Neg logit contributions
 product-0.015
line-0.015
 canvas-0.015
 tide-0.015
 harbor-0.015
Token all
Token ID477
Feature activation+6.06e-01

Pos logit contributions
uddy+0.022
girls+0.022
oof+0.022
isk+0.021
Deal+0.021
Neg logit contributions
 tide-0.026
 canvas-0.025
lee-0.025
 product-0.025
 harbor-0.025
Token kinds
Token ID6982
Feature activation+3.63e-01

Pos logit contributions
 Spot+0.017
 Buddy+0.016
girls+0.016
 Zip+0.016
 Max+0.015
Neg logit contributions
 canvas-0.024
line-0.024
 product-0.023
 tide-0.023
lee-0.022
Token of
Token ID286
Feature activation+2.61e+00

Pos logit contributions
 Spot+0.009
girls+0.009
 Buddy+0.008
 Zip+0.008
 Wh+0.008
Neg logit contributions
 canvas-0.015
line-0.015
 product-0.015
 tide-0.015
lee-0.014
Token stuffed
Token ID22259
Feature activation+4.03e+00

Pos logit contributions
uddy+0.099
girls+0.098
isk+0.095
ver+0.095
 Spot+0.094
Neg logit contributions
 canvas-0.080
 tide-0.079
 product-0.079
lee-0.077
 shell-0.073
Token animals
Token ID4695
Feature activation+5.56e-01

Pos logit contributions
ver+0.185
 OK+0.181
 Okay+0.170
 Deal+0.170
uddy+0.168
Neg logit contributions
lee-0.111
 shells-0.098
 pumpkin-0.097
 waves-0.097
 shell-0.092
Token,
Token ID11
Feature activation-8.37e-02

Pos logit contributions
oof+0.015
 Spot+0.015
girls+0.015
 Wh+0.015
 Zip+0.015
Neg logit contributions
line-0.021
 canvas-0.021
 product-0.021
 tide-0.020
 harbor-0.020
Token games
Token ID1830
Feature activation+4.79e-01

Pos logit contributions
 canvas+0.003
 tide+0.003
 pumpkin+0.003
line+0.003
 product+0.003
Neg logit contributions
uddy-0.003
ver-0.003
girls-0.003
isk-0.003
Deal-0.003
Token,
Token ID11
Feature activation+3.02e-01

Pos logit contributions
girls+0.013
oof+0.013
 Spot+0.013
 Zip+0.013
 Wh+0.013
Neg logit contributions
line-0.019
 canvas-0.018
 product-0.018
 tide-0.017
 harbor-0.017
Token humor
Token ID14733
Feature activation+6.58e-01

Pos logit contributions
uddy+0.010
girls+0.010
ver+0.010
Deal+0.010
oof+0.009
Neg logit contributions
 canvas-0.010
 tide-0.010
line-0.010
 pumpkin-0.010
 harbor-0.010
Token know
Token ID760
Feature activation-6.44e-01

Pos logit contributions
girls+0.000
 Buddy+0.000
 Spot+0.000
 Zip+0.000
 Kitty+0.000
Neg logit contributions
 product-0.000
 canvas-0.000
line-0.000
 tide-0.000
 shell-0.000
Token,
Token ID11
Feature activation-6.14e-01

Pos logit contributions
 canvas+0.025
 tide+0.024
line+0.024
 product+0.023
lee+0.023
Neg logit contributions
girls-0.018
 Spot-0.018
uddy-0.018
 Buddy-0.017
 Zip-0.017
Token right
Token ID826
Feature activation-5.08e-01

Pos logit contributions
 canvas+0.024
line+0.024
 tide+0.023
 shell+0.022
 product+0.022
Neg logit contributions
girls-0.018
uddy-0.017
oof-0.017
 Spot-0.017
 Buddy-0.017
Token?
Token ID30
Feature activation-5.46e-01

Pos logit contributions
line+0.024
 canvas+0.023
 product+0.022
lee+0.022
 pulp+0.022
Neg logit contributions
 Spot-0.011
 Max-0.010
 Zip-0.010
 Fl-0.010
 Buddy-0.010
Token Micro
Token ID4527
Feature activation-5.33e-01

Pos logit contributions
 canvas+0.020
line+0.020
 tide+0.019
 product+0.019
lee+0.018
Neg logit contributions
girls-0.016
 Spot-0.015
 Buddy-0.015
oof-0.015
uddy-0.015
Tokensc
Token ID1416
Feature activation+3.97e+00

Pos logit contributions
 canvas+0.020
line+0.019
 tide+0.018
 product+0.018
lee+0.018
Neg logit contributions
girls-0.016
 Spot-0.016
 Buddy-0.015
uddy-0.015
 Johnson-0.015
Tokenopes
Token ID13920
Feature activation+2.63e-01

Pos logit contributions
 Spot+0.167
 Buddy+0.161
 Zip+0.161
girls+0.161
oof+0.159
Neg logit contributions
 canvas-0.101
line-0.099
 product-0.097
 tide-0.095
 harbor-0.090
Token are
Token ID389
Feature activation+3.96e-01

Pos logit contributions
 Spot+0.007
girls+0.007
 Buddy+0.007
 Zip+0.006
oof+0.006
Neg logit contributions
 canvas-0.011
line-0.011
 product-0.010
 tide-0.010
 harbor-0.010
Token amazing
Token ID4998
Feature activation+2.45e-01

Pos logit contributions
uddy+0.012
girls+0.011
oof+0.011
 Spot+0.011
 Johnson+0.011
Neg logit contributions
 canvas-0.014
 product-0.014
 tide-0.014
line-0.014
 shell-0.014
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
 Spot+0.008
uddy+0.008
 Zip+0.008
oof+0.008
 Buddy+0.008
Neg logit contributions
 canvas-0.008
 product-0.008
 tide-0.008
lee-0.008
line-0.007
Token They
Token ID1119
Feature activation-6.97e-01

Pos logit contributions
girls+0.003
 Johnson+0.003
isk+0.003
oof+0.003
ll+0.003
Neg logit contributions
line-0.004
 canvas-0.004
 tide-0.004
 harbor-0.004
lee-0.004
Token place
Token ID1295
Feature activation-2.93e-01

Pos logit contributions
 canvas+0.008
 tide+0.007
 product+0.007
 pumpkin+0.007
 harbor+0.007
Neg logit contributions
girls-0.009
 Zip-0.009
 Spot-0.008
oof-0.008
 Buddy-0.008
Token of
Token ID286
Feature activation+7.44e-01

Pos logit contributions
 canvas+0.012
line+0.012
 product+0.012
 tide+0.012
 shell+0.011
Neg logit contributions
girls-0.007
 Spot-0.007
 Zip-0.007
oof-0.007
 Buddy-0.007
Token peace
Token ID4167
Feature activation-6.15e-01

Pos logit contributions
uddy+0.030
ver+0.029
girls+0.028
 Zip+0.026
oof+0.026
Neg logit contributions
 tide-0.023
 canvas-0.022
 product-0.022
 shell-0.022
 pumpkin-0.021
Token and
Token ID290
Feature activation-5.91e-01

Pos logit contributions
 canvas+0.022
line+0.022
 product+0.021
 tide+0.021
 harbor+0.021
Neg logit contributions
 Spot-0.019
girls-0.019
 Zip-0.018
 Buddy-0.018
oof-0.018
Token content
Token ID2695
Feature activation-1.39e+00

Pos logit contributions
 canvas+0.019
 tide+0.019
line+0.018
 product+0.018
 shell+0.018
Neg logit contributions
uddy-0.022
girls-0.020
oof-0.020
 Zip-0.020
 Johnson-0.020
Tokenment
Token ID434
Feature activation-3.87e+00

Pos logit contributions
 canvas+0.049
 product+0.048
line+0.048
 tide+0.046
lee+0.045
Neg logit contributions
 Spot-0.045
girls-0.043
 Buddy-0.043
 Zip-0.042
 Fl-0.042
Token.
Token ID13
Feature activation-3.47e-01

Pos logit contributions
line+0.093
 product+0.081
 canvas+0.079
 tide+0.075
 shell+0.073
Neg logit contributions
uddy-0.167
oof-0.166
 Zip-0.162
 Wh-0.161
 Monkey-0.159
Token
Token ID220
Feature activation-3.06e-01

Pos logit contributions
line+0.012
lee+0.011
 canvas+0.011
 tide+0.011
 harbor+0.011
Neg logit contributions
girls-0.011
 losers-0.010
oof-0.010
 ever-0.010
isk-0.009
Token
Token ID198
Feature activation-6.14e-01

Pos logit contributions
line+0.012
 product+0.011
 canvas+0.011
lee+0.011
 tide+0.010
Neg logit contributions
girls-0.009
oof-0.008
 Monkey-0.008
 Spot-0.008
 Buddy-0.008
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
line+0.021
 product+0.019
 canvas+0.019
 tide+0.018
 harbor+0.018
Neg logit contributions
girls-0.020
 Spot-0.018
 losers-0.018
 Wh-0.018
oof-0.018
TokenOne
Token ID3198
Feature activation+2.85e-01

Pos logit contributions
line+0.027
 canvas+0.026
 product+0.026
 tide+0.026
 harbor+0.025
Neg logit contributions
girls-0.021
 Spot-0.020
 Buddy-0.019
 Max-0.019
 Fl-0.019
Token stopped
Token ID5025
Feature activation-2.44e-01

Pos logit contributions
 Spot+0.018
 Fl+0.017
 Will+0.017
 Buddy+0.017
 Max+0.017
Neg logit contributions
 product-0.027
 canvas-0.026
line-0.025
 tide-0.024
 harbor-0.024
Token and
Token ID290
Feature activation-2.74e-01

Pos logit contributions
 canvas+0.011
line+0.010
 product+0.010
 tide+0.010
lee+0.010
Neg logit contributions
 Spot-0.006
girls-0.006
 Buddy-0.005
 Zip-0.005
 Fl-0.005
Token froze
Token ID37785
Feature activation-9.48e-01

Pos logit contributions
 canvas+0.009
 product+0.009
line+0.009
 tide+0.008
lee+0.008
Neg logit contributions
 Spot-0.010
 Buddy-0.009
girls-0.009
 Zip-0.009
 Max-0.009
Token in
Token ID287
Feature activation-5.57e-01

Pos logit contributions
 canvas+0.041
 product+0.040
line+0.039
 tide+0.037
rys+0.037
Neg logit contributions
 Spot-0.023
 Buddy-0.021
 Max-0.021
 Fl-0.021
 Zip-0.021
Token amaz
Token ID40642
Feature activation-1.87e+00

Pos logit contributions
line+0.019
 canvas+0.019
 product+0.018
 tide+0.018
lee+0.017
Neg logit contributions
 Spot-0.019
 Buddy-0.018
 Max-0.018
 Zip-0.018
girls-0.018
Tokenment
Token ID434
Feature activation-3.78e+00

Pos logit contributions
line+0.071
 canvas+0.070
 product+0.066
 harbor+0.066
 pulp+0.065
Neg logit contributions
 Spot-0.052
 Max-0.049
 just-0.049
 Zip-0.048
 Buddy-0.048
Token,
Token ID11
Feature activation-6.37e-01

Pos logit contributions
 canvas+0.103
line+0.101
 product+0.097
 tide+0.097
 harbor+0.089
Neg logit contributions
uddy-0.156
girls-0.153
oof-0.151
 Buddy-0.150
 Monkey-0.148
Token watching
Token ID4964
Feature activation-1.00e+00

Pos logit contributions
line+0.025
 canvas+0.024
 tide+0.023
 product+0.023
lee+0.022
Neg logit contributions
girls-0.019
uddy-0.018
oof-0.018
 Buddy-0.018
 Zip-0.018
Token the
Token ID262
Feature activation-3.26e-01

Pos logit contributions
 canvas+0.037
line+0.035
 tide+0.035
 product+0.035
lee+0.034
Neg logit contributions
girls-0.031
uddy-0.030
 Spot-0.030
oof-0.030
 Zip-0.029
Token bright
Token ID6016
Feature activation-1.32e+00

Pos logit contributions
 canvas+0.010
line+0.010
 product+0.010
 tide+0.009
lee+0.009
Neg logit contributions
 Spot-0.012
girls-0.011
 Buddy-0.011
 Zip-0.011
 Max-0.011
Token colours
Token ID18915
Feature activation-8.67e-01

Pos logit contributions
line+0.045
 canvas+0.043
 product+0.042
lee+0.042
rys+0.042
Neg logit contributions
 Spot-0.041
 Buddy-0.039
 George-0.039
 Max-0.039
 Bob-0.038
Token:
Token ID25
Feature activation-1.56e+00

Pos logit contributions
line+0.009
 canvas+0.009
 tide+0.009
 product+0.009
 harbor+0.008
Neg logit contributions
girls-0.009
uddy-0.009
oof-0.009
 Buddy-0.008
 Zip-0.008
Token
Token ID198
Feature activation-3.37e-01

Pos logit contributions
line+0.054
 tide+0.052
 canvas+0.052
 product+0.050
 pumpkin+0.050
Neg logit contributions
girls-0.052
uddy-0.048
oof-0.046
isk-0.045
 Buddy-0.045
Token
Token ID198
Feature activation-2.87e-01

Pos logit contributions
 canvas+0.014
line+0.014
 product+0.014
 tide+0.014
lee+0.014
Neg logit contributions
girls-0.008
 Spot-0.008
 Buddy-0.007
 Zip-0.007
 Fl-0.007
Token"
Token ID1
Feature activation-7.43e-01

Pos logit contributions
 canvas+0.010
line+0.010
 product+0.010
 tide+0.010
lee+0.009
Neg logit contributions
 Spot-0.009
girls-0.009
 Buddy-0.009
 Zip-0.009
 Fl-0.008
TokenMeasure
Token ID47384
Feature activation+2.56e-01

Pos logit contributions
line+0.026
 canvas+0.025
 tide+0.025
 product+0.024
 harbor+0.023
Neg logit contributions
girls-0.024
 Spot-0.023
 Buddy-0.023
uddy-0.022
 Max-0.022
Tokenment
Token ID434
Feature activation-3.64e+00

Pos logit contributions
girls+0.008
 Spot+0.008
 Buddy+0.008
 Zip+0.008
uddy+0.008
Neg logit contributions
 canvas-0.009
 product-0.009
line-0.008
 tide-0.008
lee-0.008
Token complete
Token ID1844
Feature activation+2.44e-01

Pos logit contributions
 canvas+0.150
line+0.141
 product+0.141
 tide+0.136
 pumpkin+0.131
Neg logit contributions
girls-0.102
 Spot-0.100
uddy-0.099
 Buddy-0.098
 Wh-0.098
Token.
Token ID13
Feature activation+6.60e-01

Pos logit contributions
girls+0.008
uddy+0.007
 Spot+0.007
 Buddy+0.007
 Zip+0.007
Neg logit contributions
 canvas-0.009
 product-0.009
line-0.008
 tide-0.008
lee-0.008
Token Height
Token ID27280
Feature activation+8.66e-01

Pos logit contributions
girls+0.019
 Spot+0.018
 Buddy+0.018
uddy+0.017
 Zip+0.017
Neg logit contributions
 canvas-0.026
line-0.025
 tide-0.024
 product-0.024
lee-0.023
Token:
Token ID25
Feature activation-4.59e-01

Pos logit contributions
 Spot+0.031
girls+0.031
 Buddy+0.030
 Zip+0.030
 Fl+0.030
Neg logit contributions
 canvas-0.027
line-0.026
 product-0.026
 tide-0.025
lee-0.024
Token 90
Token ID4101
Feature activation-7.10e-01

Pos logit contributions
 canvas+0.017
line+0.016
 product+0.015
 tide+0.015
 pumpkin+0.015
Neg logit contributions
girls-0.015
 Spot-0.015
 Buddy-0.014
uddy-0.014
 Zip-0.014
Token we
Token ID356
Feature activation-1.07e+00

Pos logit contributions
girls+0.005
oof+0.005
uddy+0.005
 Zip+0.005
 Buddy+0.005
Neg logit contributions
 canvas-0.007
line-0.006
 tide-0.006
 product-0.006
 pumpkin-0.006
Token might
Token ID1244
Feature activation-3.30e-01

Pos logit contributions
 canvas+0.043
line+0.042
 tide+0.041
 pumpkin+0.041
 shell+0.041
Neg logit contributions
 Zip-0.027
oof-0.026
 Buddy-0.026
 Spot-0.026
 Kenny-0.025
Token break
Token ID2270
Feature activation-8.36e-03

Pos logit contributions
 canvas+0.012
line+0.012
 product+0.012
 tide+0.012
lee+0.011
Neg logit contributions
 Spot-0.010
girls-0.010
 Buddy-0.010
 Zip-0.010
 Fl-0.009
Token the
Token ID262
Feature activation-4.08e-01

Pos logit contributions
 canvas+0.000
line+0.000
 product+0.000
 tide+0.000
 pumpkin+0.000
Neg logit contributions
uddy-0.000
girls-0.000
 Zip-0.000
 Spot-0.000
 Buddy-0.000
Token st
Token ID336
Feature activation-1.76e+00

Pos logit contributions
 canvas+0.011
line+0.010
 product+0.010
 tide+0.010
 harbor+0.010
Neg logit contributions
 Spot-0.017
girls-0.016
 Buddy-0.016
 Zip-0.016
 Wh-0.016
Tokenalks
Token ID23833
Feature activation-3.64e+00

Pos logit contributions
 canvas+0.055
 tide+0.053
 product+0.052
line+0.052
lee+0.050
Neg logit contributions
girls-0.062
uddy-0.060
 Spot-0.059
 Fl-0.057
oof-0.057
Token."
Token ID526
Feature activation-1.62e-01

Pos logit contributions
 canvas+0.145
line+0.144
 product+0.140
 tide+0.138
lee+0.132
Neg logit contributions
 Spot-0.100
girls-0.099
 Buddy-0.097
 Zip-0.096
oof-0.093
Token
Token ID198
Feature activation-5.02e-01

Pos logit contributions
line+0.007
 canvas+0.007
 product+0.006
lee+0.006
 tide+0.006
Neg logit contributions
girls-0.004
 Zip-0.004
oof-0.004
 Buddy-0.004
uddy-0.004
Token
Token ID198
Feature activation-5.03e-01

Pos logit contributions
line+0.018
 product+0.018
 canvas+0.017
lee+0.017
 tide+0.016
Neg logit contributions
girls-0.015
 Monkey-0.014
 Zip-0.014
oof-0.014
 Buddy-0.013
TokenL
Token ID43
Feature activation-3.15e-01

Pos logit contributions
 canvas+0.020
line+0.020
 product+0.020
 tide+0.019
lee+0.019
Neg logit contributions
 Spot-0.014
girls-0.014
 Buddy-0.013
 Zip-0.013
 Fl-0.013
Tokenily
Token ID813
Feature activation-3.06e-01

Pos logit contributions
 canvas+0.009
line+0.009
 product+0.009
lee+0.009
 tide+0.009
Neg logit contributions
girls-0.012
 Spot-0.012
 Buddy-0.012
 Monkey-0.011
 Zip-0.011
Token looked
Token ID3114
Feature activation-1.31e+00

Pos logit contributions
 Spot+0.008
girls+0.007
 Buddy+0.007
 Zip+0.007
 Max+0.007
Neg logit contributions
 canvas-0.008
line-0.008
 product-0.008
 tide-0.008
lee-0.008
Token through
Token ID832
Feature activation-5.77e-01

Pos logit contributions
 canvas+0.060
 product+0.059
line+0.058
 tide+0.057
 harbor+0.055
Neg logit contributions
 Spot-0.030
 Max-0.027
 Buddy-0.026
 Fl-0.026
girls-0.026
Token the
Token ID262
Feature activation-4.42e-01

Pos logit contributions
 canvas+0.022
 product+0.022
line+0.021
 tide+0.021
lee+0.021
Neg logit contributions
 Spot-0.017
girls-0.017
 Buddy-0.016
 Zip-0.016
uddy-0.016
Token ey
Token ID1926
Feature activation-3.38e+00

Pos logit contributions
line+0.011
 product+0.011
 canvas+0.010
lee+0.010
 tide+0.010
Neg logit contributions
 Spot-0.018
 Max-0.017
 Fl-0.017
girls-0.017
 Buddy-0.017
Tokenep
Token ID538
Feature activation-8.23e-01

Pos logit contributions
 canvas+0.114
 harbor+0.110
line+0.109
 tide+0.108
 product+0.105
Neg logit contributions
 Zip-0.107
 Spot-0.107
girls-0.104
oof-0.103
 Buddy-0.102
Tokeniece
Token ID8535
Feature activation-3.54e+00

Pos logit contributions
line+0.023
 canvas+0.020
 product+0.020
 tide+0.019
lee+0.019
Neg logit contributions
 Buddy-0.035
 Spot-0.034
oof-0.034
girls-0.034
 Kitty-0.034
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
 canvas+0.127
line+0.125
 product+0.123
 tide+0.121
lee+0.117
Neg logit contributions
 Spot-0.111
girls-0.108
 Buddy-0.107
 Zip-0.105
 Wh-0.103
Token He
Token ID679
Feature activation-6.44e-01

Pos logit contributions
girls+0.001
oof+0.001
 Monkey+0.001
uddy+0.001
 Buddy+0.001
Neg logit contributions
line-0.001
 canvas-0.001
 tide-0.001
lee-0.001
 product-0.001
Token saw
Token ID2497
Feature activation-4.27e-01

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.018
 tide+0.017
lee+0.017
Neg logit contributions
girls-0.024
 Buddy-0.024
 Spot-0.024
uddy-0.024
oof-0.024
Token the
Token ID262
Feature activation-2.46e-02

Pos logit contributions
 canvas+0.017
line+0.017
 tide+0.017
 product+0.016
lee+0.016
Neg logit contributions
girls-0.012
 Spot-0.011
uddy-0.011
 Buddy-0.011
oof-0.011
Token tiny
Token ID7009
Feature activation-1.58e+00

Pos logit contributions
 canvas+0.001
line+0.001
 product+0.001
 tide+0.001
lee+0.001
Neg logit contributions
 Spot-0.001
girls-0.001
 Buddy-0.001
 Zip-0.001
 Max-0.001
Token fingers
Token ID9353
Feature activation-1.94e+00

Pos logit contributions
 canvas+0.033
 product+0.032
 shell+0.031
 tide+0.030
line+0.030
Neg logit contributions
 Spot-0.041
 Buddy-0.041
 Zip-0.041
girls-0.041
uddy-0.040
Token and
Token ID290
Feature activation-9.08e-01

Pos logit contributions
line+0.077
 canvas+0.077
 product+0.075
 tide+0.073
lee+0.071
Neg logit contributions
girls-0.053
 Spot-0.053
 Buddy-0.051
 Zip-0.051
oof-0.050
Token feel
Token ID1254
Feature activation-1.80e+00

Pos logit contributions
 canvas+0.031
 product+0.030
line+0.029
 tide+0.029
 shell+0.028
Neg logit contributions
 Spot-0.030
uddy-0.030
girls-0.030
oof-0.029
 Zip-0.029
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
 canvas+0.088
 product+0.085
line+0.084
 tide+0.082
lee+0.081
Neg logit contributions
 Spot-0.038
 Fl-0.035
 Buddy-0.034
 Max-0.033
 love-0.032
Token smooth
Token ID7209
Feature activation-2.36e+00

Pos logit contributions
 canvas+0.044
line+0.044
 product+0.043
lee+0.042
 tide+0.041
Neg logit contributions
 Spot-0.047
 Fl-0.044
girls-0.044
 Buddy-0.044
 Max-0.043
Tokenness
Token ID1108
Feature activation-3.53e+00

Pos logit contributions
 canvas+0.081
lee+0.079
line+0.077
 product+0.075
 tide+0.075
Neg logit contributions
 Spot-0.074
 Fl-0.069
girls-0.068
 Zip-0.067
 Wh-0.066
Token between
Token ID1022
Feature activation-1.28e+00

Pos logit contributions
 canvas+0.148
 product+0.144
line+0.143
 tide+0.140
lee+0.140
Neg logit contributions
 Spot-0.090
 Buddy-0.083
 Zip-0.082
girls-0.082
 Fl-0.081
Token his
Token ID465
Feature activation-7.19e-01

Pos logit contributions
 canvas+0.058
line+0.057
 product+0.056
 tide+0.055
 harbor+0.054
Neg logit contributions
 Spot-0.029
girls-0.027
 Buddy-0.027
 Zip-0.027
 Max-0.026
Token fingers
Token ID9353
Feature activation-2.30e+00

Pos logit contributions
 canvas+0.019
 product+0.018
line+0.018
 tide+0.018
lee+0.017
Neg logit contributions
 Spot-0.029
girls-0.029
 Buddy-0.029
 Zip-0.029
 Wh-0.028
Token and
Token ID290
Feature activation-9.14e-01

Pos logit contributions
line+0.075
 canvas+0.074
 product+0.072
 tide+0.070
lee+0.068
Neg logit contributions
 Spot-0.080
girls-0.079
 Zip-0.078
 Buddy-0.078
oof-0.077
Token think
Token ID892
Feature activation-1.97e+00

Pos logit contributions
 canvas+0.032
line+0.031
 product+0.031
 tide+0.030
lee+0.029
Neg logit contributions
 Spot-0.029
girls-0.029
 Buddy-0.028
 Zip-0.028
uddy-0.028
Token,
Token ID11
Feature activation+3.27e-01

Pos logit contributions
oof+0.047
girls+0.046
 Wh+0.046
uddy+0.046
 Spot+0.045
Neg logit contributions
 canvas-0.046
 product-0.046
line-0.045
 tide-0.043
 harbor-0.042
Token and
Token ID290
Feature activation+2.28e-01

Pos logit contributions
girls+0.010
uddy+0.010
oof+0.010
 Bones+0.009
 Monkey+0.009
Neg logit contributions
line-0.012
 canvas-0.012
 harbor-0.012
 product-0.012
 tide-0.011
Token enjoyed
Token ID8359
Feature activation-1.77e-01

Pos logit contributions
oof+0.008
uddy+0.008
girls+0.008
 Johnson+0.007
 Wh+0.007
Neg logit contributions
line-0.007
lee-0.007
 canvas-0.007
 product-0.007
 harbor-0.007
Token the
Token ID262
Feature activation+2.69e-01

Pos logit contributions
line+0.006
 product+0.006
 canvas+0.006
 tide+0.006
 harbor+0.006
Neg logit contributions
uddy-0.006
girls-0.006
oof-0.005
 Buddy-0.005
 Spot-0.005
Token refresh
Token ID14976
Feature activation-7.01e-01

Pos logit contributions
girls+0.010
 Spot+0.010
 Wh+0.009
uddy+0.009
 Zip+0.009
Neg logit contributions
 tide-0.009
 canvas-0.008
 harbor-0.008
 product-0.008
line-0.008
Tokenment
Token ID434
Feature activation-3.42e+00

Pos logit contributions
 canvas+0.015
line+0.014
 pulp+0.014
 product+0.013
 tide+0.012
Neg logit contributions
 Spot-0.030
 ever-0.030
girls-0.030
 Zip-0.029
 Bob-0.028
Token of
Token ID286
Feature activation+9.05e-01

Pos logit contributions
line+0.129
 canvas+0.127
 product+0.123
 tide+0.121
lee+0.116
Neg logit contributions
girls-0.101
oof-0.100
 Wh-0.100
 Spot-0.099
 Buddy-0.098
Token the
Token ID262
Feature activation-6.86e-02

Pos logit contributions
uddy+0.034
ver+0.032
girls+0.031
oof+0.030
 Monkey+0.029
Neg logit contributions
 tide-0.030
 canvas-0.029
 product-0.028
 harbor-0.028
 pumpkin-0.028
Token cool
Token ID3608
Feature activation-1.01e+00

Pos logit contributions
 tide+0.002
 canvas+0.002
 harbor+0.002
 product+0.002
 shell+0.002
Neg logit contributions
girls-0.003
 Spot-0.003
 Wh-0.003
uddy-0.003
 Buddy-0.003
Token lake
Token ID13546
Feature activation+9.95e-02

Pos logit contributions
 canvas+0.031
line+0.030
 product+0.030
lee+0.028
 tide+0.028
Neg logit contributions
 Spot-0.037
 Buddy-0.036
 Zip-0.035
girls-0.035
 Fl-0.035
Token water
Token ID1660
Feature activation+2.02e-01

Pos logit contributions
girls+0.003
 Spot+0.003
oof+0.003
 Zip+0.003
 Wh+0.003
Neg logit contributions
line-0.004
 product-0.004
 canvas-0.004
 tide-0.003
 harbor-0.003
Token run
Token ID1057
Feature activation-9.47e-01

Pos logit contributions
 canvas+0.019
line+0.019
 product+0.018
 tide+0.018
 harbor+0.018
Neg logit contributions
 Spot-0.020
girls-0.019
 Buddy-0.019
 Zip-0.019
uddy-0.019
Token through
Token ID832
Feature activation-8.81e-01

Pos logit contributions
 canvas+0.038
 product+0.037
line+0.037
 tide+0.036
lee+0.035
Neg logit contributions
 Spot-0.027
girls-0.026
 Buddy-0.025
 Zip-0.025
 Fl-0.024
Token the
Token ID262
Feature activation-4.35e-01

Pos logit contributions
line+0.043
 canvas+0.041
 product+0.041
 tide+0.041
lee+0.040
Neg logit contributions
 Spot-0.018
 Fl-0.017
 Kitty-0.016
 Buddy-0.016
 Max-0.015
Token tall
Token ID7331
Feature activation-2.06e+00

Pos logit contributions
line+0.013
 canvas+0.013
 product+0.013
 complexion+0.012
lee+0.012
Neg logit contributions
 Spot-0.016
girls-0.016
 Buddy-0.015
 Max-0.015
 Fl-0.015
Token st
Token ID336
Feature activation-1.66e+00

Pos logit contributions
 canvas+0.066
line+0.066
 product+0.066
 tide+0.063
rys+0.063
Neg logit contributions
 Spot-0.068
girls-0.067
 Buddy-0.061
 Fl-0.061
 Max-0.061
Tokenalks
Token ID23833
Feature activation-3.40e+00

Pos logit contributions
 canvas+0.044
 tide+0.042
 product+0.041
 pulp+0.038
 pumpkin+0.037
Neg logit contributions
girls-0.069
uddy-0.066
 Spot-0.064
oof-0.063
 Wh-0.062
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
 canvas+0.133
 product+0.131
 tide+0.128
line+0.126
lee+0.124
Neg logit contributions
 Spot-0.093
girls-0.091
 Buddy-0.088
 Zip-0.087
 Max-0.086
Token
Token ID198
Feature activation-5.77e-01

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.017
 tide+0.017
lee+0.017
Neg logit contributions
girls-0.011
 Spot-0.010
 Zip-0.010
 Buddy-0.010
oof-0.009
Token
Token ID198
Feature activation-7.82e-01

Pos logit contributions
 canvas+0.024
line+0.024
 product+0.024
 tide+0.023
lee+0.023
Neg logit contributions
girls-0.014
 Spot-0.013
 Buddy-0.013
 Zip-0.013
 Wh-0.012
TokenOne
Token ID3198
Feature activation+5.14e-01

Pos logit contributions
 canvas+0.035
line+0.034
 product+0.034
 tide+0.033
 harbor+0.033
Neg logit contributions
girls-0.018
 Spot-0.018
 Buddy-0.017
 Zip-0.017
 Fl-0.016
Token day
Token ID1110
Feature activation-5.00e-01

Pos logit contributions
 Spot+0.012
 Buddy+0.011
 Zip+0.010
 Fl+0.010
 Kitty+0.010
Neg logit contributions
 canvas-0.024
line-0.023
 product-0.023
lee-0.023
 tide-0.022
Token slide
Token ID10649
Feature activation-3.67e-01

Pos logit contributions
 canvas+0.006
line+0.005
 tide+0.005
 product+0.005
 shell+0.005
Neg logit contributions
 Spot-0.010
girls-0.010
 Zip-0.010
 Buddy-0.010
uddy-0.009
Token and
Token ID290
Feature activation+2.36e-01

Pos logit contributions
line+0.014
 canvas+0.012
 pumpkin+0.011
 tide+0.011
 product+0.011
Neg logit contributions
oof-0.013
girls-0.013
 Buddy-0.012
 Enjoy-0.012
 Kitty-0.012
Token looked
Token ID3114
Feature activation-1.31e+00

Pos logit contributions
 Spot+0.008
girls+0.007
 Buddy+0.007
 Zip+0.007
 Max+0.007
Neg logit contributions
 canvas-0.008
line-0.008
 product-0.008
 tide-0.008
lee-0.008
Token through
Token ID832
Feature activation-5.77e-01

Pos logit contributions
 canvas+0.060
 product+0.059
line+0.058
 tide+0.057
 harbor+0.055
Neg logit contributions
 Spot-0.030
 Max-0.027
 Buddy-0.026
 Fl-0.026
girls-0.026
Token the
Token ID262
Feature activation-4.42e-01

Pos logit contributions
 canvas+0.022
 product+0.022
line+0.021
 tide+0.021
lee+0.021
Neg logit contributions
 Spot-0.017
girls-0.017
 Buddy-0.016
 Zip-0.016
uddy-0.016
Token ey
Token ID1926
Feature activation-3.38e+00

Pos logit contributions
line+0.011
 product+0.011
 canvas+0.010
lee+0.010
 tide+0.010
Neg logit contributions
 Spot-0.018
 Max-0.017
 Fl-0.017
girls-0.017
 Buddy-0.017
Tokenep
Token ID538
Feature activation-8.23e-01

Pos logit contributions
 canvas+0.114
 harbor+0.110
line+0.109
 tide+0.108
 product+0.105
Neg logit contributions
 Zip-0.107
 Spot-0.107
girls-0.104
oof-0.103
 Buddy-0.102
Tokeniece
Token ID8535
Feature activation-3.54e+00

Pos logit contributions
line+0.023
 canvas+0.020
 product+0.020
 tide+0.019
lee+0.019
Neg logit contributions
 Buddy-0.035
 Spot-0.034
oof-0.034
girls-0.034
 Kitty-0.034
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
 canvas+0.127
line+0.125
 product+0.123
 tide+0.121
lee+0.117
Neg logit contributions
 Spot-0.111
girls-0.108
 Buddy-0.107
 Zip-0.105
 Wh-0.103
Token He
Token ID679
Feature activation-6.44e-01

Pos logit contributions
girls+0.001
oof+0.001
 Monkey+0.001
uddy+0.001
 Buddy+0.001
Neg logit contributions
line-0.001
 canvas-0.001
 tide-0.001
lee-0.001
 product-0.001
Token saw
Token ID2497
Feature activation-4.27e-01

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.018
 tide+0.017
lee+0.017
Neg logit contributions
girls-0.024
 Buddy-0.024
 Spot-0.024
uddy-0.024
oof-0.024
Token rub
Token ID6437
Feature activation+3.36e-01

Pos logit contributions
 canvas+0.015
line+0.015
 product+0.015
 tide+0.015
 shell+0.014
Neg logit contributions
uddy-0.016
girls-0.016
 Zip-0.016
oof-0.016
 Spot-0.016
Token the
Token ID262
Feature activation-7.55e-01

Pos logit contributions
girls+0.011
uddy+0.010
 Zip+0.010
oof+0.010
 Spot+0.010
Neg logit contributions
line-0.012
 canvas-0.011
 product-0.011
 tide-0.011
lee-0.011
Token magical
Token ID10883
Feature activation-1.11e+00

Pos logit contributions
 canvas+0.020
 tide+0.019
line+0.018
 product+0.018
 harbor+0.018
Neg logit contributions
 Spot-0.032
girls-0.031
 Zip-0.031
 Buddy-0.031
uddy-0.031
Token o
Token ID267
Feature activation-6.23e-01

Pos logit contributions
 canvas+0.032
line+0.031
 product+0.031
 tide+0.030
lee+0.029
Neg logit contributions
 Spot-0.043
girls-0.042
 Buddy-0.041
 Zip-0.041
 Max-0.040
Tokenint
Token ID600
Feature activation+5.93e-03

Pos logit contributions
 canvas+0.014
 product+0.013
line+0.013
 tide+0.013
lee+0.012
Neg logit contributions
girls-0.027
 Spot-0.027
 Buddy-0.026
 Zip-0.026
 Fl-0.026
Tokenment
Token ID434
Feature activation-3.38e+00

Pos logit contributions
 Spot+0.000
girls+0.000
 Buddy+0.000
 Zip+0.000
 Max+0.000
Neg logit contributions
line-0.000
 canvas-0.000
 product-0.000
 tide-0.000
lee-0.000
Token on
Token ID319
Feature activation+4.14e-02

Pos logit contributions
 canvas+0.114
line+0.112
 tide+0.106
 product+0.105
 shell+0.099
Neg logit contributions
 Buddy-0.117
girls-0.117
oof-0.117
 Zip-0.117
 Spot-0.117
Token her
Token ID607
Feature activation-2.39e-01

Pos logit contributions
girls+0.001
uddy+0.001
oof+0.001
ver+0.001
 Zip+0.001
Neg logit contributions
 canvas-0.001
 product-0.001
 tide-0.001
line-0.001
lee-0.001
Token forehead
Token ID22645
Feature activation+1.22e-02

Pos logit contributions
 canvas+0.006
line+0.006
 product+0.006
 tide+0.006
lee+0.006
Neg logit contributions
 Spot-0.010
girls-0.010
 Buddy-0.009
 Zip-0.009
 Max-0.009
Token.
Token ID13
Feature activation-2.21e-01

Pos logit contributions
girls+0.000
 Spot+0.000
 Zip+0.000
 Buddy+0.000
oof+0.000
Neg logit contributions
line-0.000
 canvas-0.000
 product-0.000
 tide-0.000
lee-0.000
Token She
Token ID1375
Feature activation-7.37e-01

Pos logit contributions
lee+0.007
line+0.007
 canvas+0.007
 product+0.007
 harbor+0.007
Neg logit contributions
girls-0.007
 losers-0.007
oof-0.006
 ever-0.006
Deal-0.006
Token by
Token ID416
Feature activation-1.75e-01

Pos logit contributions
uddy+0.004
girls+0.004
 Johnson+0.003
 Zip+0.003
isk+0.003
Neg logit contributions
 canvas-0.004
 product-0.004
 shell-0.004
line-0.004
lee-0.004
Token singing
Token ID13777
Feature activation+4.13e-01

Pos logit contributions
 canvas+0.006
line+0.006
 product+0.006
 tide+0.006
lee+0.005
Neg logit contributions
girls-0.006
uddy-0.006
 Spot-0.006
 Buddy-0.006
 Zip-0.006
Token with
Token ID351
Feature activation+2.16e-01

Pos logit contributions
uddy+0.014
 Johnson+0.014
girls+0.013
 Wh+0.013
 Kenny+0.013
Neg logit contributions
 canvas-0.015
line-0.014
 tide-0.013
 product-0.013
 harbor-0.013
Token others
Token ID1854
Feature activation-1.13e+00

Pos logit contributions
uddy+0.008
girls+0.008
ver+0.007
Deal+0.007
 Johnson+0.007
Neg logit contributions
 canvas-0.007
lee-0.006
 tide-0.006
 shell-0.006
 product-0.006
Token and
Token ID290
Feature activation-7.78e-01

Pos logit contributions
 canvas+0.041
line+0.040
 product+0.038
 tide+0.036
 shell+0.036
Neg logit contributions
 Wh-0.035
uddy-0.035
girls-0.035
 Zip-0.035
oof-0.034
Token getting
Token ID1972
Feature activation-3.36e+00

Pos logit contributions
 canvas+0.029
 product+0.027
line+0.027
 tide+0.026
 harbor+0.026
Neg logit contributions
uddy-0.024
 Spot-0.024
girls-0.023
 Zip-0.023
oof-0.023
Token feedback
Token ID7538
Feature activation-5.05e-01

Pos logit contributions
 canvas+0.141
line+0.137
 product+0.137
 tide+0.136
lee+0.133
Neg logit contributions
 Spot-0.085
uddy-0.085
girls-0.084
 Buddy-0.083
 Zip-0.083
Token.
Token ID13
Feature activation-2.44e-01

Pos logit contributions
 canvas+0.017
line+0.017
 product+0.017
 tide+0.016
 harbor+0.015
Neg logit contributions
 Spot-0.017
 Buddy-0.017
girls-0.016
 Wh-0.016
 Zip-0.016
Token You
Token ID921
Feature activation-5.86e-01

Pos logit contributions
 canvas+0.009
line+0.009
rys+0.008
lee+0.008
 tide+0.008
Neg logit contributions
girls-0.006
uddy-0.006
isk-0.006
 Buddy-0.006
 Johnson-0.006
Token can
Token ID460
Feature activation+3.13e-01

Pos logit contributions
 canvas+0.024
line+0.022
 harbor+0.022
 tide+0.021
 product+0.021
Neg logit contributions
 Johnson-0.016
 Spot-0.016
uddy-0.016
girls-0.015
oof-0.015
Token improve
Token ID2987
Feature activation+1.19e-01

Pos logit contributions
 Spot+0.009
girls+0.009
 Buddy+0.009
 Zip+0.009
uddy+0.009
Neg logit contributions
 canvas-0.012
line-0.012
 product-0.011
 tide-0.011
 harbor-0.011
Token you
Token ID345
Feature activation-7.13e-01

Pos logit contributions
 canvas+0.013
 product+0.012
line+0.012
 tide+0.012
 shell+0.011
Neg logit contributions
uddy-0.015
girls-0.015
 Zip-0.014
oof-0.014
 Johnson-0.014
Token from
Token ID422
Feature activation-1.12e+00

Pos logit contributions
line+0.023
 canvas+0.023
 product+0.022
 tide+0.021
 shell+0.021
Neg logit contributions
uddy-0.025
 Zip-0.024
 Spot-0.024
girls-0.024
oof-0.024
Token losing
Token ID6078
Feature activation-3.45e-01

Pos logit contributions
 canvas+0.038
 product+0.037
line+0.037
 tide+0.037
 harbor+0.036
Neg logit contributions
uddy-0.040
girls-0.037
 Zip-0.036
oof-0.035
 Buddy-0.035
Token out
Token ID503
Feature activation-6.17e-03

Pos logit contributions
 canvas+0.011
 product+0.011
line+0.011
 tide+0.011
 shell+0.010
Neg logit contributions
uddy-0.012
girls-0.012
 Zip-0.011
 Spot-0.011
oof-0.011
Token or
Token ID393
Feature activation-4.82e-01

Pos logit contributions
 canvas+0.000
 product+0.000
line+0.000
 tide+0.000
lee+0.000
Neg logit contributions
girls-0.000
uddy-0.000
oof-0.000
 Zip-0.000
 Spot-0.000
Token getting
Token ID1972
Feature activation-3.36e+00

Pos logit contributions
 canvas+0.017
line+0.017
 product+0.016
 tide+0.016
 harbor+0.016
Neg logit contributions
uddy-0.015
girls-0.015
 Zip-0.015
oof-0.015
 Spot-0.015
Token into
Token ID656
Feature activation-1.07e+00

Pos logit contributions
 canvas+0.128
line+0.125
 tide+0.125
 product+0.125
lee+0.120
Neg logit contributions
uddy-0.098
girls-0.096
 Zip-0.096
 Spot-0.093
oof-0.093
Token trouble
Token ID5876
Feature activation-9.73e-01

Pos logit contributions
 canvas+0.038
 product+0.038
 tide+0.036
line+0.036
 harbor+0.035
Neg logit contributions
uddy-0.035
girls-0.035
 Zip-0.034
 Spot-0.033
 Buddy-0.033
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
line+0.029
 product+0.028
 canvas+0.028
 tide+0.026
 harbor+0.026
Neg logit contributions
oof-0.036
 Zip-0.036
uddy-0.036
 Spot-0.036
girls-0.035
Token<|endoftext|>
Token ID50256
Feature activation+8.40e-02

Pos logit contributions
line+0.010
 product+0.010
 canvas+0.010
lee+0.009
rys+0.009
Neg logit contributions
girls-0.008
 Spot-0.007
 Buddy-0.007
uddy-0.007
 Zip-0.007
TokenOnce
Token ID7454
Feature activation-7.94e-01

Pos logit contributions
oof+0.003
girls+0.003
 losers+0.003
Deal+0.003
uddy+0.003
Neg logit contributions
line-0.002
 tide-0.002
 product-0.002
 harbor-0.002
 cliff-0.002
Token flexible
Token ID12846
Feature activation-2.31e-01

Pos logit contributions
 canvas+0.054
 product+0.053
line+0.051
lee+0.050
 tide+0.050
Neg logit contributions
 Spot-0.047
girls-0.047
uddy-0.046
 Zip-0.046
 Buddy-0.046
Token to
Token ID284
Feature activation+7.81e-02

Pos logit contributions
 canvas+0.007
line+0.007
 product+0.007
 tide+0.006
 shell+0.006
Neg logit contributions
 Zip-0.008
oof-0.008
uddy-0.008
girls-0.008
 Spot-0.008
Token hold
Token ID1745
Feature activation-8.76e-01

Pos logit contributions
girls+0.003
uddy+0.003
 Spot+0.003
oof+0.002
 Johnson+0.002
Neg logit contributions
 canvas-0.003
line-0.002
 product-0.002
 tide-0.002
 shell-0.002
Token onto
Token ID4291
Feature activation-1.29e-01

Pos logit contributions
 canvas+0.029
line+0.028
 shell+0.028
 product+0.027
 tide+0.027
Neg logit contributions
girls-0.029
isk-0.029
uddy-0.028
 Monkey-0.028
Deal-0.028
Token the
Token ID262
Feature activation-7.83e-01

Pos logit contributions
 canvas+0.004
 product+0.004
 tide+0.004
line+0.004
 pumpkin+0.004
Neg logit contributions
uddy-0.005
girls-0.005
oof-0.004
Deal-0.004
ver-0.004
Token palm
Token ID18057
Feature activation-3.34e+00

Pos logit contributions
 canvas+0.023
 tide+0.021
 pumpkin+0.020
 shell+0.019
 pulp+0.019
Neg logit contributions
girls-0.034
oof-0.032
uddy-0.032
 Spot-0.032
 Buddy-0.032
Token branches
Token ID13737
Feature activation-1.14e+00

Pos logit contributions
 canvas+0.125
 product+0.122
line+0.122
 tide+0.119
lee+0.116
Neg logit contributions
 Spot-0.099
girls-0.095
 Buddy-0.095
 Zip-0.094
 Fl-0.091
Token."
Token ID526
Feature activation-2.17e-01

Pos logit contributions
line+0.040
 canvas+0.038
 product+0.035
 tide+0.035
 harbor+0.034
Neg logit contributions
girls-0.039
oof-0.038
 Spot-0.038
 Zip-0.038
 Buddy-0.037
Token
Token ID198
Feature activation-5.58e-01

Pos logit contributions
line+0.008
lee+0.008
 canvas+0.008
 product+0.007
 tide+0.007
Neg logit contributions
girls-0.006
oof-0.006
uddy-0.006
ver-0.006
isk-0.005
Token
Token ID198
Feature activation-5.36e-01

Pos logit contributions
line+0.018
lee+0.018
 product+0.018
 canvas+0.018
 tide+0.017
Neg logit contributions
girls-0.017
 Monkey-0.015
 losers-0.015
 Johnson-0.015
 Spot-0.015
TokenTim
Token ID14967
Feature activation+3.24e-01

Pos logit contributions
 canvas+0.016
 product+0.016
line+0.016
 tide+0.016
 harbor+0.015
Neg logit contributions
girls-0.018
 Spot-0.018
 Johnson-0.017
 Buddy-0.017
 Fl-0.017
Token the
Token ID262
Feature activation-4.08e-01

Pos logit contributions
 canvas+0.029
 product+0.029
 tide+0.029
 pumpkin+0.028
 shell+0.028
Neg logit contributions
uddy-0.039
girls-0.037
ver-0.036
Deal-0.036
ll-0.036
Token hook
Token ID8011
Feature activation-8.75e-01

Pos logit contributions
 product+0.011
 canvas+0.011
line+0.011
lee+0.011
rys+0.010
Neg logit contributions
 Spot-0.016
girls-0.016
 Buddy-0.015
 Fl-0.015
 Zip-0.015
Token and
Token ID290
Feature activation-2.28e-01

Pos logit contributions
line+0.029
 canvas+0.029
 product+0.027
 tide+0.027
 shell+0.026
Neg logit contributions
 Spot-0.030
girls-0.030
 Buddy-0.029
 Zip-0.029
 Wh-0.029
Token throw
Token ID3714
Feature activation-9.32e-01

Pos logit contributions
 canvas+0.007
line+0.007
 tide+0.007
 product+0.007
 shell+0.007
Neg logit contributions
girls-0.008
 Spot-0.008
uddy-0.008
 Buddy-0.008
 Zip-0.008
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
 canvas+0.031
 tide+0.031
 shell+0.030
line+0.030
 product+0.030
Neg logit contributions
uddy-0.031
girls-0.030
 Buddy-0.029
 Spot-0.029
 Johnson-0.029
Token line
Token ID1627
Feature activation-3.32e+00

Pos logit contributions
 canvas+0.030
line+0.029
 product+0.029
 tide+0.027
lee+0.027
Neg logit contributions
 Spot-0.044
girls-0.043
 Buddy-0.042
 Zip-0.042
 Fl-0.041
Token in
Token ID287
Feature activation-9.85e-01

Pos logit contributions
 canvas+0.132
line+0.129
 product+0.129
 tide+0.126
lee+0.123
Neg logit contributions
 Spot-0.091
girls-0.088
 Buddy-0.086
 Zip-0.086
 Max-0.083
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
 canvas+0.030
 product+0.030
 tide+0.029
 shell+0.029
line+0.028
Neg logit contributions
uddy-0.038
girls-0.037
Deal-0.036
oof-0.036
ver-0.035
Token water
Token ID1660
Feature activation-5.41e-01

Pos logit contributions
line+0.026
 product+0.025
 canvas+0.025
lee+0.024
 complexion+0.023
Neg logit contributions
 Spot-0.026
 Fl-0.024
girls-0.024
 Max-0.024
 Buddy-0.024
Token.
Token ID13
Feature activation+1.64e-01

Pos logit contributions
 canvas+0.021
 product+0.020
line+0.020
 tide+0.020
lee+0.019
Neg logit contributions
 Spot-0.016
girls-0.015
 Buddy-0.015
 Fl-0.014
 Zip-0.014
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
 Spot+0.004
 Max+0.003
 Fl+0.003
 Buddy+0.003
 Tim+0.003
Neg logit contributions
 canvas-0.008
 product-0.008
line-0.008
 harbor-0.007
rys-0.007
Token rough
Token ID5210
Feature activation-6.90e-01

Pos logit contributions
 canvas+0.029
 product+0.029
line+0.027
 harbor+0.027
rys+0.027
Neg logit contributions
 Spot-0.016
 Tim-0.015
 ever-0.014
 Max-0.014
 Buddy-0.014
Token it
Token ID340
Feature activation+6.94e-01

Pos logit contributions
 canvas+0.025
line+0.025
 tide+0.024
 product+0.024
lee+0.023
Neg logit contributions
girls-0.021
 Spot-0.020
uddy-0.020
 Buddy-0.020
oof-0.020
Token was
Token ID373
Feature activation+4.55e-01

Pos logit contributions
 Spot+0.020
girls+0.019
 Buddy+0.019
 Zip+0.019
 Fl+0.019
Neg logit contributions
 canvas-0.027
line-0.026
 product-0.026
 tide-0.025
lee-0.025
Token with
Token ID351
Feature activation+1.34e-01

Pos logit contributions
girls+0.015
 Spot+0.015
 Zip+0.014
 Buddy+0.014
oof+0.014
Neg logit contributions
 canvas-0.016
line-0.016
 product-0.015
 tide-0.015
 shell-0.014
Token his
Token ID465
Feature activation-7.27e-01

Pos logit contributions
girls+0.005
uddy+0.005
Deal+0.004
 Monkey+0.004
 Johnson+0.004
Neg logit contributions
 canvas-0.005
 tide-0.004
lee-0.004
 shell-0.004
 product-0.004
Token palm
Token ID18057
Feature activation-3.32e+00

Pos logit contributions
 canvas+0.022
 product+0.021
line+0.021
 tide+0.021
 shell+0.020
Neg logit contributions
girls-0.027
 Spot-0.027
 Zip-0.026
 Buddy-0.026
 Monkey-0.026
Token.
Token ID13
Feature activation-5.32e-02

Pos logit contributions
line+0.131
 product+0.129
 canvas+0.129
 harbor+0.127
 tide+0.126
Neg logit contributions
 Spot-0.091
 Buddy-0.086
 Zip-0.085
 Fl-0.084
 Max-0.083
Token
Token ID220
Feature activation+1.65e-01

Pos logit contributions
line+0.002
 canvas+0.002
 product+0.002
 tide+0.002
lee+0.002
Neg logit contributions
girls-0.001
 Spot-0.001
 Zip-0.001
 Buddy-0.001
oof-0.001
Token
Token ID198
Feature activation-4.18e-01

Pos logit contributions
girls+0.004
 Spot+0.004
 Monkey+0.004
 Buddy+0.004
 Zip+0.004
Neg logit contributions
line-0.007
 canvas-0.006
 product-0.006
lee-0.006
 tide-0.006
Token
Token ID198
Feature activation-5.44e-01

Pos logit contributions
line+0.016
 product+0.015
 canvas+0.015
lee+0.014
 tide+0.014
Neg logit contributions
girls-0.012
 Spot-0.011
oof-0.011
 Buddy-0.011
 Monkey-0.011
TokenTim
Token ID14967
Feature activation+3.99e-01

Pos logit contributions
 canvas+0.027
 product+0.026
line+0.026
 tide+0.026
lee+0.026
Neg logit contributions
 Spot-0.010
 Buddy-0.010
 Zip-0.009
 Wh-0.009
girls-0.009
Token water
Token ID1660
Feature activation+1.05e-01

Pos logit contributions
 canvas+0.002
 product+0.002
line+0.002
lee+0.002
 pulp+0.002
Neg logit contributions
 Spot-0.002
 Fl-0.002
 Buddy-0.002
 Max-0.002
girls-0.002
Token and
Token ID290
Feature activation-6.65e-01

Pos logit contributions
girls+0.003
 Spot+0.003
 Buddy+0.003
 Zip+0.003
uddy+0.003
Neg logit contributions
line-0.004
 canvas-0.004
 tide-0.004
 product-0.004
 harbor-0.004
Token feel
Token ID1254
Feature activation-1.56e+00

Pos logit contributions
 canvas+0.022
line+0.022
 tide+0.021
 product+0.021
 harbor+0.020
Neg logit contributions
 Spot-0.022
girls-0.022
 Buddy-0.021
 Zip-0.021
uddy-0.021
Token the
Token ID262
Feature activation-1.19e+00

Pos logit contributions
 canvas+0.078
 product+0.076
 pulp+0.071
lee+0.070
line+0.069
Neg logit contributions
 Spot-0.035
 Fl-0.034
 Buddy-0.030
 Max-0.029
 love-0.029
Token cool
Token ID3608
Feature activation-1.92e+00

Pos logit contributions
 canvas+0.034
 product+0.033
line+0.033
lee+0.031
 tide+0.030
Neg logit contributions
 Spot-0.047
girls-0.045
 Buddy-0.045
 Fl-0.044
 Zip-0.044
Tokenness
Token ID1108
Feature activation-3.32e+00

Pos logit contributions
 canvas+0.058
 product+0.055
line+0.053
lee+0.052
 pulp+0.050
Neg logit contributions
 Spot-0.074
 Fl-0.070
 Buddy-0.069
 Max-0.068
 Zip-0.068
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
 canvas+0.151
 product+0.149
lee+0.148
 harbor+0.145
 pulp+0.143
Neg logit contributions
 Spot-0.070
 ever-0.066
 Fl-0.065
 Max-0.061
 Buddy-0.060
Token
Token ID198
Feature activation-5.81e-01

Pos logit contributions
 canvas+0.016
line+0.015
lee+0.015
 tide+0.015
 product+0.014
Neg logit contributions
girls-0.012
 Spot-0.010
 losers-0.010
 Buddy-0.010
 Monkey-0.010
Token
Token ID198
Feature activation-7.46e-01

Pos logit contributions
line+0.023
 canvas+0.023
 product+0.023
 tide+0.022
lee+0.022
Neg logit contributions
girls-0.015
 Spot-0.014
 Buddy-0.014
 Wh-0.014
 Monkey-0.014
TokenOne
Token ID3198
Feature activation+4.51e-01

Pos logit contributions
 canvas+0.034
line+0.034
 product+0.034
 tide+0.033
lee+0.032
Neg logit contributions
 Spot-0.016
girls-0.015
 Buddy-0.015
 Zip-0.015
 Max-0.014
Token day
Token ID1110
Feature activation-5.02e-01

Pos logit contributions
 Spot+0.010
 Buddy+0.010
 Zip+0.009
 Fl+0.009
 Max+0.009
Neg logit contributions
 canvas-0.021
line-0.020
 product-0.020
lee-0.020
 pulp-0.019
Token oy
Token ID35104
Feature activation-1.02e+00

Pos logit contributions
 canvas+0.035
 product+0.034
line+0.033
 tide+0.033
 harbor+0.031
Neg logit contributions
uddy-0.032
girls-0.031
 Zip-0.030
 Buddy-0.029
oof-0.029
Tokensters
Token ID5937
Feature activation+1.82e-02

Pos logit contributions
 canvas+0.020
 product+0.017
 tide+0.016
lee+0.016
rys+0.016
Neg logit contributions
girls-0.050
 Spot-0.047
 Monkey-0.046
 Wh-0.045
 just-0.045
Token and
Token ID290
Feature activation-8.55e-01

Pos logit contributions
 Spot+0.001
 Zip+0.001
girls+0.001
 Buddy+0.001
uddy+0.000
Neg logit contributions
line-0.001
 canvas-0.001
 product-0.001
 tide-0.001
 harbor-0.001
Token ended
Token ID4444
Feature activation-1.08e+00

Pos logit contributions
 canvas+0.030
 product+0.029
line+0.029
 tide+0.028
 shell+0.027
Neg logit contributions
girls-0.028
uddy-0.028
 Zip-0.027
oof-0.027
 Spot-0.027
Token up
Token ID510
Feature activation-4.53e-01

Pos logit contributions
 canvas+0.044
 product+0.043
line+0.043
 tide+0.042
lee+0.041
Neg logit contributions
 Spot-0.029
girls-0.028
 Buddy-0.028
 Zip-0.028
uddy-0.027
Token getting
Token ID1972
Feature activation-3.31e+00

Pos logit contributions
 canvas+0.017
line+0.017
 product+0.017
 tide+0.017
lee+0.016
Neg logit contributions
 Spot-0.013
girls-0.013
 Buddy-0.013
 Zip-0.012
 Max-0.012
Token sick
Token ID6639
Feature activation-1.24e+00

Pos logit contributions
 canvas+0.127
line+0.124
 product+0.124
 tide+0.121
lee+0.118
Neg logit contributions
 Spot-0.095
girls-0.092
 Buddy-0.090
 Zip-0.089
 Fl-0.087
Token from
Token ID422
Feature activation-8.37e-01

Pos logit contributions
 canvas+0.042
line+0.042
 product+0.041
 tide+0.040
lee+0.038
Neg logit contributions
 Spot-0.040
girls-0.040
 Zip-0.040
 Buddy-0.040
oof-0.039
Token eating
Token ID6600
Feature activation-8.32e-01

Pos logit contributions
 canvas+0.030
 product+0.030
 tide+0.029
line+0.029
 harbor+0.028
Neg logit contributions
uddy-0.027
girls-0.026
 Zip-0.025
oof-0.025
 Spot-0.025
Token them
Token ID606
Feature activation-5.68e-01

Pos logit contributions
 canvas+0.030
line+0.029
 product+0.029
 tide+0.029
 harbor+0.027
Neg logit contributions
 Spot-0.026
girls-0.026
 Zip-0.025
 Buddy-0.025
uddy-0.025
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
 product+0.017
 canvas+0.017
line+0.016
 tide+0.015
 pumpkin+0.015
Neg logit contributions
 Zip-0.022
girls-0.021
uddy-0.021
oof-0.021
 Spot-0.021
Token to
Token ID284
Feature activation-8.09e-01

Pos logit contributions
 canvas+0.009
 product+0.009
line+0.009
lee+0.009
 tide+0.009
Neg logit contributions
oof-0.010
uddy-0.010
girls-0.009
 Buddy-0.009
 Wh-0.009
Token 10
Token ID838
Feature activation-9.34e-01

Pos logit contributions
 canvas+0.028
line+0.026
 product+0.026
 tide+0.025
 shell+0.023
Neg logit contributions
uddy-0.029
girls-0.028
oof-0.027
 Spot-0.027
 Buddy-0.027
Token out
Token ID503
Feature activation+6.34e-02

Pos logit contributions
 canvas+0.032
 product+0.032
line+0.031
 tide+0.029
lee+0.029
Neg logit contributions
 Spot-0.030
 Buddy-0.030
girls-0.030
oof-0.030
uddy-0.030
Token loud
Token ID7812
Feature activation-8.22e-01

Pos logit contributions
 Spot+0.002
girls+0.002
oof+0.002
 Buddy+0.002
uddy+0.002
Neg logit contributions
 canvas-0.002
 product-0.002
lee-0.002
line-0.002
 tide-0.002
Token and
Token ID290
Feature activation-5.05e-01

Pos logit contributions
 canvas+0.029
 product+0.028
line+0.028
 tide+0.027
lee+0.027
Neg logit contributions
 Spot-0.026
girls-0.026
 Buddy-0.025
oof-0.025
uddy-0.025
Token getting
Token ID1972
Feature activation-3.29e+00

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.017
 tide+0.017
lee+0.016
Neg logit contributions
oof-0.017
uddy-0.016
girls-0.016
 Buddy-0.015
 Johnson-0.015
Token ready
Token ID3492
Feature activation-6.54e-01

Pos logit contributions
 canvas+0.116
 tide+0.114
line+0.114
 product+0.114
lee+0.108
Neg logit contributions
uddy-0.106
oof-0.105
girls-0.100
 Buddy-0.100
 Spot-0.099
Token to
Token ID284
Feature activation-3.72e-01

Pos logit contributions
 canvas+0.028
line+0.028
 product+0.028
 tide+0.027
lee+0.026
Neg logit contributions
girls-0.016
oof-0.016
 Spot-0.015
uddy-0.015
 Buddy-0.015
Token freeze
Token ID16611
Feature activation-5.48e-01

Pos logit contributions
 canvas+0.013
 product+0.013
 tide+0.013
line+0.012
 shell+0.012
Neg logit contributions
girls-0.012
uddy-0.012
 Spot-0.011
oof-0.011
 Buddy-0.011
Token.
Token ID13
Feature activation-3.10e-01

Pos logit contributions
 product+0.018
 canvas+0.018
line+0.018
 tide+0.017
lee+0.017
Neg logit contributions
oof-0.018
uddy-0.018
girls-0.018
 Spot-0.017
 Buddy-0.017
Token
Token ID198
Feature activation-4.10e-01

Pos logit contributions
line+0.011
 canvas+0.011
 product+0.010
lee+0.010
 harbor+0.010
Neg logit contributions
girls-0.010
oof-0.009
Deal-0.009
 losers-0.009
isk-0.008
Token sense
Token ID2565
Feature activation-1.01e+00

Pos logit contributions
 Spot+0.022
 Fl+0.021
 Buddy+0.020
 Max+0.020
 Zip+0.020
Neg logit contributions
line-0.031
 canvas-0.030
 product-0.030
lee-0.030
 tide-0.029
Token of
Token ID286
Feature activation+1.19e+00

Pos logit contributions
 canvas+0.044
line+0.043
 product+0.043
 tide+0.042
lee+0.041
Neg logit contributions
 Spot-0.024
girls-0.023
 Buddy-0.023
 Zip-0.023
 Max-0.022
Token joy
Token ID8716
Feature activation-9.46e-01

Pos logit contributions
girls+0.033
 Spot+0.032
 Buddy+0.031
uddy+0.031
 Zip+0.031
Neg logit contributions
 canvas-0.047
 product-0.046
 tide-0.046
line-0.046
lee-0.044
Token and
Token ID290
Feature activation-1.55e-01

Pos logit contributions
 canvas+0.035
line+0.035
 product+0.034
 tide+0.034
lee+0.033
Neg logit contributions
 Spot-0.028
girls-0.027
 Buddy-0.027
 Zip-0.027
 Max-0.026
Token content
Token ID2695
Feature activation-8.98e-01

Pos logit contributions
 canvas+0.005
line+0.005
 product+0.005
 tide+0.005
lee+0.005
Neg logit contributions
girls-0.005
 Spot-0.005
uddy-0.005
 Buddy-0.005
 Zip-0.005
Tokenment
Token ID434
Feature activation-3.29e+00

Pos logit contributions
 canvas+0.031
 product+0.029
line+0.029
 tide+0.029
 pulp+0.028
Neg logit contributions
 Spot-0.030
 Fl-0.028
 Zip-0.027
 Buddy-0.027
 Max-0.027
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
line+0.090
 product+0.082
 canvas+0.079
 tide+0.074
lee+0.074
Neg logit contributions
oof-0.137
uddy-0.134
girls-0.134
 Buddy-0.133
 Zip-0.132
Token After
Token ID2293
Feature activation-1.40e-01

Pos logit contributions
line+0.008
lee+0.008
 canvas+0.008
 product+0.008
 tide+0.008
Neg logit contributions
girls-0.006
oof-0.005
 Spot-0.005
 Buddy-0.005
 Zip-0.005
Token a
Token ID257
Feature activation+1.29e+00

Pos logit contributions
 tide+0.005
line+0.005
 canvas+0.005
 product+0.005
 harbor+0.005
Neg logit contributions
girls-0.004
uddy-0.004
oof-0.004
 Spot-0.004
Deal-0.004
Token few
Token ID1178
Feature activation+3.35e-01

Pos logit contributions
 Spot+0.032
girls+0.030
 Buddy+0.030
 Zip+0.030
 Fl+0.029
Neg logit contributions
 canvas-0.055
line-0.054
 product-0.054
 tide-0.053
lee-0.052
Token moments
Token ID7188
Feature activation-6.92e-02

Pos logit contributions
 Spot+0.011
girls+0.011
 Buddy+0.011
 Zip+0.011
 Wh+0.011
Neg logit contributions
 canvas-0.011
 product-0.011
line-0.011
 tide-0.011
lee-0.010
Token clean
Token ID3424
Feature activation-3.06e-01

Pos logit contributions
 canvas+0.007
line+0.006
 tide+0.006
 product+0.006
 harbor+0.006
Neg logit contributions
girls-0.007
 Spot-0.007
 Zip-0.007
 Buddy-0.006
uddy-0.006
Token up
Token ID510
Feature activation+2.47e-01

Pos logit contributions
 canvas+0.014
line+0.014
 product+0.014
 tide+0.013
 pulp+0.013
Neg logit contributions
 Spot-0.007
 Max-0.006
 Buddy-0.006
 Fl-0.006
 Wh-0.006
Token his
Token ID465
Feature activation-3.81e-01

Pos logit contributions
girls+0.007
 Spot+0.007
 Zip+0.007
 Buddy+0.006
uddy+0.006
Neg logit contributions
 canvas-0.010
 product-0.010
line-0.010
 tide-0.009
lee-0.009
Token toys
Token ID14958
Feature activation+4.83e-01

Pos logit contributions
line+0.016
 canvas+0.015
 pulp+0.014
rys+0.014
lee+0.014
Neg logit contributions
 Spot-0.010
 Max-0.009
 first-0.009
 for-0.009
 Fl-0.009
Token before
Token ID878
Feature activation-7.78e-01

Pos logit contributions
girls+0.014
 Zip+0.014
oof+0.014
uddy+0.014
 Monkey+0.013
Neg logit contributions
line-0.020
 canvas-0.019
 product-0.018
 tide-0.018
 harbor-0.018
Token getting
Token ID1972
Feature activation-3.29e+00

Pos logit contributions
 canvas+0.031
lee+0.031
line+0.031
 product+0.030
rys+0.030
Neg logit contributions
 Spot-0.022
 Max-0.021
 Fl-0.020
 Buddy-0.020
 Wh-0.019
Token out
Token ID503
Feature activation+5.66e-02

Pos logit contributions
 canvas+0.146
line+0.141
 product+0.141
lee+0.136
rys+0.135
Neg logit contributions
 Spot-0.076
 Max-0.071
 Fl-0.068
 Wh-0.068
 Will-0.066
Token of
Token ID286
Feature activation+4.24e-01

Pos logit contributions
 Spot+0.001
 Buddy+0.001
 Max+0.001
 Fl+0.001
 Wh+0.001
Neg logit contributions
 canvas-0.003
line-0.003
 product-0.003
 tide-0.003
 pulp-0.003
Token the
Token ID262
Feature activation-8.87e-01

Pos logit contributions
 Spot+0.012
girls+0.011
 Buddy+0.011
 Zip+0.011
 Max+0.011
Neg logit contributions
 canvas-0.017
line-0.017
 product-0.017
 tide-0.016
lee-0.016
Token tub
Token ID12202
Feature activation-9.13e-01

Pos logit contributions
 canvas+0.031
line+0.031
lee+0.030
 pulp+0.029
 product+0.029
Neg logit contributions
 Spot-0.028
 Fl-0.026
 Max-0.026
 Wh-0.025
 first-0.025
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
 canvas+0.034
line+0.033
 product+0.033
 tide+0.033
lee+0.032
Neg logit contributions
 Spot-0.027
girls-0.026
 Buddy-0.026
 Zip-0.026
 Max-0.025
Token serve
Token ID4691
Feature activation+2.73e-01

Pos logit contributions
 canvas+0.024
 product+0.023
line+0.023
 tide+0.023
 harbor+0.022
Neg logit contributions
 Spot-0.020
girls-0.020
 Zip-0.019
 Buddy-0.019
uddy-0.019
Token a
Token ID257
Feature activation+8.10e-02

Pos logit contributions
uddy+0.010
girls+0.009
 Zip+0.009
 Monkey+0.009
ver+0.009
Neg logit contributions
 canvas-0.009
 product-0.009
 tide-0.009
 pumpkin-0.009
 shell-0.009
Token picnic
Token ID35715
Feature activation+3.91e-01

Pos logit contributions
girls+0.003
 Zip+0.003
 Spot+0.003
oof+0.003
isk+0.003
Neg logit contributions
 canvas-0.003
 pumpkin-0.002
 tide-0.002
 product-0.002
 harbor-0.002
Token to
Token ID284
Feature activation-5.26e-01

Pos logit contributions
 Spot+0.011
girls+0.011
 Buddy+0.011
 Zip+0.010
 Max+0.010
Neg logit contributions
 canvas-0.015
line-0.015
 product-0.015
 tide-0.015
lee-0.014
Token their
Token ID511
Feature activation-2.41e-01

Pos logit contributions
 canvas+0.019
 product+0.018
 tide+0.018
line+0.018
 harbor+0.018
Neg logit contributions
uddy-0.017
girls-0.016
 Zip-0.015
oof-0.015
 Spot-0.015
Token stuffed
Token ID22259
Feature activation+3.26e+00

Pos logit contributions
 harbor+0.007
 tide+0.006
 pumpkin+0.006
 canvas+0.006
 product+0.006
Neg logit contributions
ver-0.010
oof-0.009
uddy-0.009
 Zip-0.009
girls-0.009
Token animals
Token ID4695
Feature activation+1.96e-01

Pos logit contributions
ver+0.118
 OK+0.114
uddy+0.114
Deal+0.107
oof+0.107
Neg logit contributions
 pumpkin-0.105
 harbor-0.104
 shell-0.100
 canvas-0.099
 tide-0.098
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
oof+0.007
 Zip+0.007
 Wh+0.007
 Spot+0.007
uddy+0.007
Neg logit contributions
line-0.006
 canvas-0.006
 harbor-0.006
 product-0.006
 pumpkin-0.005
Token They
Token ID1119
Feature activation-5.33e-01

Pos logit contributions
 canvas+0.018
 product+0.018
line+0.018
 tide+0.018
lee+0.017
Neg logit contributions
 Spot-0.009
girls-0.008
 Buddy-0.008
 Zip-0.008
 Max-0.008
Token put
Token ID1234
Feature activation-1.52e-01

Pos logit contributions
 canvas+0.018
line+0.018
 product+0.018
 tide+0.018
 harbor+0.017
Neg logit contributions
 Spot-0.017
 Zip-0.017
girls-0.017
 Buddy-0.017
oof-0.016
Token some
Token ID617
Feature activation+8.56e-01

Pos logit contributions
 pumpkin+0.005
 canvas+0.005
 tide+0.005
 product+0.005
 pulp+0.005
Neg logit contributions
uddy-0.005
ver-0.005
girls-0.005
ll-0.005
oof-0.005
Token water
Token ID1660
Feature activation+5.14e-01

Pos logit contributions
 Spot+0.012
girls+0.012
uddy+0.012
 Zip+0.012
 Buddy+0.012
Neg logit contributions
 canvas-0.010
 tide-0.010
 product-0.010
line-0.009
 shell-0.009
Token every
Token ID790
Feature activation-7.57e-01

Pos logit contributions
 Spot+0.014
girls+0.014
 Buddy+0.014
 Zip+0.013
uddy+0.013
Neg logit contributions
line-0.020
 canvas-0.020
 product-0.020
 tide-0.020
lee-0.019
Token day
Token ID1110
Feature activation-8.07e-01

Pos logit contributions
 canvas+0.029
 tide+0.029
 product+0.028
 shell+0.028
 pumpkin+0.027
Neg logit contributions
girls-0.023
 Spot-0.022
 Wh-0.021
 Buddy-0.021
 Zip-0.021
Token.
Token ID13
Feature activation-2.06e-01

Pos logit contributions
 canvas+0.027
line+0.027
 product+0.027
 tide+0.026
lee+0.025
Neg logit contributions
 Spot-0.026
girls-0.026
 Buddy-0.026
 Zip-0.026
oof-0.025
Token He
Token ID679
Feature activation-7.30e-01

Pos logit contributions
line+0.009
 canvas+0.009
 tide+0.008
 product+0.008
lee+0.008
Neg logit contributions
girls-0.005
 Buddy-0.005
 Monkey-0.005
uddy-0.005
 Spot-0.005
Token named
Token ID3706
Feature activation+2.89e+00

Pos logit contributions
 canvas+0.027
 product+0.026
 tide+0.026
line+0.026
 shell+0.025
Neg logit contributions
girls-0.021
 Spot-0.021
 Zip-0.021
 Buddy-0.021
uddy-0.020
Token it
Token ID340
Feature activation+1.22e+00

Pos logit contributions
girls+0.083
uddy+0.079
ver+0.077
Deal+0.076
 Johnson+0.075
Neg logit contributions
 canvas-0.109
 tide-0.109
lee-0.108
 shell-0.107
line-0.105
Token Buzz
Token ID15753
Feature activation+2.02e-01

Pos logit contributions
girls+0.034
uddy+0.032
oof+0.032
 Johnson+0.032
 Spot+0.032
Neg logit contributions
 shell-0.045
 tide-0.044
 canvas-0.044
line-0.044
 pumpkin-0.044
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
 Zip+0.006
 Kenny+0.006
 Buddy+0.006
 Spot+0.006
oof+0.006
Neg logit contributions
line-0.007
 product-0.007
 canvas-0.007
 shell-0.007
 harbor-0.007
Token
Token ID198
Feature activation+8.50e-02

Pos logit contributions
atum+0.013
isk+0.013
girls+0.012
oof+0.012
uddy+0.012
Neg logit contributions
 tide-0.012
line-0.012
 pumpkin-0.011
 product-0.011
 harbor-0.011
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
girls+0.003
 Buddy+0.003
 Wh+0.003
 Monkey+0.002
 Spot+0.002
Neg logit contributions
 product-0.003
line-0.003
 tide-0.003
 harbor-0.003
 canvas-0.003
Token same
Token ID976
Feature activation-3.35e-01

Pos logit contributions
ver+0.011
girls+0.011
uddy+0.011
 Kitty+0.010
 Zip+0.010
Neg logit contributions
 shell-0.007
 canvas-0.007
 tide-0.007
 harbor-0.007
 pumpkin-0.006
Token clearing
Token ID17304
Feature activation+1.11e+00

Pos logit contributions
 canvas+0.010
 shell+0.010
 product+0.010
 harbor+0.009
 tide+0.009
Neg logit contributions
girls-0.014
 Zip-0.013
 Spot-0.013
uddy-0.013
 Kitty-0.013
Token,
Token ID11
Feature activation-7.09e-03

Pos logit contributions
girls+0.034
oof+0.033
 Spot+0.032
 Zip+0.032
uddy+0.031
Neg logit contributions
 canvas-0.042
line-0.042
 product-0.041
 tide-0.039
lee-0.039
Token though
Token ID996
Feature activation-3.46e-01

Pos logit contributions
 canvas+0.000
line+0.000
 product+0.000
 tide+0.000
 shell+0.000
Neg logit contributions
girls-0.000
uddy-0.000
oof-0.000
 Zip-0.000
Deal-0.000
Token it
Token ID340
Feature activation+1.42e+00

Pos logit contributions
 canvas+0.010
lee+0.010
 product+0.009
 tide+0.009
 harbor+0.009
Neg logit contributions
girls-0.014
Deal-0.013
oof-0.013
 Enjoy-0.013
 losers-0.012
Token hadn
Token ID8020
Feature activation+3.00e+00

Pos logit contributions
oof+0.051
girls+0.050
 Enjoy+0.050
Deal+0.047
 Spot+0.045
Neg logit contributions
 product-0.044
lee-0.044
 shell-0.043
 canvas-0.041
 tide-0.041
Token't
Token ID470
Feature activation+1.09e+00

Pos logit contributions
Deal+0.085
girls+0.075
oof+0.066
 Enjoy+0.061
 Spot+0.057
Neg logit contributions
line-0.123
 product-0.122
lee-0.121
 canvas-0.118
 tide-0.116
Token looked
Token ID3114
Feature activation+2.72e-01

Pos logit contributions
girls+0.035
 Spot+0.034
oof+0.033
uddy+0.033
 Zip+0.033
Neg logit contributions
 canvas-0.038
 product-0.037
 tide-0.037
line-0.036
lee-0.035
Token as
Token ID355
Feature activation-1.17e-01

Pos logit contributions
girls+0.008
uddy+0.008
oof+0.008
 Zip+0.008
 Buddy+0.008
Neg logit contributions
 canvas-0.010
line-0.010
 product-0.010
 tide-0.010
lee-0.010
Token hurt
Token ID5938
Feature activation+4.80e-01

Pos logit contributions
 tide+0.004
 canvas+0.003
 product+0.003
line+0.003
 shell+0.003
Neg logit contributions
girls-0.005
oof-0.005
uddy-0.004
 Monkey-0.004
 Spot-0.004
Token.
Token ID13
Feature activation-7.05e-01

Pos logit contributions
girls+0.019
Deal+0.019
oof+0.019
uddy+0.018
 Enjoy+0.018
Neg logit contributions
line-0.013
 canvas-0.013
lee-0.012
 tide-0.012
 shell-0.012
Token It
Token ID632
Feature activation+1.15e+00

Pos logit contributions
 Spot+0.002
girls+0.002
 Buddy+0.002
 Zip+0.002
uddy+0.002
Neg logit contributions
 canvas-0.003
line-0.003
 product-0.003
 tide-0.003
lee-0.003
Token was
Token ID373
Feature activation+9.47e-01

Pos logit contributions
 Spot+0.023
 Buddy+0.021
 Zip+0.021
 Fl+0.021
 Max+0.021
Neg logit contributions
 canvas-0.056
line-0.056
 product-0.054
 tide-0.053
lee-0.052
Token a
Token ID257
Feature activation+8.48e-01

Pos logit contributions
 Spot+0.025
girls+0.025
 Buddy+0.024
 Zip+0.024
uddy+0.024
Neg logit contributions
 canvas-0.038
 product-0.038
line-0.037
 tide-0.037
 harbor-0.036
Token big
Token ID1263
Feature activation-5.50e-01

Pos logit contributions
girls+0.034
 Spot+0.033
 Zip+0.033
 Buddy+0.033
uddy+0.032
Neg logit contributions
 canvas-0.024
 product-0.023
 tide-0.022
 harbor-0.022
line-0.022
Token arc
Token ID10389
Feature activation-1.50e-01

Pos logit contributions
 canvas+0.017
 tide+0.017
 product+0.016
line+0.016
 harbor+0.016
Neg logit contributions
girls-0.020
 Spot-0.020
 Zip-0.019
 Buddy-0.019
uddy-0.019
Token of
Token ID286
Feature activation+2.99e+00

Pos logit contributions
 canvas+0.007
 product+0.007
lee+0.007
line+0.007
 pulp+0.007
Neg logit contributions
 Spot-0.002
 ever-0.002
 Zip-0.002
 Max-0.002
girls-0.002
Token many
Token ID867
Feature activation+8.85e-01

Pos logit contributions
girls+0.124
 Spot+0.122
uddy+0.122
 Buddy+0.121
 Zip+0.120
Neg logit contributions
 canvas-0.080
 tide-0.075
 product-0.073
line-0.072
 harbor-0.070
Token colors
Token ID7577
Feature activation-1.19e-01

Pos logit contributions
 Spot+0.032
girls+0.031
 Buddy+0.030
 Zip+0.030
 Fl+0.030
Neg logit contributions
 canvas-0.027
line-0.027
 product-0.026
 tide-0.026
lee-0.025
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
 canvas+0.006
 product+0.006
line+0.005
 tide+0.005
lee+0.005
Neg logit contributions
 Spot-0.002
 Max-0.002
 Zip-0.002
girls-0.002
 Buddy-0.002
Token It
Token ID632
Feature activation+9.34e-01

Pos logit contributions
 canvas+0.005
line+0.005
 product+0.005
 tide+0.005
 harbor+0.005
Neg logit contributions
girls-0.004
uddy-0.004
oof-0.004
 Buddy-0.004
 Johnson-0.004
Token was
Token ID373
Feature activation+9.02e-01

Pos logit contributions
 Spot+0.019
 Fl+0.018
 Zip+0.018
 Max+0.018
 Buddy+0.017
Neg logit contributions
line-0.045
 canvas-0.045
 product-0.043
 tide-0.042
lee-0.042
Token it
Token ID340
Feature activation+2.54e-01

Pos logit contributions
 Spot+0.001
girls+0.001
 Buddy+0.001
 Zip+0.001
 Max+0.001
Neg logit contributions
 canvas-0.002
line-0.002
 product-0.002
 tide-0.002
lee-0.002
Token out
Token ID503
Feature activation+9.32e-01

Pos logit contributions
 Spot+0.007
 Buddy+0.007
 Zip+0.007
girls+0.007
 Max+0.006
Neg logit contributions
 canvas-0.010
line-0.010
 product-0.010
 tide-0.010
lee-0.009
Token of
Token ID286
Feature activation+1.56e+00

Pos logit contributions
 Spot+0.025
girls+0.025
oof+0.023
 Buddy+0.023
 Zip+0.023
Neg logit contributions
 canvas-0.038
 product-0.037
line-0.037
 tide-0.036
lee-0.036
Token blocks
Token ID7021
Feature activation+4.38e-01

Pos logit contributions
uddy+0.060
girls+0.058
ver+0.055
Deal+0.054
ll+0.054
Neg logit contributions
 canvas-0.054
 product-0.051
 tide-0.051
 harbor-0.049
 shell-0.048
Token and
Token ID290
Feature activation-3.23e-01

Pos logit contributions
girls+0.011
 Spot+0.011
 Buddy+0.010
oof+0.010
 Zip+0.010
Neg logit contributions
line-0.019
 canvas-0.019
 product-0.018
 tide-0.018
 harbor-0.017
Token stuffed
Token ID22259
Feature activation+3.22e+00

Pos logit contributions
 canvas+0.011
line+0.010
 product+0.010
 tide+0.010
 harbor+0.010
Neg logit contributions
oof-0.011
uddy-0.011
girls-0.011
 Spot-0.011
 Zip-0.011
Token animals
Token ID4695
Feature activation-8.10e-02

Pos logit contributions
uddy+0.107
ver+0.103
 OK+0.100
Deal+0.100
oof+0.099
Neg logit contributions
 canvas-0.104
lee-0.101
 product-0.101
 pumpkin-0.100
line-0.099
Token,
Token ID11
Feature activation-2.12e-01

Pos logit contributions
line+0.003
 canvas+0.003
 product+0.002
 pumpkin+0.002
 shell+0.002
Neg logit contributions
oof-0.003
 Zip-0.003
 Spot-0.003
 Kitty-0.003
 Buddy-0.003
Token but
Token ID475
Feature activation-4.00e-01

Pos logit contributions
 canvas+0.008
line+0.008
 tide+0.007
 harbor+0.007
 pumpkin+0.007
Neg logit contributions
uddy-0.007
oof-0.007
girls-0.007
 Zip-0.006
 Buddy-0.006
Token it
Token ID340
Feature activation+1.05e+00

Pos logit contributions
line+0.011
 tide+0.011
 canvas+0.011
 product+0.010
 shell+0.010
Neg logit contributions
girls-0.017
oof-0.016
uddy-0.016
 Enjoy-0.015
 Zip-0.014
Token didn
Token ID1422
Feature activation+1.21e+00

Pos logit contributions
girls+0.030
oof+0.030
 Spot+0.029
 Enjoy+0.029
 Zip+0.028
Neg logit contributions
 product-0.040
 tide-0.040
 canvas-0.040
line-0.038
 shell-0.038
Token His
Token ID2399
Feature activation+2.78e-01

Pos logit contributions
 canvas+0.030
line+0.030
 product+0.030
 tide+0.029
lee+0.029
Neg logit contributions
 Spot-0.013
girls-0.013
 Buddy-0.012
 Zip-0.012
 Wh-0.012
Token mum
Token ID25682
Feature activation-9.31e-02

Pos logit contributions
girls+0.011
 Spot+0.011
 Zip+0.011
 Buddy+0.010
 Wh+0.010
Neg logit contributions
 canvas-0.008
 product-0.008
 tide-0.008
 shell-0.007
 harbor-0.007
Token said
Token ID531
Feature activation+7.34e-01

Pos logit contributions
 canvas+0.003
 product+0.003
line+0.003
 pumpkin+0.003
lee+0.003
Neg logit contributions
girls-0.003
oof-0.003
 Zip-0.003
uddy-0.003
 Buddy-0.003
Token it
Token ID340
Feature activation+1.27e+00

Pos logit contributions
girls+0.025
oof+0.024
 Spot+0.024
 Zip+0.023
uddy+0.023
Neg logit contributions
 canvas-0.025
line-0.025
 product-0.024
 tide-0.024
 pumpkin-0.023
Token was
Token ID373
Feature activation+5.44e-01

Pos logit contributions
oof+0.047
girls+0.047
 Zip+0.042
 losers+0.042
 Deal+0.041
Neg logit contributions
 product-0.039
 canvas-0.037
line-0.035
 pumpkin-0.034
 tide-0.034
Token time
Token ID640
Feature activation+9.19e-01

Pos logit contributions
girls+0.017
uddy+0.016
 Zip+0.016
 Buddy+0.015
oof+0.015
Neg logit contributions
 product-0.021
 canvas-0.021
 tide-0.020
lee-0.019
 harbor-0.019
Token to
Token ID284
Feature activation+7.03e-02

Pos logit contributions
girls+0.020
 Zip+0.018
 Spot+0.018
 Buddy+0.018
 Monkey+0.018
Neg logit contributions
line-0.044
 canvas-0.043
 product-0.042
 tide-0.041
lee-0.041
Token buy
Token ID2822
Feature activation-1.05e-01

Pos logit contributions
 Spot+0.002
girls+0.002
 Buddy+0.002
 Zip+0.002
 Max+0.002
Neg logit contributions
 canvas-0.002
line-0.002
 product-0.002
 tide-0.002
lee-0.002
Token some
Token ID617
Feature activation+2.07e-01

Pos logit contributions
 product+0.004
 canvas+0.004
 tide+0.004
line+0.004
 pumpkin+0.004
Neg logit contributions
uddy-0.003
girls-0.003
 Zip-0.003
 Buddy-0.003
 Monkey-0.003
Token salt
Token ID8268
Feature activation-3.89e-01

Pos logit contributions
 Spot+0.007
girls+0.007
 Zip+0.006
 Buddy+0.006
uddy+0.006
Neg logit contributions
 canvas-0.007
 product-0.007
 tide-0.007
line-0.007
 shell-0.007
Token.
Token ID13
Feature activation-5.72e-01

Pos logit contributions
line+0.015
 product+0.015
 canvas+0.015
 tide+0.015
 shell+0.014
Neg logit contributions
 Zip-0.011
girls-0.011
 Buddy-0.011
 Spot-0.011
uddy-0.010
Token,
Token ID11
Feature activation+8.16e-01

Pos logit contributions
 Spot+0.014
girls+0.014
 Buddy+0.013
 Zip+0.013
oof+0.013
Neg logit contributions
 canvas-0.023
line-0.023
 product-0.022
 tide-0.022
lee-0.021
Token "
Token ID366
Feature activation+2.61e-01

Pos logit contributions
girls+0.023
oof+0.023
uddy+0.022
 Spot+0.022
 Zip+0.022
Neg logit contributions
line-0.032
 canvas-0.031
 tide-0.030
 product-0.030
lee-0.029
TokenOK
Token ID11380
Feature activation+1.78e-01

Pos logit contributions
 Spot+0.006
girls+0.006
 Buddy+0.006
 Zip+0.005
 Max+0.005
Neg logit contributions
 canvas-0.012
line-0.012
 product-0.011
 tide-0.011
lee-0.011
Token,
Token ID11
Feature activation+6.02e-01

Pos logit contributions
girls+0.005
 Spot+0.005
 Buddy+0.005
 Zip+0.005
uddy+0.005
Neg logit contributions
 canvas-0.007
line-0.007
 product-0.007
 tide-0.007
lee-0.006
Token Mia
Token ID32189
Feature activation-4.31e-01

Pos logit contributions
girls+0.022
uddy+0.020
isk+0.020
oof+0.019
ver+0.019
Neg logit contributions
 canvas-0.020
 tide-0.019
line-0.019
 shell-0.018
 pumpkin-0.018
Token.
Token ID13
Feature activation+8.41e-01

Pos logit contributions
line+0.009
 canvas+0.009
 product+0.009
lee+0.009
 pumpkin+0.009
Neg logit contributions
oof-0.017
 Zip-0.017
girls-0.017
 Monkey-0.017
 Kenny-0.017
Token No
Token ID1400
Feature activation-2.79e-01

Pos logit contributions
girls+0.027
isk+0.026
oof+0.026
 Monkey+0.025
 Johnson+0.025
Neg logit contributions
line-0.025
 canvas-0.024
 tide-0.023
 pumpkin-0.021
 shell-0.021
Token more
Token ID517
Feature activation-6.30e-02

Pos logit contributions
 canvas+0.010
 tide+0.010
 product+0.010
 shell+0.009
 pumpkin+0.009
Neg logit contributions
girls-0.009
uddy-0.008
isk-0.008
 Spot-0.008
 Buddy-0.008
Token balancing
Token ID22486
Feature activation-6.35e-01

Pos logit contributions
 canvas+0.002
line+0.002
 product+0.002
 tide+0.002
lee+0.002
Neg logit contributions
 Spot-0.002
girls-0.002
 Buddy-0.002
 Zip-0.002
 Max-0.002
Token on
Token ID319
Feature activation-1.65e-01

Pos logit contributions
line+0.023
 canvas+0.023
 tide+0.022
 product+0.022
 shell+0.021
Neg logit contributions
uddy-0.020
girls-0.019
 Johnson-0.019
 Buddy-0.019
 Monkey-0.019
Token the
Token ID262
Feature activation-7.15e-02

Pos logit contributions
 canvas+0.006
 product+0.005
 tide+0.005
 pumpkin+0.005
 shell+0.005
Neg logit contributions
girls-0.006
uddy-0.006
Deal-0.005
ver-0.005
 Johnson-0.005
Token and
Token ID290
Feature activation+1.01e-01

Pos logit contributions
girls+0.053
oof+0.052
 Zip+0.050
uddy+0.049
 Buddy+0.049
Neg logit contributions
line-0.070
 product-0.069
 canvas-0.068
lee-0.065
 harbor-0.063
Token Ab
Token ID2275
Feature activation-1.66e-01

Pos logit contributions
girls+0.004
oof+0.003
uddy+0.003
 Zip+0.003
 Bones+0.003
Neg logit contributions
 canvas-0.003
line-0.003
lee-0.003
 product-0.003
 harbor-0.003
Tokenbie
Token ID12590
Feature activation-6.37e-01

Pos logit contributions
line+0.006
 canvas+0.006
 product+0.006
 tide+0.006
 harbor+0.006
Neg logit contributions
 Spot-0.004
girls-0.004
oof-0.004
 Fl-0.004
uddy-0.004
Token told
Token ID1297
Feature activation+1.03e+00

Pos logit contributions
 canvas+0.024
line+0.023
 product+0.023
 tide+0.023
lee+0.022
Neg logit contributions
 Spot-0.019
girls-0.018
 Buddy-0.018
 Zip-0.018
 Wh-0.017
Token everyone
Token ID2506
Feature activation+8.21e-02

Pos logit contributions
 Spot+0.027
girls+0.025
 Buddy+0.025
 Zip+0.025
 Fl+0.024
Neg logit contributions
 canvas-0.043
line-0.043
 product-0.042
 tide-0.041
lee-0.040
Token about
Token ID546
Feature activation+6.27e-01

Pos logit contributions
 Spot+0.002
 Buddy+0.002
girls+0.002
 Zip+0.002
 Max+0.002
Neg logit contributions
 canvas-0.004
line-0.004
 product-0.004
 tide-0.004
lee-0.003
Token her
Token ID607
Feature activation+1.41e-01

Pos logit contributions
uddy+0.023
girls+0.023
oof+0.022
 Zip+0.021
ver+0.021
Neg logit contributions
 canvas-0.021
 product-0.020
 pumpkin-0.019
 tide-0.019
line-0.019
Token special
Token ID2041
Feature activation-3.79e-01

Pos logit contributions
girls+0.006
 Spot+0.006
 Buddy+0.005
 Zip+0.005
 Fl+0.005
Neg logit contributions
 canvas-0.004
 product-0.004
 tide-0.004
line-0.004
lee-0.004
Token exam
Token ID2814
Feature activation-3.15e-01

Pos logit contributions
 canvas+0.011
 product+0.010
line+0.010
 tide+0.010
lee+0.009
Neg logit contributions
 Spot-0.015
girls-0.015
 Buddy-0.015
 Zip-0.015
 Fl-0.014
Token.
Token ID13
Feature activation-2.40e-02

Pos logit contributions
 canvas+0.011
line+0.011
 product+0.011
lee+0.009
 tide+0.009
Neg logit contributions
oof-0.011
girls-0.011
 Buddy-0.010
 Spot-0.010
uddy-0.010
Token They
Token ID1119
Feature activation-1.68e-01

Pos logit contributions
 canvas+0.001
line+0.001
 product+0.001
 tide+0.001
 harbor+0.001
Neg logit contributions
 Spot-0.001
 Fl-0.001
 Buddy-0.000
 Zip-0.000
 Kitty-0.000
Token upon
Token ID2402
Feature activation+4.81e-02

Pos logit contributions
 canvas+0.041
line+0.040
 product+0.040
 tide+0.039
lee+0.039
Neg logit contributions
 Spot-0.013
girls-0.013
 Buddy-0.012
 Zip-0.012
 Wh-0.011
Token a
Token ID257
Feature activation+6.47e-01

Pos logit contributions
girls+0.002
uddy+0.002
 Monkey+0.002
 Johnson+0.001
isk+0.001
Neg logit contributions
 tide-0.002
 canvas-0.002
line-0.001
 shell-0.001
 product-0.001
Token time
Token ID640
Feature activation-4.30e-01

Pos logit contributions
girls+0.020
 Monkey+0.018
 Wh+0.018
 Spot+0.018
 Zip+0.017
Neg logit contributions
 canvas-0.024
 product-0.023
 tide-0.023
 harbor-0.022
 shell-0.022
Token,
Token ID11
Feature activation+5.88e-01

Pos logit contributions
line+0.014
 canvas+0.014
 tide+0.014
 product+0.013
lee+0.013
Neg logit contributions
girls-0.015
oof-0.013
 Spot-0.013
Deal-0.013
 Monkey-0.012
Token there
Token ID612
Feature activation+5.21e-01

Pos logit contributions
girls+0.026
oof+0.023
 Monkey+0.023
 Spot+0.023
uddy+0.023
Neg logit contributions
 canvas-0.014
line-0.014
 tide-0.013
 product-0.013
 harbor-0.013
Token was
Token ID373
Feature activation+7.70e-01

Pos logit contributions
girls+0.020
oof+0.018
 losers+0.017
 Monkey+0.017
uddy+0.017
Neg logit contributions
 product-0.016
 tide-0.015
line-0.015
 shell-0.015
 pumpkin-0.014
Token a
Token ID257
Feature activation+6.08e-01

Pos logit contributions
girls+0.025
uddy+0.024
isk+0.023
 Monkey+0.022
Deal+0.022
Neg logit contributions
 tide-0.028
 canvas-0.027
 harbor-0.027
 pumpkin-0.027
 shell-0.025
Token little
Token ID1310
Feature activation-3.17e-02

Pos logit contributions
 Spot+0.019
 Buddy+0.018
girls+0.018
 Max+0.018
 Fl+0.018
Neg logit contributions
 canvas-0.022
line-0.022
 product-0.021
 tide-0.021
lee-0.021
Token girl
Token ID2576
Feature activation-2.86e-02

Pos logit contributions
 canvas+0.001
line+0.001
 product+0.001
 tide+0.001
lee+0.001
Neg logit contributions
 Spot-0.001
 Buddy-0.001
girls-0.001
 Zip-0.001
 Fl-0.001
Token named
Token ID3706
Feature activation+9.00e-01

Pos logit contributions
line+0.002
 tide+0.002
 product+0.002
 pulp+0.002
 tides+0.002
Neg logit contributions
 Spot-0.000
 Fl-0.000
 Max-0.000
 Wh-0.000
 Kitty-0.000
Token Jane
Token ID12091
Feature activation-5.90e-01

Pos logit contributions
girls+0.022
 Spot+0.019
 Monkey+0.018
 Zip+0.018
oof+0.018
Neg logit contributions
 canvas-0.042
line-0.039
lee-0.039
 product-0.038
 tide-0.038
Token from
Token ID422
Feature activation+3.85e-01

Pos logit contributions
girls+0.042
oof+0.041
uddy+0.040
Deal+0.039
 Buddy+0.038
Neg logit contributions
 canvas-0.047
 product-0.045
 tide-0.045
line-0.044
lee-0.043
Token the
Token ID262
Feature activation+5.61e-02

Pos logit contributions
uddy+0.016
girls+0.015
ver+0.015
ll+0.015
Deal+0.014
Neg logit contributions
 canvas-0.012
 tide-0.012
 pumpkin-0.011
 product-0.011
 shell-0.010
Token case
Token ID1339
Feature activation+1.44e-01

Pos logit contributions
girls+0.002
oof+0.002
 Spot+0.002
 Zip+0.002
ver+0.002
Neg logit contributions
 canvas-0.002
 tide-0.001
 product-0.001
 harbor-0.001
 shell-0.001
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
girls+0.006
oof+0.005
 Wh+0.005
 Enjoy+0.005
 Buddy+0.005
Neg logit contributions
line-0.005
 canvas-0.005
 shell-0.004
 tide-0.004
 harbor-0.004
Token It
Token ID632
Feature activation+1.03e+00

Pos logit contributions
girls+0.011
oof+0.010
Deal+0.009
 ever+0.009
 losers+0.009
Neg logit contributions
line-0.013
lee-0.013
 canvas-0.012
 product-0.012
 tide-0.011
Token was
Token ID373
Feature activation+1.07e+00

Pos logit contributions
girls+0.031
oof+0.031
 Spot+0.030
uddy+0.029
 Buddy+0.029
Neg logit contributions
 product-0.036
 canvas-0.036
 tide-0.035
 shell-0.035
lee-0.034
Token glad
Token ID9675
Feature activation+2.59e-01

Pos logit contributions
girls+0.039
uddy+0.039
Deal+0.037
oof+0.035
 Enjoy+0.035
Neg logit contributions
 product-0.034
 tide-0.033
 canvas-0.033
lee-0.032
 shell-0.032
Token to
Token ID284
Feature activation+5.98e-01

Pos logit contributions
girls+0.009
oof+0.008
uddy+0.008
 Spot+0.008
 Zip+0.008
Neg logit contributions
 canvas-0.009
 tide-0.008
line-0.008
 product-0.008
lee-0.008
Token be
Token ID307
Feature activation-5.91e-01

Pos logit contributions
 Spot+0.017
girls+0.017
 Buddy+0.017
 Zip+0.016
uddy+0.016
Neg logit contributions
 canvas-0.023
line-0.023
 product-0.022
 tide-0.022
lee-0.021
Token free
Token ID1479
Feature activation+2.54e-01

Pos logit contributions
 canvas+0.022
line+0.022
 product+0.022
 tide+0.021
lee+0.021
Neg logit contributions
 Spot-0.018
girls-0.017
 Zip-0.017
 Buddy-0.017
uddy-0.017
Token from
Token ID422
Feature activation+1.46e-02

Pos logit contributions
oof+0.009
girls+0.009
uddy+0.009
Deal+0.009
 Zip+0.008
Neg logit contributions
line-0.008
 canvas-0.008
 product-0.007
 shell-0.007
lee-0.007
Token
Token ID198
Feature activation-4.92e-01

Pos logit contributions
line+0.017
 canvas+0.016
lee+0.016
 tide+0.015
 product+0.015
Neg logit contributions
girls-0.016
oof-0.015
 losers-0.014
uddy-0.014
isk-0.014
Token
Token ID198
Feature activation-6.56e-01

Pos logit contributions
line+0.019
 canvas+0.019
 product+0.019
lee+0.019
 tide+0.018
Neg logit contributions
girls-0.013
 Spot-0.012
 Monkey-0.012
 Buddy-0.012
 Zip-0.011
Token"
Token ID1
Feature activation-1.32e+00

Pos logit contributions
 canvas+0.023
line+0.022
 product+0.022
 tide+0.022
lee+0.021
Neg logit contributions
 Spot-0.022
girls-0.021
 Buddy-0.021
 Zip-0.021
 Max-0.020
TokenGive
Token ID23318
Feature activation+1.61e-01

Pos logit contributions
 canvas+0.052
line+0.051
 product+0.050
 tide+0.049
lee+0.049
Neg logit contributions
 Spot-0.038
girls-0.036
 Zip-0.036
 Buddy-0.036
 Fl-0.035
Token it
Token ID340
Feature activation+5.54e-01

Pos logit contributions
 Spot+0.004
 Buddy+0.004
 Zip+0.004
girls+0.004
 Max+0.004
Neg logit contributions
 canvas-0.007
line-0.007
 product-0.007
 tide-0.007
 harbor-0.006
Token to
Token ID284
Feature activation+2.19e-01

Pos logit contributions
 Spot+0.015
girls+0.015
 Buddy+0.014
 Zip+0.014
 Max+0.014
Neg logit contributions
 canvas-0.022
line-0.022
 product-0.022
 tide-0.021
lee-0.020
Token me
Token ID502
Feature activation+2.50e-01

Pos logit contributions
 Spot+0.005
 Buddy+0.005
 Max+0.005
 Zip+0.005
 Wh+0.005
Neg logit contributions
line-0.010
 canvas-0.010
 product-0.009
 tide-0.009
lee-0.009
Token,
Token ID11
Feature activation+2.08e-01

Pos logit contributions
girls+0.008
uddy+0.007
 Buddy+0.007
 Spot+0.007
 Zip+0.007
Neg logit contributions
 canvas-0.009
line-0.009
 product-0.009
 shell-0.009
 pumpkin-0.009
Token Tom
Token ID4186
Feature activation-8.75e-01

Pos logit contributions
girls+0.006
uddy+0.005
 Spot+0.005
 Buddy+0.005
 Zip+0.005
Neg logit contributions
 canvas-0.009
line-0.008
 tide-0.008
 product-0.008
 shell-0.008
Token.
Token ID13
Feature activation+3.76e-01

Pos logit contributions
 canvas+0.034
line+0.033
 product+0.033
 tide+0.032
lee+0.031
Neg logit contributions
 Spot-0.024
girls-0.024
 Buddy-0.023
 Zip-0.023
uddy-0.022
Token It
Token ID632
Feature activation+8.71e-01

Pos logit contributions
 Spot+0.010
girls+0.010
 Buddy+0.010
 Zip+0.010
uddy+0.009
Neg logit contributions
 canvas-0.015
line-0.015
 product-0.015
 tide-0.014
lee-0.014
TokenWho
Token ID8241
Feature activation-9.47e-01

Pos logit contributions
 canvas+0.023
line+0.022
 product+0.022
lee+0.022
 tide+0.022
Neg logit contributions
 Spot-0.019
 Zip-0.018
girls-0.018
 Buddy-0.018
 Wh-0.017
Token is
Token ID318
Feature activation-8.34e-01

Pos logit contributions
 canvas+0.036
 product+0.034
 tide+0.034
 shell+0.033
line+0.033
Neg logit contributions
girls-0.027
 Buddy-0.026
 Spot-0.025
 Johnson-0.025
 Monkey-0.025
Token there
Token ID612
Feature activation+2.61e-01

Pos logit contributions
 canvas+0.032
line+0.032
 product+0.032
lee+0.031
 tide+0.030
Neg logit contributions
 Spot-0.025
 Max-0.024
 Buddy-0.024
 Zip-0.023
 Fl-0.023
Token?"
Token ID1701
Feature activation-3.33e-01

Pos logit contributions
girls+0.011
uddy+0.011
 Zip+0.011
 Spot+0.011
 Buddy+0.011
Neg logit contributions
 canvas-0.007
line-0.006
 tide-0.006
 product-0.006
 harbor-0.006
Token a
Token ID257
Feature activation-1.31e-02

Pos logit contributions
 canvas+0.017
line+0.017
 product+0.017
 tide+0.017
lee+0.016
Neg logit contributions
 Spot-0.005
 Buddy-0.005
 Zip-0.005
 Max-0.005
girls-0.005
Token voice
Token ID3809
Feature activation-3.52e-01

Pos logit contributions
 canvas+0.000
line+0.000
 product+0.000
lee+0.000
 tide+0.000
Neg logit contributions
 Spot-0.000
 Buddy-0.000
 Max-0.000
 Zip-0.000
 Fl-0.000
Token said
Token ID531
Feature activation+2.58e-01

Pos logit contributions
 canvas+0.016
 pulp+0.016
 product+0.016
 harbor+0.016
 tide+0.015
Neg logit contributions
 Spot-0.008
 Max-0.008
 Buddy-0.008
 Zip-0.008
 Kitty-0.008
Token.
Token ID13
Feature activation+2.11e-01

Pos logit contributions
 Spot+0.008
girls+0.007
 Buddy+0.007
 Zip+0.007
 Max+0.007
Neg logit contributions
 canvas-0.010
line-0.009
 product-0.009
 tide-0.009
 harbor-0.009
Token
Token ID198
Feature activation-3.56e-02

Pos logit contributions
girls+0.005
 Spot+0.005
 Buddy+0.005
oof+0.005
 Zip+0.005
Neg logit contributions
 canvas-0.009
line-0.009
 product-0.009
 tide-0.009
lee-0.008
Token
Token ID198
Feature activation-1.76e-01

Pos logit contributions
 canvas+0.002
line+0.002
 product+0.002
 tide+0.002
lee+0.002
Neg logit contributions
 Spot-0.001
girls-0.001
 Buddy-0.001
 Zip-0.001
 Max-0.001
TokenTom
Token ID13787
Feature activation-9.92e-02

Pos logit contributions
 canvas+0.009
 tide+0.009
 harbor+0.009
 pumpkin+0.009
 pulp+0.009
Neg logit contributions
 Spot-0.004
 Max-0.003
 Zip-0.003
 Wh-0.003
Max-0.003
Token throw
Token ID3714
Feature activation+2.44e-01

Pos logit contributions
 canvas+0.012
line+0.012
 tide+0.011
 shell+0.011
 harbor+0.011
Neg logit contributions
uddy-0.011
 Johnson-0.010
oof-0.010
 Buddy-0.010
 Spot-0.010
Token the
Token ID262
Feature activation-4.99e-01

Pos logit contributions
ll+0.010
uddy+0.010
ver+0.010
Deal+0.010
 Johnson+0.009
Neg logit contributions
 shell-0.006
 waves-0.006
 tide-0.006
 shells-0.006
 pumpkin-0.006
Token ball
Token ID2613
Feature activation-4.61e-01

Pos logit contributions
 canvas+0.018
 shell+0.017
line+0.017
 tide+0.017
 product+0.016
Neg logit contributions
girls-0.016
 Kitty-0.015
isk-0.015
 Buddy-0.015
 Fl-0.015
Token and
Token ID290
Feature activation+6.81e-01

Pos logit contributions
line+0.016
 shell+0.015
 canvas+0.015
 tide+0.015
 pumpkin+0.015
Neg logit contributions
girls-0.014
oof-0.014
 Johnson-0.014
 Monkey-0.014
 Kenny-0.014
Token Rex
Token ID17853
Feature activation-1.72e-01

Pos logit contributions
uddy+0.021
oof+0.020
ver+0.020
 Johnson+0.020
girls+0.020
Neg logit contributions
 canvas-0.024
line-0.023
 tide-0.022
 product-0.022
 shell-0.022
Token catches
Token ID17591
Feature activation-2.24e-01

Pos logit contributions
line+0.006
 canvas+0.006
 product+0.006
 shell+0.006
 tide+0.006
Neg logit contributions
 Johnson-0.005
uddy-0.005
oof-0.005
girls-0.005
 Buddy-0.005
Token it
Token ID340
Feature activation+2.19e-01

Pos logit contributions
line+0.006
 waves+0.006
 tide+0.005
 shell+0.005
 pumpkin+0.005
Neg logit contributions
uddy-0.009
Deal-0.009
ver-0.009
ll-0.009
 Johnson-0.008
Token.
Token ID13
Feature activation+5.11e-01

Pos logit contributions
oof+0.009
 Kenny+0.009
girls+0.009
 Monkey+0.009
uddy+0.009
Neg logit contributions
 shell-0.005
line-0.005
 canvas-0.005
 product-0.005
 tide-0.005
Token They
Token ID1119
Feature activation-3.81e-01

Pos logit contributions
atum+0.018
isk+0.018
Deal+0.017
ll+0.017
oof+0.017
Neg logit contributions
line-0.015
 tide-0.014
lee-0.013
 harbor-0.013
 tidal-0.013
Token have
Token ID423
Feature activation+2.99e-02

Pos logit contributions
 canvas+0.013
line+0.013
 tide+0.013
 shell+0.013
 harbor+0.012
Neg logit contributions
uddy-0.012
 Johnson-0.012
oof-0.011
 Buddy-0.011
 Kitty-0.011
Token fun
Token ID1257
Feature activation+6.62e-01

Pos logit contributions
uddy+0.001
 Monkey+0.001
 Johnson+0.001
ver+0.001
girls+0.001
Neg logit contributions
 canvas-0.001
 tide-0.001
 shell-0.001
 product-0.001
 harbor-0.001
Token and
Token ID290
Feature activation-7.37e-01

Pos logit contributions
line+0.026
 canvas+0.024
 product+0.022
 shell+0.022
 harbor+0.022
Neg logit contributions
 Zip-0.026
oof-0.025
girls-0.025
 Kitty-0.024
uddy-0.024
Token apologize
Token ID16521
Feature activation+6.94e-02

Pos logit contributions
 canvas+0.029
line+0.027
 product+0.027
 shell+0.027
 tide+0.027
Neg logit contributions
girls-0.021
uddy-0.021
 Zip-0.020
oof-0.020
 Johnson-0.019
Token when
Token ID618
Feature activation-1.13e+00

Pos logit contributions
girls+0.002
oof+0.002
 Zip+0.002
uddy+0.002
 Johnson+0.002
Neg logit contributions
line-0.003
 canvas-0.003
 product-0.002
lee-0.002
 shell-0.002
Token we
Token ID356
Feature activation-2.33e-01

Pos logit contributions
 canvas+0.041
 tide+0.040
 product+0.040
line+0.040
 harbor+0.038
Neg logit contributions
girls-0.035
uddy-0.034
oof-0.033
 Spot-0.033
 Zip-0.033
Token make
Token ID787
Feature activation-1.37e+00

Pos logit contributions
 canvas+0.009
line+0.009
 tide+0.008
 harbor+0.008
 product+0.008
Neg logit contributions
 Zip-0.007
 Spot-0.007
uddy-0.007
girls-0.007
 Kitty-0.007
Token mistakes
Token ID10135
Feature activation-2.68e-01

Pos logit contributions
 canvas+0.051
 product+0.050
line+0.049
 tide+0.049
lee+0.048
Neg logit contributions
 Spot-0.040
girls-0.040
 Zip-0.039
uddy-0.039
 Buddy-0.039
Token.
Token ID13
Feature activation+2.47e-01

Pos logit contributions
line+0.009
 canvas+0.009
 product+0.008
 tide+0.008
lee+0.008
Neg logit contributions
oof-0.009
 Zip-0.009
girls-0.009
uddy-0.009
 Spot-0.009
Token<|endoftext|>
Token ID50256
Feature activation+1.95e-01

Pos logit contributions
girls+0.007
 Zip+0.006
uddy+0.006
 Spot+0.006
 Buddy+0.006
Neg logit contributions
line-0.009
lee-0.009
 canvas-0.009
 product-0.009
 pumpkin-0.008
TokenOnce
Token ID7454
Feature activation-1.09e+00

Pos logit contributions
girls+0.007
Deal+0.007
 losers+0.007
oof+0.007
uddy+0.007
Neg logit contributions
line-0.005
 product-0.005
 tide-0.005
lee-0.005
 harbor-0.005
Token upon
Token ID2402
Feature activation-2.36e-01

Pos logit contributions
 canvas+0.056
line+0.055
 product+0.055
 tide+0.054
lee+0.053
Neg logit contributions
 Spot-0.017
girls-0.016
 Buddy-0.016
 Zip-0.015
 Max-0.015
Token a
Token ID257
Feature activation+6.31e-01

Pos logit contributions
 canvas+0.009
line+0.009
 tide+0.009
 product+0.009
 shell+0.009
Neg logit contributions
girls-0.006
uddy-0.006
 Monkey-0.006
 Zip-0.006
 Buddy-0.006
Token it
Token ID340
Feature activation+4.26e-01

Pos logit contributions
uddy+0.010
girls+0.010
 Buddy+0.010
 Zip+0.010
 Spot+0.009
Neg logit contributions
 product-0.011
 canvas-0.011
line-0.011
 tide-0.011
lee-0.010
Token."
Token ID526
Feature activation+2.08e-01

Pos logit contributions
girls+0.016
 Zip+0.015
 Buddy+0.015
uddy+0.015
oof+0.014
Neg logit contributions
line-0.013
 product-0.012
 canvas-0.012
 tide-0.012
 shell-0.011
Token So
Token ID1406
Feature activation+2.20e-01

Pos logit contributions
girls+0.006
 losers+0.005
ver+0.005
 Hero+0.005
oof+0.005
Neg logit contributions
 canvas-0.008
lee-0.008
line-0.008
 product-0.008
 pumpkin-0.007
Token,
Token ID11
Feature activation-3.20e-02

Pos logit contributions
girls+0.008
oof+0.007
isk+0.007
 Hero+0.007
uddy+0.007
Neg logit contributions
 canvas-0.007
 tide-0.006
 pumpkin-0.006
line-0.006
 product-0.006
Token Tim
Token ID5045
Feature activation+2.74e-01

Pos logit contributions
 canvas+0.001
 tide+0.001
 pumpkin+0.001
line+0.001
 product+0.001
Neg logit contributions
girls-0.001
oof-0.001
uddy-0.001
isk-0.001
 Hero-0.001
Token decided
Token ID3066
Feature activation-2.64e-01

Pos logit contributions
girls+0.010
 Zip+0.010
 Spot+0.009
 Buddy+0.009
oof+0.009
Neg logit contributions
 canvas-0.008
 product-0.008
line-0.008
lee-0.008
 shell-0.008
Token to
Token ID284
Feature activation-3.50e-01

Pos logit contributions
 canvas+0.013
 product+0.013
line+0.013
 tide+0.013
lee+0.012
Neg logit contributions
 Spot-0.005
 Buddy-0.004
 Zip-0.004
 Max-0.004
girls-0.004
Token help
Token ID1037
Feature activation+1.34e+00

Pos logit contributions
 canvas+0.011
 product+0.011
line+0.011
 tide+0.010
 pumpkin+0.010
Neg logit contributions
girls-0.013
uddy-0.012
 Zip-0.012
 Buddy-0.012
oof-0.012
Token his
Token ID465
Feature activation+3.86e-02

Pos logit contributions
girls+0.036
 Spot+0.035
 Zip+0.034
 Buddy+0.034
uddy+0.034
Neg logit contributions
 canvas-0.054
 product-0.054
line-0.053
 tide-0.051
lee-0.050
Token neighbors
Token ID12020
Feature activation+1.87e-01

Pos logit contributions
 Spot+0.001
girls+0.001
 Buddy+0.001
 Zip+0.001
 Max+0.001
Neg logit contributions
 canvas-0.001
line-0.001
 tide-0.001
 product-0.001
lee-0.001
Token.
Token ID13
Feature activation+3.12e-01

Pos logit contributions
oof+0.007
 Zip+0.006
girls+0.006
 Spot+0.006
 Buddy+0.006
Neg logit contributions
line-0.006
 canvas-0.006
 product-0.006
 harbor-0.005
 pumpkin-0.005
Token good
Token ID922
Feature activation-6.39e-01

Pos logit contributions
 canvas+0.017
 product+0.016
 pulp+0.016
line+0.016
lee+0.015
Neg logit contributions
 Spot-0.011
 Zip-0.010
 Max-0.010
 Buddy-0.010
 Fl-0.010
Token at
Token ID379
Feature activation-3.87e-01

Pos logit contributions
line+0.025
 canvas+0.024
 tide+0.024
 product+0.024
lee+0.023
Neg logit contributions
girls-0.018
 Spot-0.018
 Buddy-0.017
 Zip-0.017
uddy-0.017
Token balancing
Token ID22486
Feature activation-3.78e-01

Pos logit contributions
 canvas+0.014
 pulp+0.013
 product+0.013
line+0.013
lee+0.013
Neg logit contributions
 Spot-0.012
 Max-0.011
 first-0.011
 Zip-0.011
 Fl-0.011
Token on
Token ID319
Feature activation-4.63e-01

Pos logit contributions
 canvas+0.015
line+0.015
 product+0.015
 tide+0.015
lee+0.014
Neg logit contributions
 Spot-0.010
girls-0.010
 Buddy-0.010
 Zip-0.010
uddy-0.009
Token the
Token ID262
Feature activation-7.98e-02

Pos logit contributions
 tide+0.015
 canvas+0.015
line+0.015
 product+0.014
 shell+0.014
Neg logit contributions
uddy-0.016
girls-0.016
ver-0.015
 Buddy-0.015
 Monkey-0.015
Token board
Token ID3096
Feature activation-1.66e+00

Pos logit contributions
 product+0.003
lee+0.002
 pulp+0.002
rys+0.002
 canvas+0.002
Neg logit contributions
 first-0.002
 Spot-0.002
 Max-0.002
 for-0.002
 love-0.002
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
line+0.061
 canvas+0.060
 tide+0.059
 product+0.058
 shell+0.056
Neg logit contributions
 Spot-0.050
girls-0.050
 Buddy-0.049
 Kitty-0.048
 Wh-0.048
Token How
Token ID1374
Feature activation-4.82e-01

Pos logit contributions
girls+0.007
oof+0.006
uddy+0.006
 Spot+0.006
 Buddy+0.006
Neg logit contributions
line-0.009
 canvas-0.009
 tide-0.009
lee-0.008
 product-0.008
Token does
Token ID857
Feature activation-3.75e-01

Pos logit contributions
 canvas+0.021
line+0.021
 product+0.020
 tide+0.020
lee+0.020
Neg logit contributions
 Spot-0.011
girls-0.011
 Buddy-0.011
 Zip-0.011
 Wh-0.010
Token he
Token ID339
Feature activation+9.78e-01

Pos logit contributions
 canvas+0.017
 pulp+0.017
lee+0.017
line+0.016
 product+0.016
Neg logit contributions
 Spot-0.010
 Max-0.009
 Zip-0.009
 Buddy-0.009
 Fl-0.008
Token do
Token ID466
Feature activation-5.34e-01

Pos logit contributions
 Spot+0.030
girls+0.029
 Buddy+0.029
 Zip+0.028
 Fl+0.028
Neg logit contributions
 canvas-0.036
line-0.035
 product-0.035
 tide-0.034
lee-0.033
Token Be
Token ID1355
Feature activation-7.10e-01

Pos logit contributions
girls+0.030
uddy+0.026
isk+0.026
ll+0.026
oof+0.026
Neg logit contributions
line-0.030
 canvas-0.030
lee-0.029
 tide-0.028
rys-0.027
Token careful
Token ID8161
Feature activation+7.88e-02

Pos logit contributions
 product+0.023
 canvas+0.023
line+0.022
 tide+0.022
 shell+0.022
Neg logit contributions
girls-0.024
uddy-0.024
 Zip-0.023
 Spot-0.023
 Monkey-0.023
Token not
Token ID407
Feature activation+2.45e-02

Pos logit contributions
girls+0.002
 Spot+0.002
 Zip+0.002
oof+0.002
 Monkey+0.002
Neg logit contributions
 canvas-0.003
line-0.003
 product-0.003
 tide-0.003
lee-0.003
Token to
Token ID284
Feature activation+3.19e-02

Pos logit contributions
girls+0.001
 Spot+0.001
 Zip+0.001
 Buddy+0.001
oof+0.001
Neg logit contributions
 canvas-0.001
line-0.001
 tide-0.001
 product-0.001
 shell-0.001
Token hurt
Token ID5938
Feature activation+1.01e+00

Pos logit contributions
 Spot+0.001
girls+0.001
 Buddy+0.001
 Zip+0.001
uddy+0.001
Neg logit contributions
 canvas-0.001
line-0.001
 product-0.001
 tide-0.001
 harbor-0.001
Token yourself
Token ID3511
Feature activation-1.90e+00

Pos logit contributions
girls+0.034
uddy+0.033
oof+0.032
ver+0.031
Deal+0.031
Neg logit contributions
 canvas-0.033
line-0.033
 tide-0.032
 product-0.031
 shell-0.030
Token again
Token ID757
Feature activation+8.48e-01

Pos logit contributions
line+0.068
 canvas+0.067
 product+0.064
 tide+0.062
 harbor+0.061
Neg logit contributions
girls-0.060
oof-0.059
uddy-0.059
 Zip-0.059
 Buddy-0.058
Token,"
Token ID553
Feature activation+1.07e+00

Pos logit contributions
uddy+0.027
girls+0.027
 Zip+0.027
 Spot+0.027
 Buddy+0.026
Neg logit contributions
 canvas-0.029
line-0.028
 product-0.028
 tide-0.027
lee-0.027
Token said
Token ID531
Feature activation+4.73e-01

Pos logit contributions
girls+0.036
uddy+0.034
 Zip+0.033
 Spot+0.033
oof+0.032
Neg logit contributions
 canvas-0.036
 product-0.035
line-0.035
 tide-0.034
 pumpkin-0.034
Token the
Token ID262
Feature activation-1.11e+00

Pos logit contributions
girls+0.014
oof+0.013
uddy+0.013
Deal+0.013
 Zip+0.013
Neg logit contributions
 canvas-0.017
 product-0.017
 tide-0.017
line-0.017
 pumpkin-0.017
Token nurse
Token ID15849
Feature activation+3.78e-02

Pos logit contributions
 canvas+0.033
 product+0.032
 tide+0.032
line+0.030
 harbor+0.030
Neg logit contributions
girls-0.043
 Buddy-0.041
oof-0.041
 Zip-0.041
uddy-0.040
Token his
Token ID465
Feature activation-2.48e-02

Pos logit contributions
uddy+0.039
girls+0.038
oof+0.037
 Johnson+0.037
 Wh+0.035
Neg logit contributions
 tide-0.032
lee-0.031
 shell-0.030
 tides-0.030
 anchor-0.030
Token friends
Token ID2460
Feature activation+8.92e-01

Pos logit contributions
lee+0.001
 shell+0.001
 pumpkin+0.001
 tide+0.001
 harbor+0.001
Neg logit contributions
 Wh-0.001
isk-0.001
 Johnson-0.001
 Spot-0.001
 Fl-0.001
Token about
Token ID546
Feature activation+7.17e-01

Pos logit contributions
girls+0.024
oof+0.023
 Wh+0.022
 Spot+0.022
uddy+0.022
Neg logit contributions
line-0.036
 canvas-0.035
 tide-0.034
lee-0.034
 harbor-0.034
Token how
Token ID703
Feature activation-1.39e-01

Pos logit contributions
uddy+0.025
girls+0.024
oof+0.024
ver+0.022
 Wh+0.022
Neg logit contributions
 tide-0.023
 canvas-0.023
 product-0.023
 pumpkin-0.023
 harbor-0.022
Token the
Token ID262
Feature activation-2.13e-01

Pos logit contributions
 canvas+0.006
line+0.005
 product+0.005
 tide+0.005
 harbor+0.005
Neg logit contributions
 Spot-0.004
 Buddy-0.004
girls-0.004
 Zip-0.004
 Max-0.003
Token big
Token ID1263
Feature activation-1.80e+00

Pos logit contributions
 tide+0.006
 harbor+0.006
 canvas+0.005
 product+0.005
 pumpkin+0.005
Neg logit contributions
 Spot-0.009
girls-0.009
oof-0.009
 Fl-0.008
uddy-0.008
Token,
Token ID11
Feature activation-5.24e-01

Pos logit contributions
 canvas+0.055
 tide+0.054
 product+0.053
line+0.052
 harbor+0.051
Neg logit contributions
 Spot-0.065
girls-0.065
uddy-0.063
oof-0.063
 Zip-0.062
Token strong
Token ID1913
Feature activation-1.10e+00

Pos logit contributions
 canvas+0.016
 tide+0.015
line+0.015
 product+0.014
 harbor+0.014
Neg logit contributions
girls-0.020
uddy-0.020
oof-0.020
 Spot-0.019
 Zip-0.019
Token rabbit
Token ID22746
Feature activation+1.60e-01

Pos logit contributions
 tide+0.033
 canvas+0.032
line+0.031
 harbor+0.031
 product+0.030
Neg logit contributions
girls-0.041
 Spot-0.041
oof-0.039
uddy-0.039
 Fl-0.039
Token helped
Token ID4193
Feature activation+5.93e-01

Pos logit contributions
oof+0.005
girls+0.005
uddy+0.005
 Wh+0.005
 Spot+0.004
Neg logit contributions
line-0.006
 shell-0.006
 harbor-0.005
 product-0.005
 tide-0.005
Token him
Token ID683
Feature activation+3.91e-01

Pos logit contributions
oof+0.014
uddy+0.013
girls+0.013
 Bones+0.013
 Wh+0.013
Neg logit contributions
line-0.024
 canvas-0.024
 pumpkin-0.023
 product-0.023
 tide-0.023
Token and
Token ID290
Feature activation+2.79e-01

Pos logit contributions
girls+0.008
uddy+0.008
oof+0.007
isk+0.007
 Monkey+0.007
Neg logit contributions
line-0.008
 tide-0.008
 canvas-0.008
 harbor-0.008
 shell-0.008
Token the
Token ID262
Feature activation-4.20e-01

Pos logit contributions
uddy+0.011
girls+0.011
oof+0.010
isk+0.010
 Zip+0.010
Neg logit contributions
 tide-0.008
 canvas-0.008
line-0.008
 pumpkin-0.008
 shell-0.008
Token w
Token ID266
Feature activation-3.77e-01

Pos logit contributions
 tide+0.014
 canvas+0.013
line+0.013
 product+0.013
 shell+0.013
Neg logit contributions
girls-0.014
 Zip-0.014
ver-0.014
uddy-0.014
 Spot-0.014
Tokenaffle
Token ID30697
Feature activation+8.73e-01

Pos logit contributions
 canvas+0.013
line+0.013
 product+0.013
 tide+0.013
lee+0.013
Neg logit contributions
 Spot-0.012
girls-0.012
 Buddy-0.011
 Zip-0.011
 Max-0.011
Token was
Token ID373
Feature activation-1.82e-01

Pos logit contributions
girls+0.026
 Zip+0.026
oof+0.026
 Spot+0.025
 Buddy+0.025
Neg logit contributions
 canvas-0.031
line-0.031
 product-0.030
 tide-0.030
 shell-0.030
Token feeling
Token ID4203
Feature activation-1.84e+00

Pos logit contributions
 canvas+0.007
 product+0.007
 tide+0.007
 harbor+0.006
line+0.006
Neg logit contributions
girls-0.006
uddy-0.005
 Zip-0.005
 Monkey-0.005
 Bones-0.005
Token very
Token ID845
Feature activation+3.22e-01

Pos logit contributions
 canvas+0.076
line+0.075
 product+0.075
 tide+0.074
lee+0.071
Neg logit contributions
 Spot-0.047
girls-0.046
 Zip-0.045
 Buddy-0.045
uddy-0.043
Token cold
Token ID4692
Feature activation+9.85e-02

Pos logit contributions
 Spot+0.009
 Buddy+0.009
girls+0.009
 Fl+0.009
 Zip+0.009
Neg logit contributions
 canvas-0.012
 product-0.012
line-0.012
 tide-0.012
lee-0.011
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
girls+0.003
 Spot+0.003
 Zip+0.003
 Buddy+0.003
uddy+0.003
Neg logit contributions
 canvas-0.003
line-0.003
 tide-0.003
 product-0.003
 harbor-0.003
Token It
Token ID632
Feature activation+8.04e-01

Pos logit contributions
 canvas+0.004
line+0.004
 tide+0.004
lee+0.003
 harbor+0.003
Neg logit contributions
girls-0.003
isk-0.003
uddy-0.003
oof-0.003
 Johnson-0.003
Token wanted
Token ID2227
Feature activation-2.77e-01

Pos logit contributions
girls+0.024
 Spot+0.024
 Zip+0.024
 Buddy+0.023
uddy+0.023
Neg logit contributions
 canvas-0.029
 product-0.028
 tide-0.028
line-0.028
lee-0.027
Tokenily
Token ID813
Feature activation-2.45e-01

Pos logit contributions
 canvas+0.004
line+0.004
lee+0.003
 product+0.003
 tide+0.003
Neg logit contributions
 Spot-0.005
girls-0.005
 Buddy-0.005
 Zip-0.004
 Monkey-0.004
Token and
Token ID290
Feature activation+2.60e-01

Pos logit contributions
 canvas+0.009
line+0.009
 product+0.009
lee+0.009
 tide+0.009
Neg logit contributions
girls-0.007
 Spot-0.007
 Buddy-0.007
 Zip-0.007
uddy-0.007
Token Tom
Token ID4186
Feature activation+6.90e-02

Pos logit contributions
uddy+0.007
oof+0.007
girls+0.007
ver+0.007
Deal+0.007
Neg logit contributions
 canvas-0.010
lee-0.010
 pumpkin-0.010
line-0.009
 tide-0.009
Token held
Token ID2714
Feature activation-6.79e-01

Pos logit contributions
girls+0.002
 Spot+0.002
 Buddy+0.002
 Zip+0.002
uddy+0.002
Neg logit contributions
 canvas-0.002
line-0.002
 tide-0.002
lee-0.002
 product-0.002
Token the
Token ID262
Feature activation-5.95e-01

Pos logit contributions
 canvas+0.015
lee+0.015
 pumpkin+0.015
 shell+0.014
 product+0.014
Neg logit contributions
ll-0.029
uddy-0.029
isk-0.028
girls-0.028
ver-0.027
Token old
Token ID1468
Feature activation-2.88e+00

Pos logit contributions
 canvas+0.018
 tide+0.017
 product+0.017
 pumpkin+0.017
 shell+0.016
Neg logit contributions
girls-0.023
 Spot-0.023
 Buddy-0.023
 Zip-0.022
 Wh-0.022
Token man
Token ID582
Feature activation-1.64e+00

Pos logit contributions
 canvas+0.088
line+0.085
 product+0.085
 tide+0.083
lee+0.079
Neg logit contributions
 Spot-0.106
girls-0.104
 Buddy-0.103
 Zip-0.102
 Fl-0.100
Token's
Token ID338
Feature activation-9.61e-01

Pos logit contributions
 canvas+0.056
 product+0.056
line+0.055
 shell+0.053
 pumpkin+0.052
Neg logit contributions
girls-0.052
 Spot-0.051
 Buddy-0.050
 Wh-0.050
 Zip-0.050
Token hands
Token ID2832
Feature activation-7.44e-01

Pos logit contributions
 canvas+0.026
 product+0.025
line+0.024
 tide+0.024
 shell+0.024
Neg logit contributions
girls-0.039
 Spot-0.039
 Zip-0.038
 Buddy-0.038
 Wh-0.037
Token and
Token ID290
Feature activation-9.40e-02

Pos logit contributions
line+0.024
 canvas+0.022
 pumpkin+0.021
 shell+0.021
 harbor+0.020
Neg logit contributions
girls-0.028
oof-0.028
 Zip-0.027
uddy-0.027
isk-0.027
Token led
Token ID2957
Feature activation-7.68e-01

Pos logit contributions
 canvas+0.003
line+0.003
 product+0.003
 tide+0.003
lee+0.003
Neg logit contributions
uddy-0.003
oof-0.003
girls-0.003
 Zip-0.003
 Spot-0.003