TOP ACTIVATIONS
MAX = 4.347

Once there was a tall palm tree . It lived in
Lily . We 'll stand under a space that 's covered
at the shore . They see sand , water , shells
They have fun . They see a sees aw . They
flag ! Can we go see it ?" Mom
was gray and full of big clouds . Tim saw a
He lived in a big palm tree by the beach .
flag . It was a big flag , with bright colors
Yes , let 's go find them !" Su
naughty . They liked the palm tree and the garden .
Sure , let 's go see the bird ." But as
, there was a big palm tree in the middle of
a big anchor on the front , to help it stay
Yes , we can go see the sunset ."
, he wanted to give his dad a big hug .
shore , Lily saw a palm tree waving in the wind
a little boat with a big sail . The boat sailed
to the beach . They saw a boat and wanted to
beautiful butterfly . It had big , colorful wings . The
bird ! Can we go see it ?" Mom

MIN ACTIVATIONS
MIN = -4.719

school !" Bon nie was so happy that
One day , Lily and Sunny were in the field
One day , Tim and Fl uffy went to the
, Bonnie !" Bon nie was so happy and
One day , Spot and Shadow were playing on the
for tomorrow ." Bon nie p outed , then
was so thankful that the mer maid had forgiven him .
day , Lucy and Mr . Bear went to the park
his paw . Gr ace was surprised and said
Every day , Ho ppy and Cotton would explore the me
strange . Joe and May wanted to touch the
age . Gr ace was very excited .
One day , Spot and Daisy went to a fun
The b unn ies happily hopped back to
So , Frost y and Lily used their magic powers
One day , Tim my and Midnight went for a walk
One day , Lily and Fl uffy went to the
being curious ." Gr ace laughed and said ,
. One day , Rudy and his friends went for a
One sunny day , Max and Lucy found a patch of

INTERVAL 2.080 - 4.347
CONTAINS 0.246%

looked out the window and saw the lightning . Suddenly ,
Lily hiding under the t arp . He knew they were
a secret before and he didn 't know what to do
cry Sammy . We can find somewhere else to dance !"
, but the sky was full of dark clouds .

INTERVAL -0.186 - 2.080
CONTAINS 60.680%

hold hands and walk away from the cage . They learn
but he knew he had to stay on the floor .
of the grass made her feel very relaxed .
park . Spot would throw the pipe and then run to
She said , " I want to look like a peac

INTERVAL -2.453 - -0.186
CONTAINS 38.986%

. " Now you have no red car .
little boy named Jack . He loved to tell jokes to
more . Her mom my took her to the hospital .
of the night , all of the girl â € ™
and cl apped his paws together to applaud the train .

INTERVAL -4.719 - -2.453
CONTAINS 0.088%

. One day , Lily and her friends found a big
this is Mr . Jones . He is a friend from
!" But Ben and Mia did not stop .
<|endoftext|> One day , Chad and his mom went to the
became too hard . Andy and Amy tried to fix it
TokenOnce
Token ID7454
Feature activation+1.65e-01

Pos logit contributions
ement+0.033
bridge+0.027
aw+0.026
 swings+0.026
 amaz+0.026
Neg logit contributions
working-0.022
 Claus-0.021
inky-0.021
ppy-0.021
ny-0.020
Token there
Token ID612
Feature activation+9.73e-02

Pos logit contributions
ement+0.008
bridge+0.006
 sliding+0.006
 amaz+0.006
aw+0.006
Neg logit contributions
 Claus-0.003
working-0.003
inky-0.003
ny-0.002
ppy-0.002
Token was
Token ID373
Feature activation-3.85e-02

Pos logit contributions
ement+0.003
bridge+0.003
aw+0.002
 swings+0.002
irling+0.002
Neg logit contributions
working-0.003
ny-0.003
 Claus-0.003
inky-0.003
ley-0.003
Token a
Token ID257
Feature activation+8.68e-01

Pos logit contributions
working+0.001
inky+0.001
ny+0.001
ppy+0.001
 Claus+0.001
Neg logit contributions
ement-0.001
bridge-0.001
irling-0.001
uct-0.001
 amaz-0.001
Token tall
Token ID7331
Feature activation+2.71e+00

Pos logit contributions
ement+0.025
 swings+0.021
 sliding+0.020
aw+0.020
 amaz+0.019
Neg logit contributions
working-0.028
ppy-0.027
ley-0.027
inky-0.027
 Claus-0.027
Token palm
Token ID18057
Feature activation+4.35e+00

Pos logit contributions
ement+0.082
bridge+0.063
 amaz+0.060
aw+0.059
irling+0.058
Neg logit contributions
working-0.090
 Claus-0.087
ny-0.087
inky-0.085
ley-0.084
Token tree
Token ID5509
Feature activation+1.39e+00

Pos logit contributions
ement+0.138
 amaz+0.124
aded+0.120
irled+0.113
bridge+0.111
Neg logit contributions
working-0.133
ny-0.124
ro-0.124
y-0.123
inky-0.114
Token.
Token ID13
Feature activation+7.14e-01

Pos logit contributions
ement+0.049
 amaz+0.040
bridge+0.040
 awesome+0.036
 cal+0.036
Neg logit contributions
working-0.041
ny-0.039
 Claus-0.038
inky-0.038
ro-0.037
Token It
Token ID632
Feature activation+3.83e-01

Pos logit contributions
ement+0.024
bridge+0.020
 swings+0.020
aw+0.019
 amaz+0.019
Neg logit contributions
working-0.020
 Claus-0.020
ppy-0.020
inky-0.020
ley-0.020
Token lived
Token ID5615
Feature activation+2.01e-01

Pos logit contributions
ement+0.015
 amaz+0.012
bridge+0.012
irling+0.011
aw+0.011
Neg logit contributions
working-0.010
ny-0.010
ro-0.009
 Claus-0.009
ppy-0.009
Token in
Token ID287
Feature activation+1.38e+00

Pos logit contributions
ement+0.008
 amaz+0.007
bridge+0.006
aw+0.006
 swings+0.006
Neg logit contributions
working-0.005
ny-0.005
 Claus-0.005
inky-0.005
ppy-0.005
Token Lily
Token ID20037
Feature activation+6.77e-01

Pos logit contributions
ement+0.001
bridge+0.001
aw+0.001
aming+0.001
irling+0.001
Neg logit contributions
ppy-0.001
working-0.001
 Claus-0.001
inky-0.001
ro-0.001
Token.
Token ID13
Feature activation+5.55e-01

Pos logit contributions
ement+0.020
bridge+0.016
 swings+0.015
aw+0.015
 amaz+0.015
Neg logit contributions
working-0.023
 Claus-0.022
inky-0.022
ppy-0.022
ny-0.022
Token We
Token ID775
Feature activation+3.13e-01

Pos logit contributions
ement+0.020
bridge+0.016
aw+0.016
 swings+0.016
 amaz+0.016
Neg logit contributions
working-0.015
 Claus-0.014
inky-0.014
ppy-0.014
ny-0.014
Token'll
Token ID1183
Feature activation+1.31e+00

Pos logit contributions
ement+0.012
bridge+0.010
aw+0.010
 swings+0.010
 amaz+0.010
Neg logit contributions
working-0.008
inky-0.007
 Claus-0.007
ppy-0.007
ny-0.007
Token stand
Token ID1302
Feature activation+1.60e+00

Pos logit contributions
ement+0.056
bridge+0.046
aw+0.045
 amaz+0.043
uct+0.042
Neg logit contributions
inky-0.029
working-0.029
ppy-0.028
ny-0.028
 Claus-0.028
Token under
Token ID739
Feature activation+3.89e+00

Pos logit contributions
ement+0.059
bridge+0.047
 amaz+0.046
aw+0.045
uct+0.044
Neg logit contributions
 Claus-0.041
working-0.041
ppy-0.040
 Ho-0.039
ley-0.038
Token a
Token ID257
Feature activation+1.07e+00

Pos logit contributions
ement+0.163
bridge+0.136
uct+0.130
aded+0.124
irled+0.122
Neg logit contributions
 Ho-0.084
working-0.079
 guys-0.076
 Penny-0.074
 Th-0.073
Token space
Token ID2272
Feature activation+3.82e-01

Pos logit contributions
ement+0.036
irled+0.028
aw+0.028
uct+0.028
bridge+0.028
Neg logit contributions
ny-0.034
inky-0.032
ro-0.030
ppy-0.030
working-0.029
Token that
Token ID326
Feature activation+1.62e+00

Pos logit contributions
ement+0.014
uct+0.011
bridge+0.011
 amaz+0.011
aw+0.011
Neg logit contributions
working-0.010
ro-0.010
ny-0.010
 Claus-0.010
ppy-0.010
Token's
Token ID338
Feature activation+1.66e+00

Pos logit contributions
ement+0.067
bridge+0.052
irling+0.052
aw+0.051
uct+0.050
Neg logit contributions
ny-0.039
working-0.038
 Claus-0.037
ppy-0.036
ley-0.035
Token covered
Token ID5017
Feature activation+1.69e+00

Pos logit contributions
ement+0.061
aw+0.047
bridge+0.046
uct+0.044
atted+0.042
Neg logit contributions
working-0.044
 Ho-0.043
gy-0.043
ro-0.042
ny-0.042
Token at
Token ID379
Feature activation+1.53e+00

Pos logit contributions
ement+0.013
 amaz+0.011
bridge+0.011
uct+0.010
aw+0.010
Neg logit contributions
working-0.011
inky-0.010
ny-0.010
ppy-0.010
 Claus-0.010
Token the
Token ID262
Feature activation+1.63e+00

Pos logit contributions
ement+0.044
bridge+0.033
aw+0.032
 swings+0.031
 amaz+0.031
Neg logit contributions
working-0.053
 Claus-0.052
inky-0.051
ny-0.051
ppy-0.051
Token shore
Token ID15191
Feature activation+1.03e+00

Pos logit contributions
ement+0.042
bridge+0.030
aw+0.029
 amaz+0.029
 swings+0.028
Neg logit contributions
working-0.061
 Claus-0.060
inky-0.060
ny-0.059
ppy-0.059
Token.
Token ID13
Feature activation+1.56e+00

Pos logit contributions
ement+0.033
bridge+0.026
 amaz+0.025
irling+0.024
 swings+0.024
Neg logit contributions
working-0.032
ny-0.031
 Claus-0.031
ppy-0.031
inky-0.031
Token They
Token ID1119
Feature activation+6.69e-01

Pos logit contributions
ement+0.073
bridge+0.063
irling+0.061
aw+0.061
 amaz+0.060
Neg logit contributions
ny-0.024
inky-0.024
working-0.024
 Claus-0.023
ppy-0.022
Token see
Token ID766
Feature activation+3.85e+00

Pos logit contributions
ement+0.023
 swings+0.019
bridge+0.019
 sliding+0.019
aw+0.019
Neg logit contributions
inky-0.018
 Claus-0.018
working-0.018
ley-0.017
ppy-0.017
Token sand
Token ID6450
Feature activation+6.78e-01

Pos logit contributions
ement+0.163
uct+0.143
bridge+0.133
irling+0.133
ieved+0.126
Neg logit contributions
 Ho-0.082
 guys-0.077
ny-0.074
y-0.074
ory-0.072
Token,
Token ID11
Feature activation+6.98e-01

Pos logit contributions
ement+0.017
uct+0.012
bridge+0.011
 amaz+0.011
irling+0.011
Neg logit contributions
 Claus-0.026
working-0.025
ny-0.025
inky-0.025
ro-0.025
Token water
Token ID1660
Feature activation+6.22e-01

Pos logit contributions
ement+0.023
bridge+0.016
uct+0.015
irling+0.015
aw+0.015
Neg logit contributions
ny-0.023
ppy-0.023
ro-0.023
working-0.022
 Claus-0.022
Token,
Token ID11
Feature activation+4.33e-01

Pos logit contributions
ement+0.024
bridge+0.019
 amaz+0.019
aw+0.019
uct+0.018
Neg logit contributions
working-0.015
 Claus-0.015
inky-0.015
ny-0.015
ppy-0.014
Token shells
Token ID19679
Feature activation+1.91e-01

Pos logit contributions
ement+0.015
uct+0.010
irling+0.010
bridge+0.010
 amaz+0.010
Neg logit contributions
ro-0.014
ny-0.013
ppy-0.013
working-0.013
 Claus-0.013
Token They
Token ID1119
Feature activation+1.07e+00

Pos logit contributions
ement+0.023
 swings+0.022
aw+0.021
 sliding+0.020
 waves+0.020
Neg logit contributions
 Claus-0.016
working-0.016
ppy-0.016
ley-0.015
pp-0.015
Token have
Token ID423
Feature activation+7.50e-01

Pos logit contributions
ement+0.041
bridge+0.033
aw+0.031
 amaz+0.031
aded+0.031
Neg logit contributions
working-0.028
ny-0.028
 Claus-0.027
ppy-0.027
inky-0.026
Token fun
Token ID1257
Feature activation+9.92e-01

Pos logit contributions
ement+0.035
ined+0.027
irling+0.027
bridge+0.026
cking+0.026
Neg logit contributions
ny-0.015
 guys-0.014
ro-0.013
 while-0.013
 Ho-0.013
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
ement+0.042
 amaz+0.039
bridge+0.038
 cal+0.037
 horrified+0.037
Neg logit contributions
working-0.018
 while-0.016
y-0.015
care-0.014
ro-0.013
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
ement+0.024
 swings+0.022
aw+0.022
 sliding+0.021
 circles+0.020
Neg logit contributions
working-0.016
 Claus-0.016
ley-0.016
ppy-0.016
pp-0.015
Token see
Token ID766
Feature activation+3.84e+00

Pos logit contributions
ement+0.039
bridge+0.032
aw+0.031
 swings+0.031
 amaz+0.031
Neg logit contributions
working-0.030
 Claus-0.029
inky-0.029
ppy-0.028
ny-0.028
Token a
Token ID257
Feature activation+6.23e-01

Pos logit contributions
ement+0.163
irling+0.141
uct+0.140
bridge+0.139
aded+0.139
Neg logit contributions
 Ho-0.068
 Mr-0.063
 guys-0.059
y-0.058
 Th-0.056
Token sees
Token ID7224
Feature activation+2.83e+00

Pos logit contributions
ement+0.020
bridge+0.015
aw+0.015
 amaz+0.014
 swings+0.014
Neg logit contributions
working-0.020
 Claus-0.019
inky-0.019
ny-0.019
ppy-0.019
Tokenaw
Token ID707
Feature activation+1.89e-01

Pos logit contributions
 amaz+0.065
 breathtaking+0.060
 accomplishment+0.060
irling+0.059
ement+0.059
Neg logit contributions
y-0.100
ny-0.091
ro-0.086
s-0.084
ly-0.080
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
ement+0.006
bridge+0.004
 amaz+0.004
aded+0.004
irled+0.004
Neg logit contributions
 Claus-0.006
working-0.006
ny-0.006
inky-0.006
ppy-0.006
Token They
Token ID1119
Feature activation+9.79e-01

Pos logit contributions
ement+0.057
aw+0.049
 swings+0.048
bridge+0.048
 amaz+0.047
Neg logit contributions
working-0.035
 Claus-0.033
ley-0.033
ppy-0.032
ny-0.031
Token flag
Token ID6056
Feature activation+7.75e-01

Pos logit contributions
ement+0.031
uct+0.025
aded+0.025
irling+0.025
 horrified+0.024
Neg logit contributions
working-0.036
ny-0.035
 Claus-0.034
y-0.033
ro-0.033
Token!
Token ID0
Feature activation+1.83e+00

Pos logit contributions
ement+0.022
bridge+0.016
aw+0.016
 amaz+0.016
 swings+0.016
Neg logit contributions
working-0.027
 Claus-0.027
inky-0.027
ny-0.026
ppy-0.026
Token Can
Token ID1680
Feature activation+2.38e+00

Pos logit contributions
ement+0.067
bridge+0.055
aw+0.053
 swings+0.053
 amaz+0.053
Neg logit contributions
working-0.048
 Claus-0.047
inky-0.047
ppy-0.046
ny-0.046
Token we
Token ID356
Feature activation+2.16e+00

Pos logit contributions
ement+0.097
bridge+0.081
aw+0.079
 amaz+0.078
 swings+0.077
Neg logit contributions
 Claus-0.053
working-0.052
inky-0.052
ppy-0.049
ny-0.049
Token go
Token ID467
Feature activation+1.77e+00

Pos logit contributions
ement+0.073
bridge+0.058
 swings+0.056
aw+0.056
 amaz+0.056
Neg logit contributions
working-0.063
 Claus-0.062
inky-0.062
ppy-0.061
ny-0.061
Token see
Token ID766
Feature activation+3.80e+00

Pos logit contributions
ement+0.065
bridge+0.053
 amaz+0.051
aw+0.051
 swings+0.049
Neg logit contributions
 Claus-0.048
working-0.048
ny-0.047
inky-0.046
ppy-0.045
Token it
Token ID340
Feature activation+1.27e+00

Pos logit contributions
ement+0.146
aded+0.128
bridge+0.126
irling+0.124
irled+0.121
Neg logit contributions
 Claus-0.085
 guys-0.080
 Ho-0.073
working-0.073
ory-0.071
Token?"
Token ID1701
Feature activation+8.63e-01

Pos logit contributions
ement+0.042
bridge+0.033
aw+0.032
 amaz+0.032
 swings+0.031
Neg logit contributions
working-0.039
 Claus-0.039
inky-0.038
ny-0.037
ppy-0.037
Token
Token ID198
Feature activation+3.29e-01

Pos logit contributions
ement+0.033
bridge+0.026
 swings+0.026
aw+0.026
 amaz+0.026
Neg logit contributions
working-0.022
 Claus-0.021
inky-0.021
ppy-0.021
ny-0.021
Token
Token ID198
Feature activation+4.48e-01

Pos logit contributions
ement+0.013
bridge+0.010
aw+0.010
 swings+0.010
 amaz+0.010
Neg logit contributions
working-0.008
 Claus-0.008
inky-0.008
ppy-0.008
ny-0.008
TokenMom
Token ID29252
Feature activation+4.48e-01

Pos logit contributions
ement+0.015
bridge+0.012
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.014
 Claus-0.013
inky-0.013
ppy-0.013
ny-0.013
Token was
Token ID373
Feature activation+6.69e-01

Pos logit contributions
ement+0.008
bridge+0.006
 amaz+0.006
irling+0.006
aw+0.006
Neg logit contributions
ny-0.005
working-0.005
y-0.005
ro-0.004
 Claus-0.004
Token gray
Token ID12768
Feature activation+1.38e+00

Pos logit contributions
ement+0.026
bridge+0.020
aw+0.020
 amaz+0.020
irling+0.019
Neg logit contributions
working-0.018
ny-0.017
 Claus-0.017
inky-0.016
 Ho-0.015
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
ement+0.051
bridge+0.042
 amaz+0.042
irling+0.040
uct+0.040
Neg logit contributions
working-0.036
ny-0.036
inky-0.035
 Claus-0.035
ppy-0.033
Token full
Token ID1336
Feature activation+2.94e+00

Pos logit contributions
ement+0.065
bridge+0.050
aw+0.050
 amaz+0.048
aded+0.047
Neg logit contributions
working-0.056
 Claus-0.055
ny-0.055
ppy-0.052
ley-0.051
Token of
Token ID286
Feature activation+2.57e+00

Pos logit contributions
ement+0.115
irling+0.115
cking+0.111
 wounds+0.105
irled+0.101
Neg logit contributions
 while-0.061
y-0.061
ny-0.059
ro-0.057
 They-0.055
Token big
Token ID1263
Feature activation+3.73e+00

Pos logit contributions
ement+0.098
uct+0.083
irling+0.078
ieved+0.076
bridge+0.075
Neg logit contributions
 guys-0.064
working-0.058
 Ho-0.055
ny-0.054
ro-0.053
Token clouds
Token ID15114
Feature activation+1.11e+00

Pos logit contributions
ement+0.127
uct+0.123
bridge+0.114
ieved+0.111
alled+0.111
Neg logit contributions
 guys-0.096
working-0.090
ny-0.089
y-0.087
 Ho-0.086
Token.
Token ID13
Feature activation+7.05e-01

Pos logit contributions
ement+0.041
 amaz+0.035
bridge+0.034
uct+0.033
irling+0.031
Neg logit contributions
working-0.031
ny-0.030
y-0.028
 Claus-0.028
inky-0.027
Token Tim
Token ID5045
Feature activation+1.12e+00

Pos logit contributions
ement+0.029
bridge+0.024
 amaz+0.023
aw+0.023
irling+0.023
Neg logit contributions
working-0.016
inky-0.016
ny-0.015
 Claus-0.015
ppy-0.015
Token saw
Token ID2497
Feature activation+2.21e+00

Pos logit contributions
ement+0.046
bridge+0.038
 amaz+0.037
aw+0.033
uct+0.033
Neg logit contributions
ny-0.029
working-0.028
ppy-0.028
 Claus-0.027
ley-0.026
Token a
Token ID257
Feature activation+1.17e+00

Pos logit contributions
ement+0.112
irling+0.093
uct+0.089
irled+0.085
bridge+0.083
Neg logit contributions
 Ho-0.033
 guys-0.032
working-0.028
 Th-0.028
 Benny-0.028
Token He
Token ID679
Feature activation+6.48e-01

Pos logit contributions
ement+0.039
bridge+0.031
 swings+0.030
aw+0.030
 amaz+0.030
Neg logit contributions
working-0.031
 Claus-0.031
inky-0.031
ppy-0.030
ley-0.030
Token lived
Token ID5615
Feature activation+5.11e-02

Pos logit contributions
ement+0.023
bridge+0.018
 amaz+0.018
aw+0.017
 swings+0.017
Neg logit contributions
working-0.018
 Claus-0.018
ny-0.018
ppy-0.018
inky-0.017
Token in
Token ID287
Feature activation+6.46e-01

Pos logit contributions
ement+0.002
bridge+0.002
 amaz+0.002
aw+0.002
 swings+0.002
Neg logit contributions
working-0.001
ny-0.001
 Claus-0.001
inky-0.001
ppy-0.001
Token a
Token ID257
Feature activation+1.07e+00

Pos logit contributions
ement+0.021
bridge+0.016
aw+0.015
 swings+0.015
 amaz+0.015
Neg logit contributions
working-0.020
 Claus-0.020
inky-0.020
ny-0.020
ppy-0.020
Token big
Token ID1263
Feature activation+2.74e+00

Pos logit contributions
ement+0.034
bridge+0.026
 amaz+0.024
aw+0.024
 swings+0.024
Neg logit contributions
working-0.034
inky-0.034
 Claus-0.034
ny-0.033
ppy-0.033
Token palm
Token ID18057
Feature activation+3.72e+00

Pos logit contributions
ement+0.078
bridge+0.061
aw+0.054
 amaz+0.054
aded+0.053
Neg logit contributions
working-0.095
ny-0.094
 Claus-0.093
inky-0.093
ppy-0.091
Token tree
Token ID5509
Feature activation+7.25e-01

Pos logit contributions
ement+0.114
 amaz+0.097
aded+0.094
bridge+0.092
irling+0.089
Neg logit contributions
working-0.116
ny-0.115
y-0.112
ro-0.112
inky-0.109
Token by
Token ID416
Feature activation-6.30e-01

Pos logit contributions
ement+0.026
bridge+0.021
 amaz+0.021
 swings+0.019
aw+0.019
Neg logit contributions
working-0.021
ny-0.020
 Claus-0.020
inky-0.019
ppy-0.019
Token the
Token ID262
Feature activation+8.63e-01

Pos logit contributions
working+0.021
 Claus+0.021
inky+0.021
ppy+0.021
ny+0.021
Neg logit contributions
ement-0.018
bridge-0.014
 swings-0.014
aw-0.014
 amaz-0.013
Token beach
Token ID10481
Feature activation+8.74e-01

Pos logit contributions
ement+0.020
 swings+0.016
aw+0.015
 amaz+0.014
 sliding+0.014
Neg logit contributions
working-0.034
ppy-0.033
 Claus-0.033
inky-0.033
ley-0.033
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
ement+0.027
bridge+0.021
 amaz+0.020
aw+0.020
 swings+0.020
Neg logit contributions
working-0.028
 Claus-0.028
ny-0.027
inky-0.027
ppy-0.027
Token flag
Token ID6056
Feature activation+1.24e+00

Pos logit contributions
ement+0.021
 swings+0.017
bridge+0.016
aw+0.016
 sliding+0.016
Neg logit contributions
working-0.021
inky-0.020
ppy-0.020
 Claus-0.020
ley-0.020
Token.
Token ID13
Feature activation+5.44e-01

Pos logit contributions
ement+0.047
 amaz+0.041
 wounds+0.037
bridge+0.037
uct+0.037
Neg logit contributions
working-0.032
ny-0.031
y-0.031
 Claus-0.031
inky-0.030
Token It
Token ID632
Feature activation+1.20e+00

Pos logit contributions
ement+0.019
bridge+0.015
aw+0.015
 swings+0.015
 amaz+0.015
Neg logit contributions
working-0.015
 Claus-0.015
inky-0.015
ppy-0.015
ley-0.015
Token was
Token ID373
Feature activation+5.23e-01

Pos logit contributions
ement+0.048
 amaz+0.038
uct+0.037
bridge+0.036
 horror+0.036
Neg logit contributions
ny-0.032
working-0.030
 Claus-0.030
ro-0.029
ley-0.028
Token a
Token ID257
Feature activation+1.33e+00

Pos logit contributions
ement+0.020
bridge+0.015
aw+0.015
 amaz+0.015
irling+0.014
Neg logit contributions
working-0.014
 Claus-0.014
ny-0.014
inky-0.014
 Ho-0.013
Token big
Token ID1263
Feature activation+3.71e+00

Pos logit contributions
ement+0.038
bridge+0.029
aw+0.028
 swings+0.028
 amaz+0.027
Neg logit contributions
working-0.046
 Claus-0.045
inky-0.045
ny-0.044
ppy-0.044
Token flag
Token ID6056
Feature activation+8.10e-01

Pos logit contributions
ement+0.127
bridge+0.103
uct+0.101
aded+0.100
irled+0.098
Neg logit contributions
working-0.109
ny-0.108
 Claus-0.105
inky-0.098
ro-0.098
Token,
Token ID11
Feature activation+1.23e+00

Pos logit contributions
ement+0.027
 amaz+0.022
bridge+0.021
aded+0.021
irled+0.020
Neg logit contributions
working-0.025
 Claus-0.024
ny-0.024
inky-0.023
ley-0.023
Token with
Token ID351
Feature activation+1.64e+00

Pos logit contributions
ement+0.047
bridge+0.036
aded+0.035
uct+0.035
 amaz+0.035
Neg logit contributions
working-0.032
 Claus-0.031
ny-0.031
ro-0.030
inky-0.028
Token bright
Token ID6016
Feature activation+2.90e+00

Pos logit contributions
ement+0.060
irling+0.044
uct+0.044
bridge+0.043
 cal+0.042
Neg logit contributions
working-0.045
ny-0.043
 Claus-0.043
inky-0.042
 Ho-0.041
Token colors
Token ID7577
Feature activation+1.82e+00

Pos logit contributions
ement+0.094
uct+0.092
 horrified+0.085
 furious+0.084
 cal+0.082
Neg logit contributions
y-0.071
working-0.070
ny-0.068
ro-0.067
 guys-0.066
TokenYes
Token ID5297
Feature activation+1.14e+00

Pos logit contributions
ement+0.010
aw+0.007
bridge+0.007
 swings+0.007
 sliding+0.007
Neg logit contributions
working-0.014
 Claus-0.014
inky-0.013
ppy-0.013
ley-0.013
Token,
Token ID11
Feature activation+1.79e+00

Pos logit contributions
ement+0.045
bridge+0.038
 amaz+0.037
 swings+0.037
aw+0.037
Neg logit contributions
inky-0.026
ppy-0.026
working-0.026
ny-0.026
 Claus-0.025
Token let
Token ID1309
Feature activation+6.35e-01

Pos logit contributions
ement+0.079
irling+0.066
irled+0.065
bridge+0.064
aded+0.064
Neg logit contributions
ppy-0.035
ny-0.035
 Claus-0.033
working-0.033
inky-0.033
Token's
Token ID338
Feature activation+1.34e+00

Pos logit contributions
ement+0.024
bridge+0.019
 amaz+0.019
irling+0.018
 sliding+0.018
Neg logit contributions
ny-0.017
inky-0.017
working-0.017
 Claus-0.016
ppy-0.016
Token go
Token ID467
Feature activation+1.04e+00

Pos logit contributions
ement+0.048
bridge+0.038
aw+0.038
 swings+0.037
 amaz+0.037
Neg logit contributions
working-0.037
 Claus-0.036
inky-0.036
ny-0.035
ppy-0.035
Token find
Token ID1064
Feature activation+3.64e+00

Pos logit contributions
ement+0.038
bridge+0.031
 amaz+0.030
aw+0.029
 swings+0.028
Neg logit contributions
working-0.029
ny-0.029
 Claus-0.028
inky-0.028
ppy-0.027
Token them
Token ID606
Feature activation+1.64e+00

Pos logit contributions
ement+0.134
irling+0.124
bridge+0.113
uct+0.113
irled+0.111
Neg logit contributions
 guys-0.088
 Ho-0.080
 Ros-0.079
 Penny-0.077
 Benny-0.075
Token!"
Token ID2474
Feature activation+1.72e+00

Pos logit contributions
ement+0.057
bridge+0.045
 amaz+0.044
aw+0.043
aded+0.042
Neg logit contributions
 Claus-0.048
working-0.047
inky-0.047
ppy-0.046
ny-0.046
Token
Token ID198
Feature activation+5.07e-01

Pos logit contributions
ement+0.068
bridge+0.055
aw+0.054
 swings+0.054
 amaz+0.054
Neg logit contributions
working-0.041
 Claus-0.040
inky-0.040
ppy-0.039
ny-0.039
Token
Token ID198
Feature activation+1.19e+00

Pos logit contributions
ement+0.020
bridge+0.017
 amaz+0.016
 swings+0.016
aw+0.016
Neg logit contributions
inky-0.012
working-0.011
 Claus-0.011
ny-0.011
ppy-0.011
TokenSu
Token ID5606
Feature activation+1.75e+00

Pos logit contributions
ement+0.043
bridge+0.035
 amaz+0.033
 soaring+0.032
aw+0.031
Neg logit contributions
working-0.032
inky-0.032
ny-0.032
 Claus-0.031
ppy-0.031
Token naughty
Token ID45128
Feature activation+1.07e-01

Pos logit contributions
ley+0.015
inky+0.014
 Claus+0.014
working+0.014
ppy+0.014
Neg logit contributions
ement-0.012
 sliding-0.012
 swings-0.011
 soaring-0.011
 swinging-0.011
Token.
Token ID13
Feature activation+3.26e-01

Pos logit contributions
ement+0.003
bridge+0.002
aw+0.002
 swings+0.002
 amaz+0.002
Neg logit contributions
working-0.004
 Claus-0.003
inky-0.003
ppy-0.003
ny-0.003
Token They
Token ID1119
Feature activation+2.88e-02

Pos logit contributions
ement+0.012
 amaz+0.011
 swings+0.011
aw+0.011
 sliding+0.010
Neg logit contributions
working-0.008
ley-0.008
ppy-0.008
 Claus-0.007
ny-0.007
Token liked
Token ID8288
Feature activation-4.64e-01

Pos logit contributions
ement+0.001
bridge+0.001
 amaz+0.001
aw+0.001
irling+0.001
Neg logit contributions
working-0.001
 Claus-0.001
ny-0.001
ppy-0.001
inky-0.001
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
working+0.012
 Claus+0.011
inky+0.011
ny+0.011
ppy+0.011
Neg logit contributions
ement-0.018
bridge-0.015
aw-0.014
 amaz-0.014
 swings-0.014
Token palm
Token ID18057
Feature activation+3.63e+00

Pos logit contributions
ement+0.041
irling+0.034
irled+0.033
aded+0.033
aw+0.033
Neg logit contributions
working-0.032
ny-0.031
 Claus-0.029
ro-0.029
 guys-0.029
Token tree
Token ID5509
Feature activation+1.50e+00

Pos logit contributions
ement+0.126
aded+0.118
 amaz+0.115
irling+0.112
aming+0.109
Neg logit contributions
ny-0.098
ro-0.094
working-0.093
y-0.091
 Claus-0.079
Token and
Token ID290
Feature activation-1.83e-01

Pos logit contributions
ement+0.050
bridge+0.040
aded+0.038
 amaz+0.038
irling+0.038
Neg logit contributions
 Claus-0.045
ny-0.044
working-0.044
inky-0.043
ppy-0.043
Token the
Token ID262
Feature activation+7.72e-01

Pos logit contributions
working+0.006
 Claus+0.006
ppy+0.006
inky+0.006
ny+0.006
Neg logit contributions
ement-0.006
bridge-0.005
aw-0.004
 amaz-0.004
 swings-0.004
Token garden
Token ID11376
Feature activation+1.21e+00

Pos logit contributions
ement+0.024
bridge+0.018
irled+0.017
aw+0.017
irling+0.017
Neg logit contributions
working-0.025
 Claus-0.025
ny-0.025
inky-0.024
ro-0.024
Token.
Token ID13
Feature activation+5.59e-01

Pos logit contributions
ement+0.043
irling+0.036
uct+0.035
aded+0.035
bridge+0.035
Neg logit contributions
ny-0.032
 Claus-0.032
ro-0.031
working-0.031
ppy-0.030
TokenSure
Token ID19457
Feature activation+4.69e-01

Pos logit contributions
ement+0.007
bridge+0.006
 amaz+0.006
 swings+0.006
aw+0.006
Neg logit contributions
working-0.006
ny-0.006
 Claus-0.006
inky-0.006
ppy-0.006
Token,
Token ID11
Feature activation-6.38e-01

Pos logit contributions
ement+0.019
bridge+0.017
 amaz+0.016
 swings+0.016
aw+0.016
Neg logit contributions
working-0.010
inky-0.010
ny-0.010
 Claus-0.010
ppy-0.010
Token let
Token ID1309
Feature activation+1.14e+00

Pos logit contributions
ppy+0.015
inky+0.014
 Claus+0.014
ny+0.014
working+0.014
Neg logit contributions
ement-0.026
bridge-0.021
aw-0.021
 amaz-0.020
irling-0.020
Token's
Token ID338
Feature activation+1.28e+00

Pos logit contributions
ement+0.046
bridge+0.040
 amaz+0.038
irling+0.036
 sliding+0.035
Neg logit contributions
ny-0.028
inky-0.027
ley-0.026
ppy-0.026
 Claus-0.025
Token go
Token ID467
Feature activation+7.49e-01

Pos logit contributions
ement+0.048
bridge+0.038
aw+0.037
irling+0.036
 amaz+0.036
Neg logit contributions
working-0.034
 Claus-0.034
inky-0.033
ny-0.033
ppy-0.032
Token see
Token ID766
Feature activation+3.62e+00

Pos logit contributions
ement+0.029
bridge+0.023
 amaz+0.023
aw+0.022
 swings+0.021
Neg logit contributions
ny-0.020
working-0.019
 Claus-0.019
inky-0.019
ppy-0.019
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
ement+0.146
bridge+0.132
irling+0.123
irled+0.123
aded+0.121
Neg logit contributions
 Ho-0.073
 Claus-0.072
ppy-0.069
 guys-0.068
y-0.067
Token bird
Token ID6512
Feature activation+8.66e-01

Pos logit contributions
ement+0.043
irling+0.036
irled+0.036
bridge+0.035
atted+0.034
Neg logit contributions
working-0.035
 Claus-0.035
ny-0.033
inky-0.033
 guys-0.031
Token."
Token ID526
Feature activation-3.60e-01

Pos logit contributions
ement+0.031
bridge+0.024
 amaz+0.024
aw+0.023
aded+0.023
Neg logit contributions
 Claus-0.025
ny-0.024
working-0.024
ppy-0.024
inky-0.024
Token But
Token ID887
Feature activation-6.38e-01

Pos logit contributions
working+0.009
 Claus+0.008
ley+0.008
ppy+0.007
inky+0.007
Neg logit contributions
ement-0.015
 swings-0.012
aw-0.012
bridge-0.012
 amaz-0.012
Token as
Token ID355
Feature activation-3.38e-02

Pos logit contributions
working+0.019
 Claus+0.019
inky+0.019
ny+0.018
ppy+0.017
Neg logit contributions
ement-0.021
 sliding-0.017
 swings-0.017
irled-0.016
uct-0.016
Token,
Token ID11
Feature activation-5.79e-01

Pos logit contributions
ement+0.014
 sliding+0.011
 amaz+0.010
 soaring+0.010
 swings+0.010
Neg logit contributions
working-0.014
 Claus-0.014
ley-0.014
ppy-0.014
inky-0.014
Token there
Token ID612
Feature activation-1.24e-01

Pos logit contributions
working+0.023
 Claus+0.023
inky+0.023
ley+0.023
ppy+0.022
Neg logit contributions
ement-0.013
bridge-0.009
 sliding-0.009
aw-0.009
 swings-0.009
Token was
Token ID373
Feature activation-4.06e-01

Pos logit contributions
ny+0.004
working+0.004
inky+0.004
 Claus+0.003
ppy+0.003
Neg logit contributions
ement-0.004
bridge-0.003
aw-0.003
irling-0.003
 swings-0.003
Token a
Token ID257
Feature activation+7.16e-01

Pos logit contributions
working+0.012
inky+0.011
ny+0.011
 Claus+0.011
ppy+0.011
Neg logit contributions
ement-0.014
bridge-0.011
 amaz-0.011
irling-0.010
aw-0.010
Token big
Token ID1263
Feature activation+2.27e+00

Pos logit contributions
ement+0.022
 swings+0.018
aw+0.018
bridge+0.018
 sliding+0.017
Neg logit contributions
working-0.022
inky-0.021
ppy-0.021
 Claus-0.021
ley-0.021
Token palm
Token ID18057
Feature activation+3.58e+00

Pos logit contributions
ement+0.071
bridge+0.055
 swings+0.054
aw+0.054
 amaz+0.053
Neg logit contributions
working-0.071
 Claus-0.070
inky-0.070
ppy-0.069
ny-0.069
Token tree
Token ID5509
Feature activation+1.07e+00

Pos logit contributions
ement+0.106
 amaz+0.093
aded+0.087
bridge+0.084
irled+0.083
Neg logit contributions
working-0.117
ny-0.113
ro-0.110
y-0.109
inky-0.109
Token in
Token ID287
Feature activation+3.55e-02

Pos logit contributions
ement+0.039
 amaz+0.032
bridge+0.032
aded+0.029
 swings+0.029
Neg logit contributions
working-0.030
ny-0.029
 Claus-0.029
inky-0.029
ro-0.027
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
ement+0.001
bridge+0.001
aw+0.001
irling+0.001
irled+0.001
Neg logit contributions
working-0.001
ny-0.001
 Claus-0.001
ley-0.001
ppy-0.001
Token middle
Token ID3504
Feature activation+1.66e+00

Pos logit contributions
ement+0.039
bridge+0.030
irling+0.027
irled+0.027
 amaz+0.026
Neg logit contributions
working-0.040
ny-0.040
inky-0.039
 Claus-0.038
ppy-0.037
Token of
Token ID286
Feature activation+1.84e-02

Pos logit contributions
ement+0.060
 wounds+0.053
irling+0.053
 furious+0.052
 accomplishment+0.051
Neg logit contributions
y-0.044
ny-0.039
ro-0.036
working-0.033
s-0.031
Token a
Token ID257
Feature activation+1.17e+00

Pos logit contributions
ement+0.026
irling+0.019
uct+0.019
 amaz+0.018
irled+0.018
Neg logit contributions
ny-0.012
working-0.012
 Claus-0.012
 guys-0.011
inky-0.011
Token big
Token ID1263
Feature activation+2.82e+00

Pos logit contributions
ement+0.038
bridge+0.029
uct+0.028
aw+0.028
 amaz+0.027
Neg logit contributions
working-0.037
 Claus-0.037
inky-0.036
ny-0.035
ley-0.034
Token anchor
Token ID18021
Feature activation+9.18e-01

Pos logit contributions
ement+0.089
uct+0.073
bridge+0.072
aw+0.067
aming+0.065
Neg logit contributions
working-0.088
 Claus-0.085
ny-0.084
inky-0.084
ley-0.081
Token on
Token ID319
Feature activation+1.31e+00

Pos logit contributions
ement+0.031
 amaz+0.024
bridge+0.023
uct+0.023
 cal+0.022
Neg logit contributions
working-0.029
 Claus-0.028
inky-0.027
ny-0.027
ley-0.026
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
ement+0.043
bridge+0.033
aw+0.032
 amaz+0.031
uct+0.031
Neg logit contributions
working-0.041
ny-0.039
inky-0.039
 Claus-0.039
ley-0.038
Token front
Token ID2166
Feature activation+3.57e+00

Pos logit contributions
ement+0.044
bridge+0.033
 amaz+0.032
aw+0.031
irling+0.031
Neg logit contributions
working-0.045
 Claus-0.045
ny-0.044
inky-0.044
ley-0.043
Token,
Token ID11
Feature activation+1.12e+00

Pos logit contributions
ement+0.122
irling+0.103
irled+0.101
uct+0.100
aded+0.095
Neg logit contributions
ny-0.099
ro-0.099
working-0.097
inky-0.092
 Claus-0.092
Token to
Token ID284
Feature activation+8.04e-01

Pos logit contributions
ement+0.036
bridge+0.027
aw+0.026
 amaz+0.026
irling+0.025
Neg logit contributions
working-0.036
 Claus-0.035
ny-0.034
inky-0.034
ley-0.033
Token help
Token ID1037
Feature activation-5.08e-01

Pos logit contributions
ement+0.028
bridge+0.021
aw+0.021
 amaz+0.021
 swings+0.021
Neg logit contributions
working-0.024
 Claus-0.023
ny-0.022
ppy-0.022
inky-0.022
Token it
Token ID340
Feature activation+1.61e-01

Pos logit contributions
working+0.019
 Claus+0.019
inky+0.018
ppy+0.018
ley+0.018
Neg logit contributions
ement-0.012
aw-0.010
 swings-0.010
 waves-0.009
bridge-0.009
Token stay
Token ID2652
Feature activation+3.41e-01

Pos logit contributions
ement+0.006
aw+0.005
bridge+0.005
 amaz+0.005
irling+0.005
Neg logit contributions
working-0.004
 Claus-0.004
ny-0.004
inky-0.004
ppy-0.004
TokenYes
Token ID5297
Feature activation+4.89e-01

Pos logit contributions
ement+0.002
bridge+0.001
aw+0.001
 swings+0.001
 amaz+0.001
Neg logit contributions
working-0.002
 Claus-0.002
inky-0.002
ppy-0.002
ny-0.002
Token,
Token ID11
Feature activation-2.76e-02

Pos logit contributions
ement+0.020
bridge+0.017
 amaz+0.016
 swings+0.016
aw+0.016
Neg logit contributions
inky-0.011
working-0.011
ppy-0.011
ny-0.010
 Claus-0.010
Token we
Token ID356
Feature activation-7.95e-02

Pos logit contributions
ppy+0.001
inky+0.001
 Claus+0.001
ny+0.001
working+0.001
Neg logit contributions
ement-0.001
bridge-0.001
 amaz-0.001
irling-0.001
aw-0.001
Token can
Token ID460
Feature activation+1.82e+00

Pos logit contributions
working+0.002
inky+0.002
 Claus+0.002
ppy+0.002
ley+0.002
Neg logit contributions
ement-0.003
bridge-0.002
aw-0.002
 swings-0.002
 amaz-0.002
Token go
Token ID467
Feature activation+8.46e-01

Pos logit contributions
ement+0.067
bridge+0.055
aw+0.053
 amaz+0.052
irling+0.051
Neg logit contributions
working-0.049
 Claus-0.048
inky-0.048
ny-0.047
ppy-0.045
Token see
Token ID766
Feature activation+3.56e+00

Pos logit contributions
ement+0.031
bridge+0.025
 amaz+0.024
aw+0.024
 swings+0.024
Neg logit contributions
working-0.023
 Claus-0.023
inky-0.022
ny-0.022
ppy-0.022
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
ement+0.134
aded+0.120
bridge+0.117
irling+0.117
irled+0.116
Neg logit contributions
 Claus-0.075
 guys-0.074
working-0.071
y-0.070
 Ho-0.067
Token sunset
Token ID26428
Feature activation-3.07e-01

Pos logit contributions
ement+0.039
irling+0.034
irled+0.034
aded+0.034
atted+0.034
Neg logit contributions
working-0.037
 Claus-0.035
ny-0.033
 guys-0.033
y-0.032
Token."
Token ID526
Feature activation-5.50e-01

Pos logit contributions
working+0.010
 Claus+0.010
inky+0.009
ny+0.009
ppy+0.009
Neg logit contributions
ement-0.010
bridge-0.008
 amaz-0.007
aw-0.007
 swings-0.007
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
working+0.016
 Claus+0.015
ppy+0.015
inky+0.015
ley+0.015
Neg logit contributions
ement-0.019
 swings-0.015
aw-0.015
bridge-0.015
 amaz-0.015
Token
Token ID198
Feature activation-8.72e-01

Pos logit contributions
working+0.024
inky+0.024
 Claus+0.024
ny+0.024
ppy+0.023
Neg logit contributions
ement-0.041
bridge-0.034
 amaz-0.033
 swings-0.033
aw-0.033
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
inky+0.002
 Claus+0.002
ppy+0.002
working+0.002
ny+0.002
Neg logit contributions
ement-0.002
bridge-0.002
aw-0.002
 sliding-0.002
 swings-0.002
Token he
Token ID339
Feature activation-6.57e-02

Pos logit contributions
ement+0.008
bridge+0.006
 swings+0.006
 amaz+0.006
 sliding+0.006
Neg logit contributions
inky-0.007
ppy-0.007
 Claus-0.007
ny-0.007
working-0.007
Token wanted
Token ID2227
Feature activation+5.81e-01

Pos logit contributions
working+0.002
inky+0.002
 Claus+0.002
ppy+0.002
ny+0.002
Neg logit contributions
ement-0.002
bridge-0.002
aw-0.002
 swings-0.002
 amaz-0.002
Token to
Token ID284
Feature activation+1.39e+00

Pos logit contributions
ement+0.024
bridge+0.020
 amaz+0.019
aw+0.019
irling+0.019
Neg logit contributions
working-0.013
 Claus-0.013
ny-0.013
ppy-0.012
inky-0.012
Token give
Token ID1577
Feature activation+9.16e-01

Pos logit contributions
ement+0.057
bridge+0.046
aw+0.045
 amaz+0.043
irling+0.043
Neg logit contributions
working-0.032
 Claus-0.031
ny-0.031
inky-0.031
ppy-0.031
Token his
Token ID465
Feature activation+3.55e+00

Pos logit contributions
ement+0.030
bridge+0.024
 amaz+0.022
aw+0.022
 swings+0.022
Neg logit contributions
working-0.028
 Claus-0.028
ny-0.028
inky-0.027
ppy-0.027
Token dad
Token ID9955
Feature activation-2.60e-01

Pos logit contributions
ement+0.139
bridge+0.130
uct+0.116
aw+0.114
cking+0.114
Neg logit contributions
working-0.081
 Claus-0.079
ory-0.078
by-0.075
ny-0.072
Token a
Token ID257
Feature activation+5.00e-01

Pos logit contributions
inky+0.009
working+0.009
 Claus+0.009
ley+0.009
ro+0.009
Neg logit contributions
ement-0.007
aw-0.005
 swings-0.005
bridge-0.005
 amaz-0.005
Token big
Token ID1263
Feature activation+1.43e+00

Pos logit contributions
ement+0.016
bridge+0.012
aw+0.012
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.016
 Claus-0.016
inky-0.016
ny-0.016
ppy-0.015
Token hug
Token ID16225
Feature activation-4.92e-02

Pos logit contributions
ement+0.048
bridge+0.039
aw+0.038
irling+0.037
 swings+0.037
Neg logit contributions
working-0.042
ny-0.041
 Claus-0.041
inky-0.040
ley-0.039
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
working+0.002
inky+0.002
 Claus+0.002
ppy+0.002
ny+0.002
Neg logit contributions
ement-0.001
bridge-0.001
aw-0.001
 swings-0.001
 amaz-0.001
Token shore
Token ID15191
Feature activation-3.61e-01

Pos logit contributions
ement+0.014
bridge+0.011
uct+0.010
 amaz+0.010
pled+0.010
Neg logit contributions
ny-0.013
working-0.013
ro-0.012
 Claus-0.012
ory-0.012
Token,
Token ID11
Feature activation-3.45e-02

Pos logit contributions
inky+0.010
 Claus+0.010
working+0.010
ppy+0.010
ny+0.010
Neg logit contributions
ement-0.013
 swings-0.010
bridge-0.010
aw-0.010
 sliding-0.010
Token Lily
Token ID20037
Feature activation+6.64e-01

Pos logit contributions
inky+0.001
ny+0.001
 Claus+0.001
ppy+0.001
working+0.001
Neg logit contributions
ement-0.001
 swings-0.001
 sliding-0.001
bridge-0.001
aw-0.001
Token saw
Token ID2497
Feature activation+2.16e+00

Pos logit contributions
ement+0.025
bridge+0.020
 amaz+0.020
aw+0.019
uct+0.018
Neg logit contributions
working-0.018
 Claus-0.018
ppy-0.017
ny-0.017
ley-0.017
Token a
Token ID257
Feature activation+6.81e-01

Pos logit contributions
ement+0.091
uct+0.074
irling+0.072
bridge+0.070
 amaz+0.068
Neg logit contributions
 Ho-0.046
working-0.044
 Claus-0.041
 Cotton-0.041
 Penny-0.041
Token palm
Token ID18057
Feature activation+3.53e+00

Pos logit contributions
ement+0.017
 swings+0.013
aw+0.013
 amaz+0.013
bridge+0.013
Neg logit contributions
working-0.025
ppy-0.025
inky-0.025
ley-0.024
 Claus-0.024
Token tree
Token ID5509
Feature activation+6.83e-01

Pos logit contributions
ement+0.111
 amaz+0.096
aded+0.095
irled+0.090
bridge+0.088
Neg logit contributions
working-0.104
ny-0.101
ro-0.100
y-0.100
 Claus-0.094
Token waving
Token ID25849
Feature activation+8.07e-01

Pos logit contributions
ement+0.024
bridge+0.020
 amaz+0.019
aded+0.019
irled+0.018
Neg logit contributions
working-0.019
ny-0.018
 Claus-0.018
inky-0.018
ro-0.017
Token in
Token ID287
Feature activation+9.52e-01

Pos logit contributions
ement+0.031
irling+0.025
bridge+0.025
uct+0.024
 swings+0.024
Neg logit contributions
ny-0.020
working-0.020
y-0.019
ro-0.018
ppy-0.018
Token the
Token ID262
Feature activation+1.17e+00

Pos logit contributions
ement+0.035
bridge+0.030
irled+0.028
irling+0.027
aded+0.027
Neg logit contributions
ro-0.024
ny-0.024
 Ho-0.024
working-0.022
ory-0.022
Token wind
Token ID2344
Feature activation-1.64e-01

Pos logit contributions
ement+0.035
bridge+0.026
irling+0.026
irled+0.025
 amaz+0.024
Neg logit contributions
ny-0.040
working-0.039
ro-0.038
 Claus-0.038
ley-0.038
Token a
Token ID257
Feature activation+6.80e-01

Pos logit contributions
working+0.020
inky+0.020
 Claus+0.020
ny+0.019
ppy+0.019
Neg logit contributions
ement-0.023
bridge-0.017
 amaz-0.017
aw-0.017
 swings-0.016
Token little
Token ID1310
Feature activation+1.09e-01

Pos logit contributions
ement+0.021
 swings+0.017
bridge+0.017
aw+0.017
 sliding+0.016
Neg logit contributions
working-0.021
inky-0.020
ppy-0.020
 Claus-0.020
ley-0.020
Token boat
Token ID8848
Feature activation+7.97e-01

Pos logit contributions
ement+0.003
 swings+0.003
aw+0.003
 waves+0.003
 sliding+0.003
Neg logit contributions
inky-0.003
working-0.003
 Claus-0.003
ppy-0.003
ro-0.003
Token with
Token ID351
Feature activation+4.86e-01

Pos logit contributions
ement+0.030
 amaz+0.024
bridge+0.023
uct+0.022
 swings+0.022
Neg logit contributions
working-0.023
 Claus-0.022
ny-0.022
inky-0.021
ley-0.020
Token a
Token ID257
Feature activation+1.54e+00

Pos logit contributions
ement+0.019
uct+0.014
irling+0.014
bridge+0.014
 cal+0.013
Neg logit contributions
working-0.013
inky-0.012
 Claus-0.012
 Ho-0.012
ny-0.012
Token big
Token ID1263
Feature activation+3.53e+00

Pos logit contributions
ement+0.052
bridge+0.040
uct+0.040
aw+0.039
 amaz+0.037
Neg logit contributions
 Claus-0.047
working-0.047
inky-0.046
ny-0.045
ley-0.043
Token sail
Token ID14936
Feature activation+7.63e-01

Pos logit contributions
ement+0.114
uct+0.098
bridge+0.096
aw+0.089
aming+0.088
Neg logit contributions
working-0.105
 Claus-0.103
ny-0.103
inky-0.101
ley-0.098
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
ement+0.027
 amaz+0.023
uct+0.021
irling+0.021
bridge+0.021
Neg logit contributions
working-0.022
ny-0.022
 Claus-0.021
inky-0.021
ley-0.021
Token The
Token ID383
Feature activation+6.20e-01

Pos logit contributions
ement+0.009
bridge+0.007
 swings+0.007
 amaz+0.007
aw+0.007
Neg logit contributions
working-0.007
ppy-0.007
inky-0.007
 Claus-0.007
ley-0.007
Token boat
Token ID8848
Feature activation+1.11e+00

Pos logit contributions
ement+0.025
uct+0.020
 amaz+0.019
irling+0.019
aw+0.019
Neg logit contributions
ny-0.016
 Claus-0.016
inky-0.015
working-0.015
 guys-0.015
Token sailed
Token ID33835
Feature activation-3.31e-01

Pos logit contributions
ement+0.048
 amaz+0.041
uct+0.039
bridge+0.039
irling+0.038
Neg logit contributions
ny-0.026
 Claus-0.026
working-0.025
ley-0.022
gy-0.022
Token to
Token ID284
Feature activation+2.25e-01

Pos logit contributions
ement+0.002
 sliding+0.001
 swings+0.001
 soaring+0.001
bridge+0.001
Neg logit contributions
ppy-0.002
 Claus-0.002
inky-0.002
working-0.002
ley-0.002
Token the
Token ID262
Feature activation+1.56e+00

Pos logit contributions
ement+0.007
bridge+0.006
aw+0.006
irling+0.005
 amaz+0.005
Neg logit contributions
working-0.007
 Claus-0.007
ny-0.007
inky-0.007
ppy-0.007
Token beach
Token ID10481
Feature activation+6.94e-01

Pos logit contributions
ement+0.040
bridge+0.029
 swings+0.029
aw+0.029
 amaz+0.028
Neg logit contributions
working-0.058
 Claus-0.057
inky-0.057
ppy-0.056
ny-0.056
Token.
Token ID13
Feature activation+7.19e-01

Pos logit contributions
ement+0.027
bridge+0.022
 amaz+0.021
aw+0.021
uct+0.021
Neg logit contributions
working-0.017
ny-0.016
 Claus-0.016
ro-0.016
ory-0.016
Token They
Token ID1119
Feature activation+7.27e-01

Pos logit contributions
ement+0.027
 swings+0.023
 amaz+0.023
bridge+0.022
 sliding+0.022
Neg logit contributions
 Claus-0.018
inky-0.018
ppy-0.017
working-0.017
ley-0.017
Token saw
Token ID2497
Feature activation+3.52e+00

Pos logit contributions
ement+0.027
bridge+0.022
aw+0.021
 amaz+0.021
 swings+0.020
Neg logit contributions
working-0.020
 Claus-0.019
ny-0.019
ppy-0.019
ley-0.018
Token a
Token ID257
Feature activation+8.24e-01

Pos logit contributions
ement+0.148
irling+0.130
uct+0.125
bridge+0.120
irled+0.115
Neg logit contributions
 Ho-0.069
ory-0.063
 guys-0.062
working-0.061
 Penny-0.060
Token boat
Token ID8848
Feature activation+5.16e-01

Pos logit contributions
ement+0.023
bridge+0.017
 swings+0.017
aw+0.016
 amaz+0.016
Neg logit contributions
working-0.029
 Claus-0.029
inky-0.029
ppy-0.028
ny-0.028
Token and
Token ID290
Feature activation+1.74e+00

Pos logit contributions
ement+0.018
bridge+0.015
 amaz+0.015
uct+0.014
irled+0.014
Neg logit contributions
 Claus-0.014
working-0.014
ny-0.014
inky-0.013
ley-0.013
Token wanted
Token ID2227
Feature activation+1.50e+00

Pos logit contributions
ement+0.059
bridge+0.046
aw+0.044
 amaz+0.044
 swings+0.044
Neg logit contributions
working-0.052
 Claus-0.051
inky-0.050
ny-0.050
ppy-0.050
Token to
Token ID284
Feature activation+1.94e+00

Pos logit contributions
ement+0.080
bridge+0.069
irling+0.068
 amaz+0.065
irled+0.065
Neg logit contributions
working-0.018
ny-0.016
 Claus-0.015
 guys-0.014
by-0.014
Token beautiful
Token ID4950
Feature activation+2.39e-01

Pos logit contributions
ement+0.026
 swings+0.021
bridge+0.020
aw+0.020
 sliding+0.020
Neg logit contributions
working-0.029
inky-0.028
ppy-0.028
 Claus-0.028
ley-0.028
Token butterfly
Token ID35113
Feature activation+9.42e-01

Pos logit contributions
ement+0.007
 swings+0.005
bridge+0.005
aw+0.005
 amaz+0.005
Neg logit contributions
working-0.008
ppy-0.008
 Claus-0.008
inky-0.008
ny-0.008
Token.
Token ID13
Feature activation+3.28e-01

Pos logit contributions
ement+0.032
 amaz+0.026
bridge+0.025
aded+0.024
uct+0.023
Neg logit contributions
working-0.028
inky-0.028
ny-0.028
 Claus-0.027
ppy-0.027
Token It
Token ID632
Feature activation+5.73e-01

Pos logit contributions
ement+0.010
bridge+0.008
 swings+0.008
 amaz+0.008
aw+0.008
Neg logit contributions
 Claus-0.010
ley-0.010
ppy-0.010
inky-0.010
working-0.010
Token had
Token ID550
Feature activation+5.47e-01

Pos logit contributions
ement+0.022
 amaz+0.018
bridge+0.017
aw+0.016
uct+0.016
Neg logit contributions
ny-0.015
working-0.015
ppy-0.015
 Claus-0.014
inky-0.014
Token big
Token ID1263
Feature activation+3.51e+00

Pos logit contributions
ement+0.022
irling+0.016
bridge+0.016
 amaz+0.016
uct+0.016
Neg logit contributions
working-0.013
inky-0.013
ny-0.013
ro-0.013
 Ho-0.013
Token,
Token ID11
Feature activation+1.43e+00

Pos logit contributions
ement+0.110
bridge+0.094
uct+0.092
aming+0.084
aded+0.083
Neg logit contributions
working-0.106
inky-0.103
 Ho-0.101
ro-0.098
ny-0.098
Token colorful
Token ID20239
Feature activation+2.49e+00

Pos logit contributions
ement+0.046
bridge+0.035
 amaz+0.034
aw+0.033
aded+0.033
Neg logit contributions
working-0.046
inky-0.043
ny-0.043
 Claus-0.043
ro-0.042
Token wings
Token ID12098
Feature activation+7.93e-01

Pos logit contributions
ement+0.074
uct+0.058
bridge+0.057
 horrified+0.054
 amaz+0.054
Neg logit contributions
inky-0.083
ro-0.081
working-0.081
 Ho-0.078
ny-0.077
Token.
Token ID13
Feature activation+9.67e-01

Pos logit contributions
ement+0.026
 amaz+0.021
bridge+0.021
 swings+0.020
uct+0.019
Neg logit contributions
working-0.024
ny-0.023
inky-0.023
 Claus-0.023
ppy-0.023
Token The
Token ID383
Feature activation+1.54e+00

Pos logit contributions
ement+0.038
bridge+0.031
 amaz+0.030
aw+0.030
irling+0.030
Neg logit contributions
working-0.023
 Claus-0.023
inky-0.022
ny-0.022
ppy-0.022
Token bird
Token ID6512
Feature activation+1.07e+00

Pos logit contributions
ement+0.075
irling+0.062
aded+0.062
uct+0.061
bridge+0.060
Neg logit contributions
working-0.074
ny-0.073
y-0.071
 guys-0.070
 Claus-0.069
Token!
Token ID0
Feature activation+1.52e+00

Pos logit contributions
ement+0.035
bridge+0.028
 amaz+0.028
aded+0.026
 swings+0.025
Neg logit contributions
ny-0.033
 Claus-0.032
ppy-0.032
working-0.032
inky-0.032
Token Can
Token ID1680
Feature activation+2.35e+00

Pos logit contributions
ement+0.055
bridge+0.044
 swings+0.043
aw+0.043
 amaz+0.043
Neg logit contributions
working-0.042
 Claus-0.040
inky-0.040
ppy-0.040
ny-0.039
Token we
Token ID356
Feature activation+1.89e+00

Pos logit contributions
ement+0.097
bridge+0.082
aw+0.079
 amaz+0.079
irling+0.077
Neg logit contributions
 Claus-0.052
working-0.051
inky-0.050
ppy-0.048
ny-0.047
Token go
Token ID467
Feature activation+1.67e+00

Pos logit contributions
ement+0.058
 swings+0.046
bridge+0.045
aw+0.045
 sliding+0.045
Neg logit contributions
working-0.059
 Claus-0.057
inky-0.057
ppy-0.057
ley-0.057
Token see
Token ID766
Feature activation+3.50e+00

Pos logit contributions
ement+0.063
bridge+0.051
 amaz+0.050
aw+0.049
 swings+0.047
Neg logit contributions
working-0.044
 Claus-0.044
ny-0.043
inky-0.042
ppy-0.042
Token it
Token ID340
Feature activation+1.35e+00

Pos logit contributions
ement+0.131
bridge+0.113
aded+0.109
irling+0.109
irled+0.108
Neg logit contributions
 Claus-0.084
 guys-0.079
 Ho-0.078
working-0.076
ppy-0.074
Token?"
Token ID1701
Feature activation+1.11e+00

Pos logit contributions
ement+0.045
bridge+0.035
aw+0.034
 amaz+0.034
 swings+0.033
Neg logit contributions
working-0.041
 Claus-0.041
inky-0.040
ny-0.039
ppy-0.039
Token
Token ID198
Feature activation+2.32e-01

Pos logit contributions
ement+0.043
bridge+0.036
aw+0.034
 amaz+0.034
 swings+0.034
Neg logit contributions
 Claus-0.027
working-0.026
inky-0.026
ny-0.026
ppy-0.025
Token
Token ID198
Feature activation+3.39e-01

Pos logit contributions
ement+0.009
bridge+0.008
aw+0.007
 swings+0.007
 amaz+0.007
Neg logit contributions
working-0.005
inky-0.005
 Claus-0.005
ny-0.005
ppy-0.005
TokenMom
Token ID29252
Feature activation+2.39e-01

Pos logit contributions
ement+0.010
bridge+0.008
aw+0.008
 swings+0.008
 amaz+0.008
Neg logit contributions
working-0.011
 Claus-0.011
inky-0.011
ppy-0.011
ny-0.011
Token school
Token ID1524
Feature activation+2.77e-01

Pos logit contributions
ement+0.001
bridge+0.001
aw+0.001
aming+0.001
irled+0.001
Neg logit contributions
working-0.001
 Claus-0.001
ny-0.001
inky-0.001
ppy-0.001
Token!"
Token ID2474
Feature activation-1.01e+00

Pos logit contributions
ement+0.009
bridge+0.007
 amaz+0.007
aw+0.007
 swings+0.007
Neg logit contributions
working-0.009
 Claus-0.008
inky-0.008
ny-0.008
ppy-0.008
Token
Token ID220
Feature activation-1.17e+00

Pos logit contributions
working+0.029
 Claus+0.027
ppy+0.026
inky+0.026
ro+0.026
Neg logit contributions
ement-0.036
aw-0.028
 swings-0.027
 amaz-0.027
bridge-0.027
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
working+0.032
 Claus+0.031
ppy+0.031
ny+0.030
ley+0.030
Neg logit contributions
ement-0.042
bridge-0.033
aw-0.033
 swings-0.033
 amaz-0.032
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
working+0.036
 Claus+0.035
inky+0.034
ppy+0.034
ny+0.034
Neg logit contributions
ement-0.046
bridge-0.036
aw-0.036
 swings-0.036
 amaz-0.035
TokenBon
Token ID20682
Feature activation-4.63e+00

Pos logit contributions
working+0.029
 Claus+0.028
inky+0.027
ny+0.026
ppy+0.026
Neg logit contributions
ement-0.041
bridge-0.033
aw-0.033
 swings-0.032
irling-0.032
Tokennie
Token ID11952
Feature activation+3.23e-01

Pos logit contributions
working+0.108
 robber+0.104
 Claus+0.095
inky+0.090
 robbers+0.089
Neg logit contributions
ement-0.180
aming-0.143
irled-0.143
irling-0.139
 cal-0.137
Token was
Token ID373
Feature activation+4.10e-01

Pos logit contributions
ement+0.011
bridge+0.009
 amaz+0.008
 awesome+0.008
 swings+0.008
Neg logit contributions
ny-0.009
 Claus-0.009
ppy-0.009
ley-0.009
working-0.009
Token so
Token ID523
Feature activation+9.73e-01

Pos logit contributions
ement+0.019
aw+0.015
ades+0.015
bridge+0.015
 swings+0.014
Neg logit contributions
ny-0.007
 Claus-0.007
 While-0.006
 Penny-0.006
ppy-0.006
Token happy
Token ID3772
Feature activation-1.09e+00

Pos logit contributions
ement+0.031
bridge+0.025
 swings+0.024
aw+0.023
 waves+0.021
Neg logit contributions
working-0.031
 Claus-0.030
ny-0.030
inky-0.030
ppy-0.029
Token that
Token ID326
Feature activation-3.05e-01

Pos logit contributions
working+0.033
 Claus+0.032
inky+0.032
ny+0.031
ppy+0.031
Neg logit contributions
ement-0.036
bridge-0.029
aw-0.027
 swings-0.027
 amaz-0.027
Token
Token ID198
Feature activation-1.58e+00

Pos logit contributions
working+0.044
 Claus+0.043
inky+0.042
ppy+0.042
ley+0.042
Neg logit contributions
ement-0.055
bridge-0.044
 swings-0.043
aw-0.043
 sliding-0.042
TokenOne
Token ID3198
Feature activation-7.10e-02

Pos logit contributions
 Claus+0.062
ley+0.057
inky+0.057
working+0.055
ppy+0.055
Neg logit contributions
ement-0.035
 swings-0.032
bridge-0.031
aw-0.031
irling-0.028
Token day
Token ID1110
Feature activation-2.36e+00

Pos logit contributions
 Claus+0.002
inky+0.002
working+0.002
ppy+0.002
ley+0.002
Neg logit contributions
ement-0.002
aw-0.002
 swings-0.002
bridge-0.002
 sliding-0.002
Token,
Token ID11
Feature activation-2.19e+00

Pos logit contributions
 Claus+0.092
inky+0.090
ppy+0.090
isk+0.088
ley+0.088
Neg logit contributions
ement-0.050
 sliding-0.040
aw-0.039
 swings-0.038
 soaring-0.035
Token Lily
Token ID20037
Feature activation-3.98e-01

Pos logit contributions
ub+0.081
pp+0.080
ppy+0.079
inky+0.079
 Claus+0.077
Neg logit contributions
 swings-0.048
ement-0.043
 more-0.040
 sliding-0.039
aw-0.037
Token and
Token ID290
Feature activation-4.57e+00

Pos logit contributions
working+0.012
inky+0.012
 Claus+0.012
ppy+0.011
ny+0.011
Neg logit contributions
ement-0.013
bridge-0.010
aw-0.010
 swings-0.010
 amaz-0.010
Token Sunny
Token ID32241
Feature activation-2.19e+00

Pos logit contributions
ub+0.191
pp+0.179
ro+0.173
airy+0.171
inky+0.171
Neg logit contributions
ement-0.092
 swings-0.087
 cal-0.078
 smiles-0.076
 waves-0.075
Token were
Token ID547
Feature activation-7.02e-01

Pos logit contributions
working+0.076
inky+0.074
ro+0.073
 Claus+0.070
ppy+0.070
Neg logit contributions
ement-0.053
aw-0.047
 swings-0.045
 waves-0.043
 sliding-0.043
Token in
Token ID287
Feature activation-1.31e+00

Pos logit contributions
working+0.026
 Claus+0.026
inky+0.026
ppy+0.025
ny+0.025
Neg logit contributions
ement-0.018
bridge-0.013
aw-0.013
 swings-0.013
 amaz-0.013
Token the
Token ID262
Feature activation+4.44e-02

Pos logit contributions
ppy+0.053
inky+0.053
working+0.052
 Claus+0.052
ny+0.051
Neg logit contributions
ement-0.028
 amaz-0.021
 swings-0.021
 sliding-0.020
 cal-0.019
Token field
Token ID2214
Feature activation+4.56e-02

Pos logit contributions
ement+0.001
bridge+0.001
 amaz+0.001
aw+0.001
 sliding+0.001
Neg logit contributions
working-0.002
 Claus-0.002
inky-0.002
ny-0.002
ppy-0.002
Token
Token ID198
Feature activation-8.65e-01

Pos logit contributions
working+0.032
 Claus+0.031
inky+0.031
ppy+0.030
ny+0.030
Neg logit contributions
ement-0.045
bridge-0.036
aw-0.035
 swings-0.035
 amaz-0.035
TokenOne
Token ID3198
Feature activation+2.57e-01

Pos logit contributions
 Claus+0.025
working+0.024
ley+0.023
ppy+0.023
inky+0.023
Neg logit contributions
ement-0.030
 swings-0.025
aw-0.024
bridge-0.024
 sliding-0.024
Token day
Token ID1110
Feature activation-1.30e+00

Pos logit contributions
ement+0.009
aw+0.007
 swings+0.007
bridge+0.007
 sliding+0.007
Neg logit contributions
 Claus-0.007
inky-0.007
working-0.007
ley-0.007
ppy-0.007
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
 Claus+0.049
ppy+0.046
ley+0.046
working+0.045
inky+0.044
Neg logit contributions
ement-0.033
 sliding-0.028
aw-0.026
 swings-0.025
 swinging-0.024
Token Tim
Token ID5045
Feature activation-4.09e-01

Pos logit contributions
 Claus+0.041
ppy+0.041
ley+0.039
inky+0.039
working+0.039
Neg logit contributions
ement-0.029
 sliding-0.026
 swings-0.025
aw-0.023
 swinging-0.022
Token and
Token ID290
Feature activation-4.55e+00

Pos logit contributions
inky+0.012
working+0.012
 Claus+0.012
ppy+0.012
ley+0.012
Neg logit contributions
ement-0.013
 swings-0.010
aw-0.010
bridge-0.010
 sliding-0.010
Token Fl
Token ID1610
Feature activation-2.45e+00

Pos logit contributions
pp+0.153
working+0.153
ub+0.145
inky+0.143
ory+0.142
Neg logit contributions
 swings-0.114
ement-0.109
 sliding-0.104
 cal-0.100
 ic-0.098
Tokenuffy
Token ID15352
Feature activation-1.13e-01

Pos logit contributions
working+0.068
 Claus+0.062
ley+0.057
ny+0.057
ro+0.056
Neg logit contributions
ement-0.089
aw-0.072
irled-0.069
aded-0.068
 swings-0.068
Token went
Token ID1816
Feature activation-2.03e-01

Pos logit contributions
working+0.003
inky+0.003
 Claus+0.003
ppy+0.003
ny+0.003
Neg logit contributions
ement-0.004
aw-0.003
bridge-0.003
 swings-0.003
 sliding-0.003
Token to
Token ID284
Feature activation-1.62e+00

Pos logit contributions
ppy+0.006
working+0.006
ley+0.006
 Claus+0.006
inky+0.006
Neg logit contributions
ement-0.006
 swings-0.005
 sliding-0.005
 soaring-0.005
aw-0.005
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
ppy+0.071
working+0.070
inky+0.070
pp+0.069
ub+0.069
Neg logit contributions
 swings-0.024
ement-0.022
 sliding-0.022
 amaz-0.020
 waves-0.018
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
working+0.017
inky+0.017
 Claus+0.017
ppy+0.017
ny+0.017
Neg logit contributions
ement-0.013
bridge-0.010
aw-0.010
 swings-0.010
 amaz-0.009
Token Bonnie
Token ID39203
Feature activation-1.25e+00

Pos logit contributions
working+0.013
 Claus+0.013
inky+0.013
ny+0.013
ppy+0.013
Neg logit contributions
ement-0.013
bridge-0.010
 swings-0.010
aw-0.010
 amaz-0.010
Token!"
Token ID2474
Feature activation-8.48e-01

Pos logit contributions
working+0.044
inky+0.043
 Claus+0.043
ny+0.043
ppy+0.043
Neg logit contributions
ement-0.033
bridge-0.025
aw-0.024
 swings-0.024
 amaz-0.024
Token
Token ID198
Feature activation-1.06e+00

Pos logit contributions
working+0.026
ppy+0.025
ny+0.025
 Claus+0.024
ro+0.024
Neg logit contributions
ement-0.029
aw-0.021
 swings-0.021
 amaz-0.021
 sliding-0.020
Token
Token ID198
Feature activation-1.40e+00

Pos logit contributions
working+0.032
 Claus+0.031
ppy+0.030
ny+0.030
ley+0.029
Neg logit contributions
ement-0.036
aw-0.028
bridge-0.027
 swings-0.027
irling-0.027
TokenBon
Token ID20682
Feature activation-4.53e+00

Pos logit contributions
working+0.043
 Claus+0.042
ny+0.040
ppy+0.040
ro+0.040
Neg logit contributions
ement-0.045
irling-0.035
aming-0.035
aw-0.034
bridge-0.034
Tokennie
Token ID11952
Feature activation-3.85e-03

Pos logit contributions
 robber+0.106
working+0.105
 Claus+0.095
 robbers+0.090
inky+0.088
Neg logit contributions
ement-0.177
aming-0.141
irled-0.139
irling-0.136
aw-0.134
Token was
Token ID373
Feature activation+5.18e-01

Pos logit contributions
 Claus+0.000
working+0.000
ppy+0.000
ley+0.000
ny+0.000
Neg logit contributions
ement-0.000
bridge-0.000
 swings-0.000
 sliding-0.000
aw-0.000
Token so
Token ID523
Feature activation+8.11e-01

Pos logit contributions
ement+0.022
bridge+0.018
aw+0.018
aded+0.017
 umb+0.017
Neg logit contributions
 Claus-0.010
 Gr-0.009
 Penny-0.009
working-0.009
 St-0.008
Token happy
Token ID3772
Feature activation-1.35e+00

Pos logit contributions
ement+0.024
bridge+0.020
 swings+0.019
aw+0.019
 sliding+0.017
Neg logit contributions
working-0.027
 Claus-0.026
inky-0.025
ny-0.024
ppy-0.024
Token and
Token ID290
Feature activation+3.82e-01

Pos logit contributions
working+0.042
 Claus+0.042
inky+0.042
ppy+0.041
ny+0.041
Neg logit contributions
ement-0.043
bridge-0.033
aw-0.032
 swings-0.032
 amaz-0.032
Token
Token ID198
Feature activation-1.06e+00

Pos logit contributions
working+0.014
inky+0.014
ny+0.014
 Claus+0.014
ppy+0.014
Neg logit contributions
ement-0.025
bridge-0.021
 amaz-0.020
aw-0.020
 swings-0.020
TokenOne
Token ID3198
Feature activation+6.33e-01

Pos logit contributions
 Claus+0.029
working+0.029
ppy+0.028
ley+0.028
inky+0.028
Neg logit contributions
ement-0.036
aw-0.031
 swings-0.031
bridge-0.029
 sliding-0.029
Token day
Token ID1110
Feature activation-1.56e+00

Pos logit contributions
ement+0.022
aw+0.018
bridge+0.018
 swings+0.018
 sliding+0.017
Neg logit contributions
 Claus-0.017
inky-0.017
working-0.017
ppy-0.016
ley-0.016
Token,
Token ID11
Feature activation-1.81e+00

Pos logit contributions
 Claus+0.053
ppy+0.051
working+0.051
ley+0.050
inky+0.050
Neg logit contributions
ement-0.043
 sliding-0.036
aw-0.035
 swings-0.034
 swinging-0.032
Token Spot
Token ID15899
Feature activation-1.53e+00

Pos logit contributions
pp+0.063
ppy+0.062
ub+0.062
inky+0.060
working+0.060
Neg logit contributions
ement-0.044
 swings-0.041
 sliding-0.039
aw-0.036
 swinging-0.034
Token and
Token ID290
Feature activation-4.49e+00

Pos logit contributions
working+0.054
inky+0.054
ley+0.050
ro+0.050
 Claus+0.050
Neg logit contributions
ement-0.034
aw-0.031
 swings-0.030
 waves-0.029
 shocked-0.027
Token Shadow
Token ID8843
Feature activation-1.06e+00

Pos logit contributions
pp+0.149
ub+0.147
ory+0.146
inky+0.144
working+0.141
Neg logit contributions
 swings-0.102
ement-0.102
 cal-0.100
 circles-0.098
 ways-0.097
Token were
Token ID547
Feature activation+3.56e-01

Pos logit contributions
working+0.035
inky+0.034
 Claus+0.033
ro+0.033
ny+0.032
Neg logit contributions
ement-0.030
aw-0.024
 swings-0.024
bridge-0.023
 waves-0.022
Token playing
Token ID2712
Feature activation+1.77e-01

Pos logit contributions
ement+0.012
bridge+0.009
 amaz+0.009
aw+0.008
uct+0.008
Neg logit contributions
working-0.012
 Claus-0.011
inky-0.011
ny-0.011
ppy-0.011
Token on
Token ID319
Feature activation+4.56e-01

Pos logit contributions
ement+0.007
 amaz+0.005
bridge+0.005
uct+0.005
aw+0.005
Neg logit contributions
working-0.005
ny-0.005
ppy-0.004
inky-0.004
 Claus-0.004
Token the
Token ID262
Feature activation+2.83e-02

Pos logit contributions
ement+0.011
 swings+0.009
 sliding+0.008
bridge+0.008
aw+0.008
Neg logit contributions
 Claus-0.017
working-0.017
inky-0.017
ppy-0.017
ny-0.017
Token for
Token ID329
Feature activation-3.73e-02

Pos logit contributions
working+0.029
 Claus+0.028
inky+0.028
ppy+0.028
ny+0.028
Neg logit contributions
ement-0.026
bridge-0.020
aw-0.019
 swings-0.019
 amaz-0.019
Token tomorrow
Token ID9439
Feature activation-2.37e-01

Pos logit contributions
working+0.001
 Claus+0.001
ny+0.001
inky+0.001
ppy+0.001
Neg logit contributions
ement-0.001
 swings-0.001
aw-0.001
 sliding-0.001
bridge-0.001
Token."
Token ID526
Feature activation-1.07e+00

Pos logit contributions
working+0.008
 Claus+0.007
inky+0.007
ppy+0.007
ny+0.007
Neg logit contributions
ement-0.007
bridge-0.006
aw-0.005
 swings-0.005
 amaz-0.005
Token
Token ID198
Feature activation-5.94e-01

Pos logit contributions
working+0.032
 Claus+0.030
inky+0.029
ppy+0.029
ny+0.029
Neg logit contributions
ement-0.037
aw-0.028
 amaz-0.028
 swings-0.028
bridge-0.028
Token
Token ID198
Feature activation-9.67e-01

Pos logit contributions
inky+0.014
working+0.014
 Claus+0.014
ny+0.014
ppy+0.014
Neg logit contributions
ement-0.023
bridge-0.019
 swings-0.018
aw-0.018
 amaz-0.018
TokenBon
Token ID20682
Feature activation-4.45e+00

Pos logit contributions
working+0.026
 Claus+0.025
inky+0.023
ro+0.023
ppy+0.023
Neg logit contributions
ement-0.036
aw-0.030
bridge-0.029
irling-0.029
 swings-0.028
Tokennie
Token ID11952
Feature activation-4.24e-01

Pos logit contributions
working+0.099
 robber+0.098
 Claus+0.093
inky+0.090
pp+0.085
Neg logit contributions
ement-0.176
aming-0.141
irled-0.139
irling-0.139
uct-0.135
Token p
Token ID279
Feature activation-2.28e-01

Pos logit contributions
 Claus+0.013
working+0.013
ppy+0.013
ny+0.013
ley+0.012
Neg logit contributions
ement-0.014
bridge-0.011
 swings-0.011
aw-0.010
 amaz-0.010
Tokenouted
Token ID18534
Feature activation-8.09e-01

Pos logit contributions
inky+0.009
 Claus+0.008
ppy+0.008
working+0.008
ley+0.008
Neg logit contributions
ement-0.005
bridge-0.004
 amaz-0.004
 swings-0.004
 soaring-0.004
Token,
Token ID11
Feature activation+2.31e-01

Pos logit contributions
working+0.028
 Claus+0.027
inky+0.027
ppy+0.026
ley+0.025
Neg logit contributions
ement-0.025
 amaz-0.018
aw-0.018
 sliding-0.018
 swings-0.017
Token then
Token ID788
Feature activation+8.51e-02

Pos logit contributions
ement+0.009
bridge+0.007
aw+0.007
 amaz+0.007
 swings+0.007
Neg logit contributions
working-0.006
 Claus-0.006
ppy-0.005
ny-0.005
inky-0.005
Token was
Token ID373
Feature activation+7.05e-01

Pos logit contributions
ement+0.005
bridge+0.004
 sliding+0.004
irling+0.004
 swings+0.004
Neg logit contributions
 Claus-0.005
ny-0.005
ley-0.005
ppy-0.005
working-0.004
Token so
Token ID523
Feature activation+7.06e-01

Pos logit contributions
ement+0.026
 swings+0.021
bridge+0.020
aw+0.020
 heights+0.019
Neg logit contributions
 Claus-0.019
 Penny-0.018
ppy-0.017
ny-0.017
 Ho-0.017
Token thankful
Token ID25535
Feature activation-1.10e+00

Pos logit contributions
ement+0.019
bridge+0.014
 swings+0.014
aw+0.014
 amaz+0.013
Neg logit contributions
working-0.026
 Claus-0.026
inky-0.025
ny-0.025
ppy-0.024
Token that
Token ID326
Feature activation-2.71e-01

Pos logit contributions
working+0.033
 Claus+0.032
inky+0.032
ppy+0.031
ny+0.031
Neg logit contributions
ement-0.037
bridge-0.029
 swings-0.028
aw-0.028
 amaz-0.028
Token the
Token ID262
Feature activation-8.70e-01

Pos logit contributions
inky+0.008
ppy+0.008
 Claus+0.008
working+0.008
ny+0.008
Neg logit contributions
ement-0.009
 amaz-0.007
bridge-0.007
 sliding-0.007
 swings-0.007
Token mer
Token ID4017
Feature activation-4.40e+00

Pos logit contributions
working+0.024
 Claus+0.024
ny+0.023
inky+0.023
ppy+0.023
Neg logit contributions
ement-0.031
bridge-0.025
aw-0.024
irling-0.024
 swings-0.024
Tokenmaid
Token ID23151
Feature activation-2.81e-01

Pos logit contributions
working+0.145
ppy+0.140
inky+0.139
 Claus+0.136
ny+0.136
Neg logit contributions
ement-0.140
bridge-0.104
irled-0.096
 waves-0.096
 amaz-0.096
Token had
Token ID550
Feature activation-6.62e-01

Pos logit contributions
 Claus+0.008
working+0.008
ny+0.008
ley+0.008
ppy+0.008
Neg logit contributions
ement-0.010
bridge-0.008
aw-0.007
 swings-0.007
 amaz-0.007
Token forgiven
Token ID32350
Feature activation-1.29e+00

Pos logit contributions
working+0.020
 Claus+0.019
ny+0.019
ppy+0.019
inky+0.018
Neg logit contributions
ement-0.023
bridge-0.017
 swings-0.017
irling-0.016
 amaz-0.016
Token him
Token ID683
Feature activation+6.34e-01

Pos logit contributions
working+0.041
inky+0.040
 Claus+0.040
ppy+0.038
ny+0.037
Neg logit contributions
ement-0.041
aw-0.032
 amaz-0.032
bridge-0.031
 swings-0.031
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
ement+0.018
bridge+0.014
aw+0.013
 swings+0.013
 amaz+0.013
Neg logit contributions
working-0.022
 Claus-0.021
inky-0.021
ppy-0.021
ny-0.021
Token day
Token ID1110
Feature activation-2.16e+00

Pos logit contributions
inky+0.008
 Claus+0.008
ley+0.008
ppy+0.007
ub+0.007
Neg logit contributions
ement-0.007
 swings-0.006
aw-0.005
 sliding-0.005
 awesome-0.005
Token,
Token ID11
Feature activation-1.94e+00

Pos logit contributions
ppy+0.079
 Claus+0.077
inky+0.077
ro+0.076
ley+0.075
Neg logit contributions
ement-0.055
 sliding-0.044
aw-0.039
 swings-0.039
 swinging-0.037
Token Lucy
Token ID22162
Feature activation-1.17e+00

Pos logit contributions
ppy+0.072
inky+0.071
ub+0.069
working+0.068
 Claus+0.068
Neg logit contributions
ement-0.051
 swings-0.040
 sliding-0.038
bridge-0.035
aw-0.035
Token and
Token ID290
Feature activation-3.75e+00

Pos logit contributions
inky+0.039
working+0.039
ppy+0.037
 Claus+0.037
ley+0.036
Neg logit contributions
ement-0.032
aw-0.026
 swings-0.026
bridge-0.024
 waves-0.024
Token Mr
Token ID1770
Feature activation-2.55e+00

Pos logit contributions
ub+0.145
pp+0.127
ro+0.127
suit+0.125
inky+0.124
Neg logit contributions
ement-0.091
uct-0.083
 swings-0.082
 tears-0.082
 delight-0.080
Token.
Token ID13
Feature activation-4.38e+00

Pos logit contributions
working+0.109
ro+0.105
ub+0.102
 robber+0.099
airy+0.098
Neg logit contributions
ement-0.045
 cal-0.028
 ways-0.026
aw-0.026
 smiles-0.024
Token Bear
Token ID14732
Feature activation-1.26e+00

Pos logit contributions
working+0.132
ro+0.125
ems+0.122
ppy+0.121
pp+0.118
Neg logit contributions
ement-0.134
 amaz-0.113
 horror-0.112
 delight-0.109
 circles-0.108
Token went
Token ID1816
Feature activation-4.14e-01

Pos logit contributions
working+0.038
 Claus+0.037
inky+0.037
ppy+0.036
ny+0.036
Neg logit contributions
ement-0.042
bridge-0.033
aw-0.032
 swings-0.032
 amaz-0.032
Token to
Token ID284
Feature activation-2.18e+00

Pos logit contributions
ppy+0.012
working+0.012
inky+0.012
 Claus+0.012
ley+0.012
Neg logit contributions
ement-0.012
 sliding-0.011
 swings-0.011
 soaring-0.010
aw-0.010
Token the
Token ID262
Feature activation-4.02e-01

Pos logit contributions
ppy+0.101
ub+0.098
working+0.097
inky+0.096
pp+0.096
Neg logit contributions
 swings-0.029
ement-0.025
 sliding-0.025
 amaz-0.023
 cal-0.022
Token park
Token ID3952
Feature activation+3.75e-01

Pos logit contributions
ppy+0.016
working+0.016
ley+0.015
inky+0.015
ny+0.015
Neg logit contributions
ement-0.009
 swings-0.008
aw-0.007
bridge-0.007
 waves-0.007
Token his
Token ID465
Feature activation+8.46e-01

Pos logit contributions
ement+0.024
bridge+0.019
irling+0.019
 swings+0.018
uct+0.018
Neg logit contributions
working-0.021
ny-0.020
inky-0.020
 Claus-0.020
ley-0.019
Token paw
Token ID41827
Feature activation+1.31e+00

Pos logit contributions
ement+0.025
bridge+0.019
aw+0.018
 swings+0.018
 amaz+0.018
Neg logit contributions
working-0.029
inky-0.029
 Claus-0.029
ppy-0.028
ny-0.028
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
ement+0.042
bridge+0.033
 amaz+0.032
 swings+0.031
aw+0.031
Neg logit contributions
working-0.040
inky-0.040
ny-0.040
 Claus-0.040
ppy-0.039
Token
Token ID198
Feature activation-1.44e+00

Pos logit contributions
ppy+0.041
working+0.041
ory+0.038
ley+0.037
pp+0.036
Neg logit contributions
ement-0.044
bridge-0.036
 swings-0.034
 sliding-0.033
 amaz-0.032
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
working+0.046
 Claus+0.044
ley+0.043
ppy+0.043
ory+0.042
Neg logit contributions
ement-0.044
bridge-0.036
 sliding-0.034
aw-0.033
irling-0.033
TokenGr
Token ID8642
Feature activation-4.38e+00

Pos logit contributions
working+0.035
 Claus+0.035
inky+0.033
ley+0.033
ppy+0.033
Neg logit contributions
ement-0.046
bridge-0.041
aming-0.038
irling-0.038
aw-0.037
Tokenace
Token ID558
Feature activation-3.85e-01

Pos logit contributions
working+0.163
 Claus+0.157
 Cotton+0.149
 Ho+0.148
use+0.145
Neg logit contributions
ement-0.114
aming-0.086
 ways-0.080
bridge-0.079
aw-0.076
Token was
Token ID373
Feature activation+2.57e-01

Pos logit contributions
working+0.012
 Claus+0.012
inky+0.012
ppy+0.012
ny+0.012
Neg logit contributions
ement-0.012
bridge-0.009
 swings-0.009
aw-0.009
 amaz-0.009
Token surprised
Token ID6655
Feature activation-1.02e+00

Pos logit contributions
ement+0.008
bridge+0.007
 swings+0.006
aw+0.006
irled+0.006
Neg logit contributions
 Claus-0.008
ny-0.008
ppy-0.007
inky-0.007
working-0.007
Token and
Token ID290
Feature activation+5.52e-01

Pos logit contributions
working+0.032
 Claus+0.032
inky+0.032
ppy+0.031
ny+0.031
Neg logit contributions
ement-0.033
aw-0.025
 amaz-0.025
bridge-0.024
 swings-0.024
Token said
Token ID531
Feature activation+2.69e-01

Pos logit contributions
ement+0.018
bridge+0.014
aw+0.013
 swings+0.013
 amaz+0.013
Neg logit contributions
working-0.017
 Claus-0.017
inky-0.017
ny-0.017
ppy-0.017
Token Every
Token ID3887
Feature activation+8.09e-01

Pos logit contributions
working+0.070
ppy+0.058
ro+0.058
airy+0.058
 Claus+0.057
Neg logit contributions
ement-0.045
 swings-0.036
aw-0.035
 waves-0.034
 circles-0.032
Token day
Token ID1110
Feature activation-1.68e+00

Pos logit contributions
ement+0.031
bridge+0.026
aw+0.025
 swings+0.025
 amaz+0.025
Neg logit contributions
working-0.020
 Claus-0.019
inky-0.019
ny-0.019
ppy-0.019
Token,
Token ID11
Feature activation-1.81e+00

Pos logit contributions
isk+0.046
working+0.044
 Claus+0.043
airy+0.042
uries+0.041
Neg logit contributions
aw-0.050
ement-0.049
 waves-0.047
 soaring-0.046
 more-0.044
Token Ho
Token ID9544
Feature activation-3.03e+00

Pos logit contributions
working+0.041
ro+0.039
airy+0.038
ny+0.037
isk+0.037
Neg logit contributions
 waves-0.060
 soaring-0.060
ement-0.059
 swings-0.057
 more-0.055
Tokenppy
Token ID14097
Feature activation-8.66e-01

Pos logit contributions
working+0.046
 While+0.042
 robber+0.038
ny+0.036
 guys+0.035
Neg logit contributions
ement-0.128
irling-0.119
aw-0.117
irled-0.115
aming-0.111
Token and
Token ID290
Feature activation-4.36e+00

Pos logit contributions
working+0.026
inky+0.026
 Claus+0.026
ppy+0.025
ny+0.025
Neg logit contributions
ement-0.028
bridge-0.022
aw-0.022
 swings-0.022
 amaz-0.021
Token Cotton
Token ID23915
Feature activation-2.24e+00

Pos logit contributions
ub+0.115
ro+0.114
eth+0.113
airy+0.110
eware+0.109
Neg logit contributions
 thanks-0.129
 cal-0.128
 tears-0.126
 waves-0.123
 smiles-0.121
Token would
Token ID561
Feature activation-5.77e-01

Pos logit contributions
inky+0.067
working+0.065
 Claus+0.063
ro+0.061
airy+0.060
Neg logit contributions
ement-0.066
 swings-0.057
aw-0.056
 waves-0.056
 amaz-0.053
Token explore
Token ID7301
Feature activation+4.85e-01

Pos logit contributions
working+0.016
 Claus+0.016
inky+0.016
ley+0.016
ppy+0.015
Neg logit contributions
ement-0.018
 swings-0.016
 sliding-0.015
 amaz-0.015
 waves-0.015
Token the
Token ID262
Feature activation-8.27e-01

Pos logit contributions
ement+0.015
bridge+0.012
 amaz+0.011
aw+0.011
 swings+0.011
Neg logit contributions
working-0.015
ny-0.015
ppy-0.015
 Claus-0.015
ley-0.015
Token me
Token ID502
Feature activation-1.58e-01

Pos logit contributions
 Claus+0.030
working+0.029
inky+0.029
ppy+0.029
ley+0.028
Neg logit contributions
ement-0.022
 swings-0.018
aw-0.017
 waves-0.016
 amaz-0.016
Token strange
Token ID6283
Feature activation+5.72e-01

Pos logit contributions
ement+0.000
bridge+0.000
 swings+0.000
aw+0.000
 amaz+0.000
Neg logit contributions
 Claus-0.001
working-0.001
ppy-0.001
inky-0.001
ny-0.001
Token.
Token ID13
Feature activation+5.81e-01

Pos logit contributions
ement+0.019
bridge+0.015
aw+0.015
 amaz+0.014
 swings+0.014
Neg logit contributions
working-0.017
 Claus-0.016
ny-0.016
inky-0.016
ppy-0.016
Token
Token ID198
Feature activation-9.00e-01

Pos logit contributions
ement+0.019
 swings+0.015
aw+0.015
 amaz+0.014
bridge+0.014
Neg logit contributions
working-0.019
ppy-0.018
 Claus-0.018
inky-0.018
ley-0.017
Token
Token ID198
Feature activation-1.46e-03

Pos logit contributions
working+0.026
 Claus+0.025
ppy+0.024
inky+0.024
ley+0.024
Neg logit contributions
ement-0.031
bridge-0.025
aw-0.025
 swings-0.025
 sliding-0.024
TokenJoe
Token ID19585
Feature activation-2.33e-02

Pos logit contributions
 Claus+0.000
working+0.000
inky+0.000
ppy+0.000
ley+0.000
Neg logit contributions
ement-0.000
aw-0.000
bridge-0.000
 swings-0.000
aming-0.000
Token and
Token ID290
Feature activation-4.30e+00

Pos logit contributions
working+0.001
 Claus+0.001
inky+0.001
ny+0.001
ppy+0.001
Neg logit contributions
ement-0.001
bridge-0.001
 swings-0.001
 amaz-0.001
aw-0.001
Token May
Token ID1737
Feature activation-6.97e-01

Pos logit contributions
pp+0.159
inky+0.159
working+0.154
ppy+0.150
ub+0.150
Neg logit contributions
ement-0.102
 smiles-0.084
 cal-0.081
 swings-0.081
 ways-0.079
Token wanted
Token ID2227
Feature activation+5.75e-01

Pos logit contributions
working+0.022
 Claus+0.022
inky+0.022
ppy+0.022
ny+0.021
Neg logit contributions
ement-0.022
bridge-0.017
 swings-0.016
aw-0.016
 amaz-0.016
Token to
Token ID284
Feature activation+1.48e+00

Pos logit contributions
ement+0.028
bridge+0.024
irling+0.023
irled+0.022
 amaz+0.022
Neg logit contributions
working-0.010
 Claus-0.010
ny-0.009
ley-0.009
inky-0.009
Token touch
Token ID3638
Feature activation+1.61e+00

Pos logit contributions
ement+0.067
bridge+0.053
aw+0.053
irling+0.052
aming+0.051
Neg logit contributions
working-0.032
ny-0.030
 Claus-0.029
inky-0.029
ro-0.027
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
ement+0.057
bridge+0.050
irling+0.047
uct+0.046
aming+0.046
Neg logit contributions
ley-0.041
ny-0.040
working-0.039
 Ho-0.039
ppy-0.038
Tokenage
Token ID496
Feature activation+2.83e-01

Pos logit contributions
ement+0.039
 amaz+0.032
 swings+0.031
uct+0.031
bridge+0.031
Neg logit contributions
inky-0.025
working-0.024
ny-0.024
ro-0.023
ppy-0.023
Token.
Token ID13
Feature activation-1.88e+00

Pos logit contributions
ement+0.009
bridge+0.007
 amaz+0.007
 swings+0.007
aw+0.007
Neg logit contributions
working-0.009
 Claus-0.009
ny-0.009
inky-0.008
ppy-0.008
Token
Token ID220
Feature activation-1.22e+00

Pos logit contributions
working+0.065
ppy+0.060
 Claus+0.059
ory+0.058
ro+0.057
Neg logit contributions
ement-0.056
 swings-0.043
bridge-0.042
 amaz-0.041
 soaring-0.040
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
working+0.039
 Claus+0.036
ley+0.036
ppy+0.035
ny+0.035
Neg logit contributions
ement-0.040
aw-0.031
 swings-0.030
bridge-0.030
 sliding-0.030
Token
Token ID198
Feature activation-1.61e+00

Pos logit contributions
working+0.073
 Claus+0.069
ppy+0.068
ley+0.068
inky+0.065
Neg logit contributions
ement-0.056
 swings-0.043
aw-0.042
 sliding-0.042
bridge-0.042
TokenGr
Token ID8642
Feature activation-4.30e+00

Pos logit contributions
working+0.041
 Claus+0.040
inky+0.038
ory+0.037
ro+0.037
Neg logit contributions
ement-0.055
bridge-0.049
irling-0.048
aw-0.048
aming-0.048
Tokenace
Token ID558
Feature activation-3.59e-01

Pos logit contributions
working+0.153
 Claus+0.147
 robber+0.134
 Ho+0.132
 Cotton+0.131
Neg logit contributions
ement-0.123
aming-0.092
aw-0.086
irled-0.086
 ways-0.085
Token was
Token ID373
Feature activation+2.25e-01

Pos logit contributions
working+0.011
 Claus+0.011
inky+0.011
ny+0.011
ppy+0.011
Neg logit contributions
ement-0.011
bridge-0.009
 amaz-0.009
 swings-0.009
aw-0.008
Token very
Token ID845
Feature activation-2.11e-01

Pos logit contributions
ement+0.008
bridge+0.006
aw+0.006
 amaz+0.006
 swings+0.005
Neg logit contributions
 Claus-0.006
ny-0.006
working-0.006
 Ho-0.006
inky-0.006
Token excited
Token ID6568
Feature activation-7.51e-01

Pos logit contributions
working+0.008
 Claus+0.008
inky+0.008
ppy+0.008
ny+0.008
Neg logit contributions
ement-0.005
bridge-0.004
aw-0.003
 swings-0.003
 amaz-0.003
Token.
Token ID13
Feature activation-1.45e+00

Pos logit contributions
working+0.024
inky+0.024
 Claus+0.024
ppy+0.023
ny+0.023
Neg logit contributions
ement-0.024
aw-0.018
 swings-0.018
bridge-0.018
 sliding-0.017
Token
Token ID198
Feature activation-8.87e-01

Pos logit contributions
inky+0.015
working+0.015
ny+0.015
 Claus+0.015
ppy+0.015
Neg logit contributions
ement-0.029
bridge-0.024
 amaz-0.024
aw-0.023
 swings-0.023
TokenOne
Token ID3198
Feature activation+3.52e-01

Pos logit contributions
 Claus+0.022
working+0.022
inky+0.021
ppy+0.021
ley+0.021
Neg logit contributions
ement-0.034
bridge-0.027
aw-0.027
 swings-0.027
 sliding-0.026
Token day
Token ID1110
Feature activation-1.42e+00

Pos logit contributions
ement+0.011
aw+0.008
 swings+0.008
 sliding+0.008
bridge+0.008
Neg logit contributions
 Claus-0.011
inky-0.011
ley-0.011
working-0.011
ppy-0.011
Token,
Token ID11
Feature activation-1.47e+00

Pos logit contributions
 Claus+0.044
ppy+0.043
working+0.043
ley+0.042
inky+0.042
Neg logit contributions
ement-0.045
aw-0.036
 sliding-0.036
 swings-0.035
irled-0.033
Token Spot
Token ID15899
Feature activation-1.30e+00

Pos logit contributions
 Claus+0.038
ppy+0.038
inky+0.038
working+0.038
ley+0.037
Neg logit contributions
ement-0.053
 swings-0.044
aw-0.043
 sliding-0.043
bridge-0.042
Token and
Token ID290
Feature activation-4.28e+00

Pos logit contributions
inky+0.043
working+0.043
ley+0.041
ppy+0.041
 Claus+0.041
Neg logit contributions
ement-0.033
 swings-0.029
aw-0.029
 waves-0.027
 sliding-0.026
Token Daisy
Token ID40355
Feature activation-1.31e+00

Pos logit contributions
inky+0.158
ub+0.158
 Claus+0.155
pp+0.155
working+0.151
Neg logit contributions
ement-0.088
 swings-0.084
 ways-0.081
 cal-0.078
 awesome-0.075
Token went
Token ID1816
Feature activation-5.03e-01

Pos logit contributions
working+0.040
inky+0.039
 Claus+0.039
ppy+0.038
ley+0.038
Neg logit contributions
ement-0.041
aw-0.033
 swings-0.032
bridge-0.032
 sliding-0.031
Token to
Token ID284
Feature activation-1.48e+00

Pos logit contributions
ppy+0.016
ley+0.016
 Claus+0.016
inky+0.016
working+0.016
Neg logit contributions
ement-0.014
 sliding-0.013
 swings-0.012
 soaring-0.012
 waves-0.011
Token a
Token ID257
Feature activation+2.49e-01

Pos logit contributions
working+0.061
ppy+0.061
inky+0.061
ley+0.060
 Claus+0.059
Neg logit contributions
ement-0.027
 swings-0.025
 amaz-0.023
 sliding-0.023
 waves-0.020
Token fun
Token ID1257
Feature activation-7.19e-01

Pos logit contributions
ement+0.006
 swings+0.005
aw+0.004
bridge+0.004
 sliding+0.004
Neg logit contributions
working-0.009
ppy-0.009
inky-0.009
 Claus-0.009
ley-0.009
Token
Token ID220
Feature activation-1.08e+00

Pos logit contributions
ement+0.005
 swings+0.004
aw+0.004
 amaz+0.004
 sliding+0.004
Neg logit contributions
working-0.004
ppy-0.004
 Claus-0.004
inky-0.004
ley-0.004
Token
Token ID198
Feature activation-4.49e-01

Pos logit contributions
working+0.035
ley+0.032
 Claus+0.032
ppy+0.032
ny+0.031
Neg logit contributions
ement-0.034
aw-0.027
 swings-0.027
bridge-0.027
 sliding-0.026
Token
Token ID198
Feature activation+8.27e-02

Pos logit contributions
working+0.013
 Claus+0.013
ley+0.012
ppy+0.012
inky+0.012
Neg logit contributions
ement-0.015
bridge-0.012
 swings-0.012
aw-0.012
 sliding-0.012
TokenThe
Token ID464
Feature activation-1.95e+00

Pos logit contributions
ement+0.002
bridge+0.002
aw+0.002
 swings+0.002
 amaz+0.002
Neg logit contributions
working-0.003
 Claus-0.003
inky-0.003
ppy-0.003
ny-0.003
Token b
Token ID275
Feature activation-3.03e+00

Pos logit contributions
working+0.061
 Claus+0.060
inky+0.059
ppy+0.059
ny+0.058
Neg logit contributions
ement-0.062
bridge-0.048
 swings-0.048
 amaz-0.046
 sliding-0.046
Tokenunn
Token ID20935
Feature activation-4.27e+00

Pos logit contributions
 Claus+0.076
working+0.067
 Taylor+0.066
 guys+0.063
 robber+0.061
Neg logit contributions
ement-0.121
aw-0.101
atted-0.099
aded-0.096
aming-0.093
Tokenies
Token ID444
Feature activation-1.25e+00

Pos logit contributions
 Claus+0.111
working+0.110
ro+0.107
 robber+0.104
inky+0.101
Neg logit contributions
ement-0.141
atted-0.123
irled-0.113
aded-0.112
irling-0.108
Token happily
Token ID18177
Feature activation-1.22e+00

Pos logit contributions
 Claus+0.037
working+0.036
ppy+0.036
ny+0.036
ley+0.036
Neg logit contributions
ement-0.041
bridge-0.033
aw-0.032
 swings-0.031
 amaz-0.030
Token hopped
Token ID45230
Feature activation-1.52e+00

Pos logit contributions
working+0.038
 Claus+0.038
ny+0.038
ppy+0.038
inky+0.037
Neg logit contributions
ement-0.039
bridge-0.031
 amaz-0.029
 swings-0.029
aw-0.028
Token back
Token ID736
Feature activation-1.69e+00

Pos logit contributions
working+0.053
 Claus+0.052
ppy+0.051
inky+0.051
ley+0.048
Neg logit contributions
ement-0.043
bridge-0.032
aw-0.032
 swings-0.032
 sliding-0.031
Token to
Token ID284
Feature activation-6.39e-01

Pos logit contributions
working+0.050
 Claus+0.049
inky+0.049
ppy+0.049
ny+0.048
Neg logit contributions
ement-0.056
 swings-0.044
 sliding-0.044
aw-0.043
 amaz-0.043
Token
Token ID198
Feature activation-1.18e+00

Pos logit contributions
working+0.026
 Claus+0.026
inky+0.026
ppy+0.025
ny+0.025
Neg logit contributions
ement-0.039
bridge-0.032
aw-0.031
 swings-0.031
 amaz-0.031
TokenSo
Token ID2396
Feature activation-2.25e+00

Pos logit contributions
working+0.040
 Claus+0.038
inky+0.037
ley+0.036
ppy+0.036
Neg logit contributions
ement-0.036
bridge-0.029
aw-0.028
 swings-0.028
 amaz-0.026
Token,
Token ID11
Feature activation-1.64e+00

Pos logit contributions
working+0.075
ppy+0.070
 Claus+0.069
inky+0.068
pp+0.066
Neg logit contributions
ement-0.068
 sliding-0.052
 swings-0.052
 amaz-0.051
 delight-0.050
Token Frost
Token ID15122
Feature activation-2.98e+00

Pos logit contributions
working+0.054
ppy+0.050
inky+0.050
ny+0.049
pp+0.047
Neg logit contributions
ement-0.049
 swings-0.043
 sliding-0.042
aw-0.038
 waves-0.038
Tokeny
Token ID88
Feature activation-1.65e+00

Pos logit contributions
working+0.043
inky+0.037
 Cotton+0.037
 robber+0.036
 Ho+0.035
Neg logit contributions
ement-0.138
aw-0.121
aming-0.119
bridge-0.118
irled-0.118
Token and
Token ID290
Feature activation-4.26e+00

Pos logit contributions
working+0.049
ny+0.048
 Claus+0.048
ppy+0.047
inky+0.047
Neg logit contributions
ement-0.057
bridge-0.044
 amaz-0.043
aw-0.043
 swings-0.042
Token Lily
Token ID20037
Feature activation-1.12e+00

Pos logit contributions
working+0.131
inky+0.129
 Claus+0.117
pp+0.114
ppy+0.113
Neg logit contributions
ement-0.133
 amaz-0.115
 cal-0.115
 swings-0.114
 waves-0.111
Token used
Token ID973
Feature activation-7.51e-01

Pos logit contributions
working+0.034
ppy+0.033
ny+0.033
 Claus+0.033
ley+0.032
Neg logit contributions
ement-0.039
bridge-0.030
 swings-0.029
 amaz-0.029
aw-0.029
Token their
Token ID511
Feature activation+5.99e-01

Pos logit contributions
working+0.020
ny+0.019
inky+0.019
ro+0.019
 Ho+0.019
Neg logit contributions
ement-0.028
aw-0.023
bridge-0.022
irling-0.022
uct-0.021
Token magic
Token ID5536
Feature activation-5.26e-02

Pos logit contributions
ement+0.022
aw+0.019
uct+0.018
bridge+0.018
irling+0.018
Neg logit contributions
working-0.016
ny-0.015
inky-0.015
ley-0.014
ppy-0.014
Token powers
Token ID5635
Feature activation-5.69e-02

Pos logit contributions
working+0.001
inky+0.001
ro+0.001
ny+0.001
ppy+0.001
Neg logit contributions
ement-0.002
uct-0.001
aw-0.001
irling-0.001
bridge-0.001
Token One
Token ID1881
Feature activation+7.46e-02

Pos logit contributions
working+0.044
ppy+0.041
ley+0.040
 Claus+0.040
ro+0.038
Neg logit contributions
ement-0.041
 swings-0.035
 sliding-0.031
uct-0.030
 amaz-0.029
Token day
Token ID1110
Feature activation-1.19e+00

Pos logit contributions
ement+0.003
bridge+0.002
aw+0.002
 swings+0.002
 amaz+0.002
Neg logit contributions
 Claus-0.002
working-0.002
inky-0.002
ppy-0.002
ley-0.002
Token,
Token ID11
Feature activation-1.36e+00

Pos logit contributions
 Claus+0.045
ppy+0.043
ley+0.043
ro+0.042
ny+0.041
Neg logit contributions
ement-0.028
 sliding-0.025
 swinging-0.022
aw-0.022
 swings-0.021
Token Tim
Token ID5045
Feature activation-9.66e-01

Pos logit contributions
ppy+0.045
ub+0.045
ro+0.044
inky+0.044
pp+0.043
Neg logit contributions
ement-0.034
 sliding-0.034
 swings-0.033
 swinging-0.031
 soaring-0.029
Tokenmy
Token ID1820
Feature activation-8.77e-01

Pos logit contributions
working+0.024
inky+0.023
 Claus+0.023
ley+0.022
ppy+0.021
Neg logit contributions
ement-0.036
aw-0.030
 swings-0.030
bridge-0.029
 sliding-0.029
Token and
Token ID290
Feature activation-4.24e+00

Pos logit contributions
working+0.027
inky+0.026
 Claus+0.026
ppy+0.025
ley+0.025
Neg logit contributions
ement-0.027
aw-0.022
 swings-0.022
bridge-0.022
 sliding-0.021
Token Midnight
Token ID27960
Feature activation-2.45e+00

Pos logit contributions
ub+0.123
ro+0.117
airy+0.114
pp+0.112
working+0.110
Neg logit contributions
ement-0.117
 cal-0.113
 tears-0.112
 swings-0.112
 kisses-0.111
Token went
Token ID1816
Feature activation-4.82e-01

Pos logit contributions
working+0.090
inky+0.087
ro+0.085
 Claus+0.082
airy+0.082
Neg logit contributions
ement-0.055
 swings-0.047
aw-0.047
 waves-0.045
bridge-0.043
Token for
Token ID329
Feature activation-1.29e+00

Pos logit contributions
ppy+0.016
working+0.015
inky+0.015
 Claus+0.015
ley+0.015
Neg logit contributions
ement-0.012
 sliding-0.011
 swings-0.011
 soaring-0.010
 waves-0.010
Token a
Token ID257
Feature activation-9.15e-01

Pos logit contributions
working+0.050
ub+0.049
ppy+0.049
inky+0.049
ley+0.049
Neg logit contributions
ement-0.027
 swings-0.022
 sliding-0.021
 awesome-0.020
 cal-0.019
Token walk
Token ID2513
Feature activation-2.63e-01

Pos logit contributions
ley+0.025
ppy+0.024
inky+0.024
working+0.024
ro+0.024
Neg logit contributions
ement-0.029
 swings-0.026
 sliding-0.025
 soaring-0.024
 awesome-0.023
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
working+0.052
 Claus+0.051
inky+0.049
ppy+0.049
ley+0.049
Neg logit contributions
ement-0.063
bridge-0.050
 swings-0.049
aw-0.049
 sliding-0.048
TokenOne
Token ID3198
Feature activation-2.02e-01

Pos logit contributions
 Claus+0.057
working+0.054
ley+0.052
inky+0.051
ory+0.051
Neg logit contributions
ement-0.046
bridge-0.040
 swings-0.039
aw-0.038
irling-0.037
Token day
Token ID1110
Feature activation-2.44e+00

Pos logit contributions
 Claus+0.006
inky+0.006
working+0.006
ley+0.006
ppy+0.006
Neg logit contributions
ement-0.006
aw-0.005
 swings-0.005
 sliding-0.005
bridge-0.005
Token,
Token ID11
Feature activation-2.29e+00

Pos logit contributions
 Claus+0.098
working+0.096
inky+0.093
pp+0.093
ley+0.093
Neg logit contributions
ement-0.048
 sliding-0.044
 swings-0.039
 swinging-0.036
aw-0.036
Token Lily
Token ID20037
Feature activation-9.87e-01

Pos logit contributions
working+0.074
 Claus+0.072
pp+0.071
inky+0.070
ppy+0.068
Neg logit contributions
ement-0.062
 swings-0.061
 sliding-0.057
 more-0.053
 awesome-0.052
Token and
Token ID290
Feature activation-4.24e+00

Pos logit contributions
inky+0.032
working+0.032
 Claus+0.031
ppy+0.030
ley+0.030
Neg logit contributions
ement-0.028
aw-0.023
 swings-0.023
bridge-0.022
 sliding-0.021
Token Fl
Token ID1610
Feature activation-2.48e+00

Pos logit contributions
working+0.149
pp+0.147
ub+0.142
ory+0.141
inky+0.139
Neg logit contributions
 swings-0.104
ement-0.097
 sliding-0.091
 cal-0.088
 more-0.088
Tokenuffy
Token ID15352
Feature activation-9.50e-01

Pos logit contributions
working+0.066
 Claus+0.062
ny+0.056
ro+0.056
ley+0.054
Neg logit contributions
ement-0.093
aw-0.075
irled-0.072
 swings-0.071
aded-0.070
Token went
Token ID1816
Feature activation-5.91e-01

Pos logit contributions
working+0.031
inky+0.031
 Claus+0.030
ro+0.029
ley+0.029
Neg logit contributions
ement-0.027
aw-0.022
 swings-0.022
bridge-0.021
 sliding-0.020
Token to
Token ID284
Feature activation-2.21e+00

Pos logit contributions
ppy+0.020
ley+0.020
inky+0.020
working+0.020
 Claus+0.019
Neg logit contributions
ement-0.014
 sliding-0.013
 swings-0.013
 soaring-0.012
 waves-0.012
Token the
Token ID262
Feature activation+9.39e-02

Pos logit contributions
ppy+0.100
working+0.099
pp+0.098
inky+0.098
ub+0.097
Neg logit contributions
 swings-0.032
 sliding-0.027
ement-0.025
 amaz-0.024
 cal-0.022
Token being
Token ID852
Feature activation+3.00e-01

Pos logit contributions
ement+0.026
bridge+0.020
aw+0.019
 swings+0.019
 amaz+0.018
Neg logit contributions
working-0.029
 Claus-0.028
ppy-0.027
ny-0.027
inky-0.027
Token curious
Token ID11040
Feature activation+4.51e-01

Pos logit contributions
ement+0.009
bridge+0.007
 amaz+0.007
 swings+0.006
aw+0.006
Neg logit contributions
working-0.010
 Claus-0.010
ny-0.010
ppy-0.010
inky-0.010
Token."
Token ID526
Feature activation-1.14e+00

Pos logit contributions
ement+0.014
bridge+0.011
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.014
 Claus-0.014
inky-0.014
ny-0.013
ppy-0.013
Token
Token ID198
Feature activation-8.82e-01

Pos logit contributions
working+0.045
ppy+0.042
ory+0.039
ny+0.039
ley+0.039
Neg logit contributions
ement-0.031
bridge-0.021
 sliding-0.020
 swings-0.020
 cal-0.020
Token
Token ID198
Feature activation-9.04e-01

Pos logit contributions
working+0.025
 Claus+0.024
ppy+0.023
inky+0.023
ny+0.023
Neg logit contributions
ement-0.031
bridge-0.025
aw-0.024
 swings-0.024
 sliding-0.024
TokenGr
Token ID8642
Feature activation-4.23e+00

Pos logit contributions
working+0.023
 Claus+0.022
inky+0.022
ppy+0.022
ny+0.021
Neg logit contributions
ement-0.034
bridge-0.028
aw-0.027
 swings-0.027
irling-0.027
Tokenace
Token ID558
Feature activation-9.96e-02

Pos logit contributions
working+0.157
 Claus+0.152
 Cotton+0.142
 Ho+0.140
 robber+0.139
Neg logit contributions
ement-0.112
aming-0.083
 ways-0.079
bridge-0.077
aw-0.075
Token laughed
Token ID13818
Feature activation+3.03e-01

Pos logit contributions
 Claus+0.003
working+0.003
ny+0.003
inky+0.003
ppy+0.003
Neg logit contributions
ement-0.003
bridge-0.002
 swings-0.002
 amaz-0.002
aw-0.002
Token and
Token ID290
Feature activation+4.60e-01

Pos logit contributions
ement+0.010
bridge+0.008
 swings+0.008
aw+0.008
 amaz+0.008
Neg logit contributions
working-0.009
 Claus-0.009
inky-0.009
ny-0.009
ppy-0.009
Token said
Token ID531
Feature activation+5.35e-01

Pos logit contributions
ement+0.013
aw+0.010
 swings+0.010
bridge+0.010
 amaz+0.010
Neg logit contributions
working-0.016
inky-0.016
 Claus-0.016
ppy-0.015
ny-0.015
Token,
Token ID11
Feature activation-5.74e-01

Pos logit contributions
ement+0.019
bridge+0.015
aw+0.015
 swings+0.015
 sliding+0.015
Neg logit contributions
working-0.014
 Claus-0.014
inky-0.014
ppy-0.014
ny-0.014
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
working+0.012
 Claus+0.011
ny+0.011
ppy+0.011
inky+0.011
Neg logit contributions
ement-0.012
bridge-0.009
 amaz-0.009
aw-0.009
 swings-0.009
Token One
Token ID1881
Feature activation+3.72e-01

Pos logit contributions
working+0.060
ppy+0.057
 Claus+0.055
pp+0.054
inky+0.053
Neg logit contributions
ement-0.051
 swings-0.042
aw-0.039
 waves-0.038
 amaz-0.036
Token day
Token ID1110
Feature activation-2.11e+00

Pos logit contributions
ement+0.013
aw+0.010
bridge+0.010
 swings+0.010
 amaz+0.010
Neg logit contributions
 Claus-0.010
inky-0.010
working-0.010
ppy-0.010
ley-0.010
Token,
Token ID11
Feature activation-1.74e+00

Pos logit contributions
 Claus+0.070
working+0.069
ppy+0.068
isk+0.068
inky+0.068
Neg logit contributions
ement-0.057
 sliding-0.045
aw-0.044
 swings-0.042
irled-0.041
Token Rudy
Token ID37602
Feature activation-1.28e+00

Pos logit contributions
pp+0.049
inky+0.049
working+0.048
isk+0.048
ppy+0.047
Neg logit contributions
ement-0.054
 swings-0.047
 waves-0.047
 sliding-0.045
aw-0.044
Token and
Token ID290
Feature activation-4.23e+00

Pos logit contributions
working+0.043
inky+0.043
ppy+0.040
 Claus+0.040
ley+0.040
Neg logit contributions
ement-0.034
aw-0.029
 swings-0.028
 waves-0.027
bridge-0.026
Token his
Token ID465
Feature activation-5.82e-01

Pos logit contributions
working+0.172
inky+0.170
pp+0.168
airy+0.161
ub+0.159
Neg logit contributions
 waves-0.075
ement-0.074
 swings-0.072
 cal-0.070
 smiles-0.065
Token friends
Token ID2460
Feature activation-8.78e-01

Pos logit contributions
inky+0.022
 Claus+0.022
working+0.022
ny+0.021
ley+0.021
Neg logit contributions
ement-0.015
bridge-0.011
 amaz-0.011
aw-0.010
 swings-0.010
Token went
Token ID1816
Feature activation-3.10e-01

Pos logit contributions
working+0.028
inky+0.027
 Claus+0.027
ppy+0.027
ny+0.026
Neg logit contributions
ement-0.027
bridge-0.021
aw-0.021
 swings-0.021
 amaz-0.020
Token for
Token ID329
Feature activation-7.30e-01

Pos logit contributions
ppy+0.010
inky+0.010
ley+0.010
 Claus+0.010
working+0.010
Neg logit contributions
ement-0.008
 sliding-0.007
 swings-0.007
 soaring-0.007
 waves-0.007
Token a
Token ID257
Feature activation-3.82e-01

Pos logit contributions
working+0.024
 Claus+0.024
inky+0.024
ppy+0.023
ny+0.023
Neg logit contributions
ement-0.022
bridge-0.017
 swings-0.016
aw-0.016
 amaz-0.016
TokenOne
Token ID3198
Feature activation+4.34e-01

Pos logit contributions
working+0.020
 Claus+0.020
inky+0.019
ppy+0.019
ley+0.019
Neg logit contributions
ement-0.032
bridge-0.026
 swings-0.026
aw-0.026
 sliding-0.025
Token sunny
Token ID27737
Feature activation-5.11e-01

Pos logit contributions
ement+0.014
aw+0.011
 swings+0.011
bridge+0.011
 sliding+0.011
Neg logit contributions
 Claus-0.013
inky-0.013
working-0.012
ley-0.012
ppy-0.012
Token day
Token ID1110
Feature activation-1.59e+00

Pos logit contributions
working+0.012
ny+0.011
inky+0.011
 Claus+0.011
ppy+0.011
Neg logit contributions
ement-0.021
bridge-0.017
 amaz-0.017
aw-0.017
 swings-0.016
Token,
Token ID11
Feature activation-1.33e+00

Pos logit contributions
 Claus+0.056
ppy+0.055
ro+0.054
ley+0.054
inky+0.054
Neg logit contributions
ement-0.042
 sliding-0.033
aw-0.031
 swings-0.030
irled-0.030
Token Max
Token ID5436
Feature activation-8.55e-01

Pos logit contributions
inky+0.038
ppy+0.038
working+0.037
 Claus+0.037
ny+0.037
Neg logit contributions
ement-0.045
 swings-0.037
 sliding-0.036
bridge-0.035
aw-0.035
Token and
Token ID290
Feature activation-4.22e+00

Pos logit contributions
inky+0.028
working+0.028
 Claus+0.027
ppy+0.026
ley+0.026
Neg logit contributions
ement-0.024
 swings-0.020
aw-0.020
bridge-0.018
 waves-0.018
Token Lucy
Token ID22162
Feature activation-7.94e-01

Pos logit contributions
inky+0.154
working+0.151
 Claus+0.149
ub+0.148
pp+0.145
Neg logit contributions
ement-0.101
 swings-0.086
 cal-0.081
 sliding-0.078
bridge-0.077
Token found
Token ID1043
Feature activation+6.64e-01

Pos logit contributions
working+0.024
 Claus+0.023
inky+0.023
ppy+0.023
ny+0.023
Neg logit contributions
ement-0.026
bridge-0.021
aw-0.020
 swings-0.020
 amaz-0.020
Token a
Token ID257
Feature activation-3.63e-01

Pos logit contributions
ement+0.022
bridge+0.017
irling+0.017
 amaz+0.016
aw+0.016
Neg logit contributions
working-0.020
 Claus-0.020
inky-0.020
ny-0.019
ppy-0.019
Token patch
Token ID8529
Feature activation+8.83e-01

Pos logit contributions
ppy+0.015
working+0.014
ley+0.014
inky+0.014
ny+0.014
Neg logit contributions
ement-0.008
 swings-0.007
 sliding-0.006
 amaz-0.006
 soaring-0.005
Token of
Token ID286
Feature activation+4.28e-01

Pos logit contributions
ement+0.027
 amaz+0.022
irling+0.020
irled+0.019
 swings+0.019
Neg logit contributions
ny-0.030
working-0.030
inky-0.029
ppy-0.028
y-0.028
Token looked
Token ID3114
Feature activation+1.47e+00

Pos logit contributions
ement+0.025
bridge+0.020
 amaz+0.019
 sliding+0.019
 swings+0.018
Neg logit contributions
ny-0.020
ppy-0.020
 Claus-0.020
working-0.020
ley-0.020
Token out
Token ID503
Feature activation+2.20e-01

Pos logit contributions
ement+0.050
bridge+0.042
 swings+0.038
aw+0.038
irling+0.038
Neg logit contributions
working-0.042
ny-0.041
 Claus-0.041
ppy-0.040
ley-0.040
Token the
Token ID262
Feature activation+9.29e-01

Pos logit contributions
ement+0.008
bridge+0.007
irling+0.007
 swings+0.007
aw+0.007
Neg logit contributions
working-0.006
ny-0.005
 Ho-0.005
ley-0.005
ppy-0.005
Token window
Token ID4324
Feature activation+4.58e-01

Pos logit contributions
ement+0.026
bridge+0.020
aw+0.019
 amaz+0.019
 swings+0.018
Neg logit contributions
working-0.032
 Claus-0.032
inky-0.032
ny-0.031
ppy-0.031
Token and
Token ID290
Feature activation+9.44e-01

Pos logit contributions
ement+0.016
bridge+0.014
 swings+0.013
aw+0.013
irling+0.013
Neg logit contributions
working-0.012
 Claus-0.012
ny-0.012
ley-0.011
ppy-0.011
Token saw
Token ID2497
Feature activation+2.29e+00

Pos logit contributions
ement+0.030
 amaz+0.023
 swings+0.023
aw+0.023
bridge+0.023
Neg logit contributions
inky-0.030
working-0.029
 Claus-0.029
ny-0.028
ppy-0.028
Token the
Token ID262
Feature activation+2.26e+00

Pos logit contributions
ement+0.090
irling+0.075
irled+0.070
bridge+0.069
uct+0.069
Neg logit contributions
working-0.056
 Ho-0.053
 Claus-0.050
 Th-0.050
ny-0.048
Token lightning
Token ID14357
Feature activation+1.90e+00

Pos logit contributions
ement+0.073
irled+0.059
uct+0.058
bridge+0.057
irling+0.057
Neg logit contributions
working-0.071
 Claus-0.065
 guys-0.064
ny-0.063
inky-0.059
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
ement+0.059
irled+0.048
uct+0.048
aded+0.048
irling+0.047
Neg logit contributions
working-0.055
ny-0.055
 Claus-0.053
y-0.053
ro-0.052
Token Suddenly
Token ID24975
Feature activation+3.65e-01

Pos logit contributions
ement+0.046
bridge+0.038
aw+0.038
 swings+0.037
 amaz+0.037
Neg logit contributions
working-0.021
 Claus-0.020
inky-0.020
ny-0.020
ppy-0.020
Token,
Token ID11
Feature activation+7.41e-01

Pos logit contributions
ement+0.013
bridge+0.010
aw+0.010
 swings+0.010
 sliding+0.010
Neg logit contributions
 Claus-0.010
inky-0.010
working-0.010
ppy-0.010
ny-0.010
Token Lily
Token ID20037
Feature activation-3.61e-01

Pos logit contributions
working+0.054
 Claus+0.053
inky+0.052
ppy+0.052
ny+0.051
Neg logit contributions
ement-0.060
bridge-0.048
aw-0.046
 swings-0.046
 amaz-0.046
Token hiding
Token ID11816
Feature activation-5.29e-02

Pos logit contributions
 Claus+0.011
working+0.011
ppy+0.011
ny+0.011
inky+0.010
Neg logit contributions
ement-0.012
bridge-0.009
aw-0.009
 amaz-0.009
 swings-0.008
Token under
Token ID739
Feature activation+1.25e+00

Pos logit contributions
working+0.002
ley+0.002
ro+0.002
 Claus+0.002
ny+0.002
Neg logit contributions
ement-0.002
bridge-0.001
uct-0.001
irling-0.001
aw-0.001
Token the
Token ID262
Feature activation+6.53e-01

Pos logit contributions
ement+0.041
bridge+0.031
aw+0.031
irling+0.030
irled+0.030
Neg logit contributions
working-0.038
 Claus-0.038
inky-0.037
ny-0.037
ro-0.036
Token t
Token ID256
Feature activation+4.62e-02

Pos logit contributions
ement+0.023
irled+0.019
aw+0.019
uct+0.018
aded+0.018
Neg logit contributions
ny-0.018
working-0.018
inky-0.018
 Claus-0.017
ro-0.017
Tokenarp
Token ID5117
Feature activation+2.14e+00

Pos logit contributions
ement+0.001
bridge+0.001
 swings+0.001
aw+0.001
 amaz+0.001
Neg logit contributions
working-0.001
 Claus-0.001
inky-0.001
ppy-0.001
ny-0.001
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
ement+0.070
 amaz+0.056
irling+0.056
bridge+0.055
aw+0.055
Neg logit contributions
ny-0.064
working-0.064
 Claus-0.063
ley-0.062
ppy-0.061
Token He
Token ID679
Feature activation+2.19e-02

Pos logit contributions
ement+0.001
bridge+0.001
aw+0.001
 swings+0.001
 amaz+0.001
Neg logit contributions
working-0.001
ley-0.001
 Claus-0.001
ppy-0.001
inky-0.001
Token knew
Token ID2993
Feature activation+7.16e-01

Pos logit contributions
ement+0.001
bridge+0.001
 amaz+0.001
 sliding+0.001
irling+0.001
Neg logit contributions
 Claus-0.001
ppy-0.001
ny-0.001
ley-0.001
working-0.001
Token they
Token ID484
Feature activation+8.07e-02

Pos logit contributions
ement+0.028
bridge+0.023
irling+0.022
 amaz+0.022
aming+0.022
Neg logit contributions
working-0.017
 Claus-0.017
 Ho-0.016
ppy-0.016
ley-0.016
Token were
Token ID547
Feature activation+8.46e-01

Pos logit contributions
ement+0.003
bridge+0.003
aw+0.003
 amaz+0.003
 swings+0.002
Neg logit contributions
 Claus-0.002
working-0.002
ppy-0.002
ny-0.002
inky-0.002
Token a
Token ID257
Feature activation-1.24e+00

Pos logit contributions
ement+0.026
irling+0.021
irled+0.021
bridge+0.020
aded+0.020
Neg logit contributions
working-0.025
 Claus-0.024
ny-0.024
ro-0.024
ppy-0.023
Token secret
Token ID3200
Feature activation-3.13e-01

Pos logit contributions
ppy+0.047
working+0.046
inky+0.045
ley+0.045
 Claus+0.044
Neg logit contributions
ement-0.032
 amaz-0.025
 swings-0.024
 sliding-0.023
bridge-0.022
Token before
Token ID878
Feature activation+4.17e-01

Pos logit contributions
working+0.009
 Claus+0.009
ny+0.008
ro+0.008
inky+0.008
Neg logit contributions
ement-0.011
irled-0.009
aw-0.008
bridge-0.008
irling-0.008
Token and
Token ID290
Feature activation+4.88e-01

Pos logit contributions
ement+0.014
bridge+0.012
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.012
 Claus-0.012
ny-0.011
inky-0.011
ley-0.011
Token he
Token ID339
Feature activation-2.68e-01

Pos logit contributions
ement+0.017
bridge+0.014
aw+0.013
irling+0.013
 swings+0.013
Neg logit contributions
working-0.014
 Claus-0.014
ny-0.013
ppy-0.013
ley-0.013
Token didn
Token ID1422
Feature activation+2.11e+00

Pos logit contributions
 Claus+0.008
working+0.008
ny+0.008
ppy+0.008
ley+0.007
Neg logit contributions
ement-0.009
bridge-0.007
aw-0.007
 sliding-0.007
 amaz-0.007
Token't
Token ID470
Feature activation-6.45e-01

Pos logit contributions
ement+0.089
bridge+0.074
 swings+0.072
aw+0.072
 amaz+0.071
Neg logit contributions
working-0.044
 Claus-0.043
inky-0.042
ppy-0.042
ny-0.041
Token know
Token ID760
Feature activation+1.50e+00

Pos logit contributions
inky+0.021
ley+0.020
 Claus+0.019
working+0.019
 Ho+0.018
Neg logit contributions
ement-0.018
bridge-0.016
 cal-0.016
 swings-0.016
 sliding-0.015
Token what
Token ID644
Feature activation-8.65e-02

Pos logit contributions
ement+0.055
aming+0.048
irled+0.047
aded+0.046
bridge+0.046
Neg logit contributions
working-0.034
ppy-0.034
 Claus-0.034
 Ho-0.034
ley-0.033
Token to
Token ID284
Feature activation+4.58e-01

Pos logit contributions
working+0.002
 Claus+0.002
ny+0.002
inky+0.002
ppy+0.002
Neg logit contributions
ement-0.003
bridge-0.002
aw-0.002
 amaz-0.002
 swings-0.002
Token do
Token ID466
Feature activation+8.31e-01

Pos logit contributions
ement+0.015
 swings+0.012
 amaz+0.011
bridge+0.011
 sliding+0.011
Neg logit contributions
working-0.014
inky-0.014
 Claus-0.014
ppy-0.014
ley-0.014
Token cry
Token ID3960
Feature activation-7.08e-01

Pos logit contributions
ley+0.042
 Claus+0.042
working+0.041
inky+0.041
ny+0.040
Neg logit contributions
ement-0.032
 sliding-0.028
 swings-0.027
 amaz-0.027
 soaring-0.026
Token Sammy
Token ID44067
Feature activation+5.33e-01

Pos logit contributions
working+0.025
 Claus+0.024
ley+0.024
 Cotton+0.023
pp+0.023
Neg logit contributions
ement-0.018
 sliding-0.014
aw-0.013
 mistakes-0.012
 shocked-0.012
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
ement+0.017
aw+0.013
 sliding+0.013
 swings+0.013
bridge+0.013
Neg logit contributions
 Claus-0.016
working-0.016
inky-0.015
ley-0.015
ppy-0.015
Token We
Token ID775
Feature activation+1.87e-04

Pos logit contributions
ement+0.006
bridge+0.005
aw+0.004
 swings+0.004
 amaz+0.004
Neg logit contributions
working-0.005
 Claus-0.005
ppy-0.004
inky-0.004
ny-0.004
Token can
Token ID460
Feature activation+1.62e+00

Pos logit contributions
ement+0.000
bridge+0.000
aw+0.000
 swings+0.000
 amaz+0.000
Neg logit contributions
working-0.000
 Claus-0.000
inky-0.000
ppy-0.000
ny-0.000
Token find
Token ID1064
Feature activation+2.31e+00

Pos logit contributions
ement+0.062
bridge+0.051
aw+0.050
 amaz+0.049
 swings+0.047
Neg logit contributions
inky-0.041
 Claus-0.041
working-0.041
ppy-0.039
ny-0.039
Token somewhere
Token ID7382
Feature activation+7.24e-01

Pos logit contributions
ement+0.084
bridge+0.069
irling+0.066
 amaz+0.064
uct+0.063
Neg logit contributions
working-0.059
inky-0.058
 Ho-0.058
ley-0.058
ppy-0.058
Token else
Token ID2073
Feature activation+1.86e-01

Pos logit contributions
ement+0.027
bridge+0.022
 amaz+0.020
aw+0.020
irled+0.019
Neg logit contributions
working-0.019
 Claus-0.019
ppy-0.019
ny-0.018
 guys-0.018
Token to
Token ID284
Feature activation+1.58e+00

Pos logit contributions
ement+0.007
bridge+0.006
 amaz+0.005
aw+0.005
irling+0.005
Neg logit contributions
working-0.005
 Claus-0.005
ppy-0.005
ny-0.005
inky-0.005
Token dance
Token ID9280
Feature activation+9.21e-01

Pos logit contributions
ement+0.069
aw+0.057
bridge+0.056
 amaz+0.053
uct+0.053
Neg logit contributions
working-0.032
inky-0.031
ny-0.031
 Claus-0.031
ppy-0.030
Token!"
Token ID2474
Feature activation+1.43e+00

Pos logit contributions
ement+0.028
 amaz+0.021
bridge+0.021
 swings+0.020
aw+0.020
Neg logit contributions
working-0.030
ny-0.030
ppy-0.030
 Claus-0.029
ro-0.029
Token,
Token ID11
Feature activation+4.98e-01

Pos logit contributions
ement+0.026
bridge+0.022
aded+0.022
 amaz+0.022
aw+0.021
Neg logit contributions
working-0.013
ny-0.012
ppy-0.012
 Claus-0.012
ro-0.012
Token but
Token ID475
Feature activation-1.03e-01

Pos logit contributions
ement+0.023
bridge+0.019
aw+0.019
aded+0.018
irled+0.018
Neg logit contributions
 Claus-0.008
ppy-0.008
working-0.008
ny-0.008
ro-0.008
Token the
Token ID262
Feature activation+8.17e-01

Pos logit contributions
working+0.003
 Claus+0.003
ppy+0.003
inky+0.002
ny+0.002
Neg logit contributions
ement-0.004
bridge-0.003
aw-0.003
irling-0.003
 amaz-0.003
Token sky
Token ID6766
Feature activation+2.61e-01

Pos logit contributions
ement+0.032
irled+0.024
irling+0.024
bridge+0.024
atted+0.024
Neg logit contributions
ny-0.022
working-0.022
ro-0.021
 guys-0.020
 Ho-0.020
Token was
Token ID373
Feature activation+1.02e+00

Pos logit contributions
ement+0.010
bridge+0.009
 amaz+0.009
irling+0.008
aw+0.008
Neg logit contributions
ny-0.006
y-0.006
working-0.006
 Claus-0.006
ley-0.006
Token full
Token ID1336
Feature activation+2.11e+00

Pos logit contributions
ement+0.042
aw+0.034
bridge+0.034
 amaz+0.032
aded+0.032
Neg logit contributions
working-0.025
ny-0.023
 Claus-0.022
y-0.022
ppy-0.021
Token of
Token ID286
Feature activation+2.39e+00

Pos logit contributions
ement+0.073
irling+0.068
cking+0.064
bridge+0.064
irled+0.064
Neg logit contributions
ny-0.058
y-0.055
ro-0.055
ppy-0.055
working-0.054
Token dark
Token ID3223
Feature activation+1.33e+00

Pos logit contributions
ement+0.087
uct+0.073
bridge+0.072
irling+0.069
ieved+0.067
Neg logit contributions
working-0.057
 guys-0.056
 Ho-0.052
ro-0.051
y-0.050
Token clouds
Token ID15114
Feature activation+9.73e-01

Pos logit contributions
ement+0.047
uct+0.041
irling+0.039
aded+0.038
 amaz+0.038
Neg logit contributions
working-0.035
ny-0.035
y-0.034
ro-0.034
ley-0.032
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
ement+0.033
bridge+0.027
 amaz+0.026
aded+0.025
irled+0.025
Neg logit contributions
working-0.029
ny-0.028
 Claus-0.028
ppy-0.027
inky-0.027
Token
Token ID198
Feature activation-7.53e-01

Pos logit contributions
working+0.005
 Claus+0.005
inky+0.005
ny+0.005
ppy+0.004
Neg logit contributions
ement-0.008
bridge-0.007
aw-0.006
 amaz-0.006
 swings-0.006
Token hold
Token ID1745
Feature activation+4.35e-01

Pos logit contributions
 Claus+0.005
ny+0.005
working+0.005
inky+0.005
ppy+0.005
Neg logit contributions
ement-0.006
bridge-0.005
aw-0.005
irling-0.005
 amaz-0.005
Token hands
Token ID2832
Feature activation+8.97e-02

Pos logit contributions
ement+0.011
bridge+0.009
 amaz+0.008
 swings+0.008
irling+0.008
Neg logit contributions
inky-0.016
working-0.016
ny-0.016
ppy-0.016
 Claus-0.016
Token and
Token ID290
Feature activation-9.87e-02

Pos logit contributions
ement+0.003
bridge+0.002
aw+0.002
 swings+0.002
 amaz+0.002
Neg logit contributions
working-0.003
 Claus-0.003
inky-0.003
ppy-0.003
ny-0.003
Token walk
Token ID2513
Feature activation-8.16e-01

Pos logit contributions
working+0.003
 Claus+0.003
inky+0.003
ny+0.003
ppy+0.003
Neg logit contributions
ement-0.004
bridge-0.003
aw-0.003
 swings-0.003
 amaz-0.003
Token away
Token ID1497
Feature activation-1.61e+00

Pos logit contributions
working+0.027
 Claus+0.027
inky+0.027
ppy+0.027
ny+0.026
Neg logit contributions
ement-0.024
bridge-0.018
aw-0.018
 swings-0.018
 amaz-0.017
Token from
Token ID422
Feature activation+1.36e+00

Pos logit contributions
working+0.059
ppy+0.058
inky+0.058
 Claus+0.057
ny+0.056
Neg logit contributions
ement-0.043
 swings-0.032
 sliding-0.032
 amaz-0.031
aw-0.031
Token the
Token ID262
Feature activation-5.10e-01

Pos logit contributions
ement+0.044
bridge+0.035
irling+0.032
aw+0.032
 amaz+0.032
Neg logit contributions
working-0.043
ley-0.042
 Claus-0.042
ny-0.041
ro-0.040
Token cage
Token ID17186
Feature activation+8.09e-01

Pos logit contributions
working+0.016
 Claus+0.016
inky+0.015
ny+0.015
ley+0.015
Neg logit contributions
ement-0.017
bridge-0.013
aw-0.012
 amaz-0.012
irled-0.012
Token.
Token ID13
Feature activation+6.50e-01

Pos logit contributions
ement+0.028
bridge+0.023
irling+0.022
 amaz+0.022
uct+0.022
Neg logit contributions
ro-0.022
ny-0.022
inky-0.022
 Claus-0.022
working-0.022
Token They
Token ID1119
Feature activation-4.00e-01

Pos logit contributions
ement+0.029
aw+0.025
 swings+0.025
bridge+0.025
 amaz+0.024
Neg logit contributions
working-0.012
ppy-0.012
 Claus-0.012
ley-0.012
inky-0.011
Token learn
Token ID2193
Feature activation+5.14e-01

Pos logit contributions
working+0.011
inky+0.011
 Claus+0.011
ppy+0.011
ny+0.011
Neg logit contributions
ement-0.014
bridge-0.011
 swings-0.011
aw-0.011
 amaz-0.011
Token but
Token ID475
Feature activation-6.30e-01

Pos logit contributions
working+0.002
 Claus+0.002
inky+0.002
ppy+0.001
ny+0.001
Neg logit contributions
ement-0.002
bridge-0.002
 swings-0.002
aw-0.002
 amaz-0.002
Token he
Token ID339
Feature activation-7.96e-01

Pos logit contributions
inky+0.021
working+0.021
 Claus+0.020
ory+0.020
ppy+0.020
Neg logit contributions
ement-0.017
 swings-0.014
 sliding-0.014
bridge-0.013
 shocked-0.013
Token knew
Token ID2993
Feature activation+5.43e-01

Pos logit contributions
working+0.025
 Claus+0.024
inky+0.024
ny+0.024
ppy+0.024
Neg logit contributions
ement-0.025
bridge-0.020
aw-0.019
 swings-0.019
 sliding-0.019
Token he
Token ID339
Feature activation-3.18e-01

Pos logit contributions
ement+0.023
 amaz+0.020
bridge+0.020
aming+0.019
irling+0.019
Neg logit contributions
 Ho-0.011
ppy-0.011
ley-0.011
working-0.010
 Claus-0.010
Token had
Token ID550
Feature activation-1.87e-01

Pos logit contributions
working+0.009
inky+0.009
 Claus+0.009
ppy+0.009
ny+0.009
Neg logit contributions
ement-0.011
bridge-0.008
 swings-0.008
aw-0.008
 sliding-0.008
Token to
Token ID284
Feature activation+1.58e-01

Pos logit contributions
working+0.003
 Claus+0.003
ppy+0.003
ny+0.003
 guys+0.003
Neg logit contributions
ement-0.009
bridge-0.008
irling-0.007
 amaz-0.007
aming-0.007
Token stay
Token ID2652
Feature activation+2.71e-01

Pos logit contributions
ement+0.005
 swings+0.004
 sliding+0.004
bridge+0.004
 amaz+0.004
Neg logit contributions
working-0.005
 Claus-0.005
ley-0.005
inky-0.005
ppy-0.005
Token on
Token ID319
Feature activation+4.88e-01

Pos logit contributions
ement+0.009
bridge+0.007
aw+0.007
 amaz+0.007
 swings+0.007
Neg logit contributions
 Claus-0.008
working-0.008
ppy-0.008
ny-0.008
inky-0.008
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
ement+0.015
bridge+0.011
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.016
 Claus-0.016
inky-0.016
ppy-0.016
ny-0.016
Token floor
Token ID4314
Feature activation+9.93e-01

Pos logit contributions
working+0.003
 Claus+0.003
inky+0.003
ny+0.003
 guys+0.003
Neg logit contributions
ement-0.005
 amaz-0.004
atted-0.004
bridge-0.004
irled-0.004
Token.
Token ID13
Feature activation-9.35e-01

Pos logit contributions
ement+0.031
bridge+0.024
aw+0.023
 swings+0.023
 amaz+0.023
Neg logit contributions
working-0.031
 Claus-0.031
inky-0.031
ppy-0.030
ny-0.030
Token of
Token ID286
Feature activation+6.69e-01

Pos logit contributions
ement+0.048
 amaz+0.039
irling+0.038
 swings+0.036
bridge+0.036
Neg logit contributions
ny-0.042
working-0.041
y-0.040
ppy-0.040
ro-0.039
Token the
Token ID262
Feature activation+8.44e-02

Pos logit contributions
ement+0.021
bridge+0.017
irling+0.016
irled+0.016
aw+0.015
Neg logit contributions
working-0.020
 Claus-0.019
ley-0.019
ny-0.019
 Ho-0.019
Token grass
Token ID8701
Feature activation+7.50e-01

Pos logit contributions
ement+0.002
bridge+0.002
irled+0.002
irling+0.002
 amaz+0.002
Neg logit contributions
working-0.003
ny-0.003
 Claus-0.003
inky-0.003
ro-0.003
Token made
Token ID925
Feature activation+4.93e-01

Pos logit contributions
ement+0.024
bridge+0.019
 amaz+0.018
 swings+0.018
irling+0.018
Neg logit contributions
working-0.023
 Claus-0.023
ny-0.023
inky-0.022
ley-0.022
Token her
Token ID607
Feature activation+9.67e-01

Pos logit contributions
ement+0.019
irling+0.016
bridge+0.016
 swings+0.015
 amaz+0.015
Neg logit contributions
working-0.011
ny-0.011
 Claus-0.010
inky-0.010
ppy-0.010
Token feel
Token ID1254
Feature activation+1.08e+00

Pos logit contributions
ement+0.041
bridge+0.035
aw+0.033
irling+0.033
aded+0.033
Neg logit contributions
 Claus-0.020
working-0.020
ny-0.020
inky-0.019
ppy-0.019
Token very
Token ID845
Feature activation+9.97e-01

Pos logit contributions
ement+0.040
 swings+0.033
bridge+0.032
irling+0.031
irled+0.030
Neg logit contributions
ny-0.027
 Ho-0.025
ppy-0.025
 Cotton-0.025
working-0.024
Token relaxed
Token ID18397
Feature activation+5.56e-01

Pos logit contributions
ement+0.032
bridge+0.028
 swings+0.025
aw+0.025
 sliding+0.024
Neg logit contributions
working-0.030
ny-0.029
 Claus-0.029
inky-0.029
ppy-0.028
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
ement+0.018
bridge+0.015
 swings+0.015
 amaz+0.015
irling+0.014
Neg logit contributions
ny-0.016
working-0.016
 Claus-0.016
ppy-0.016
ley-0.016
Token
Token ID220
Feature activation-8.37e-02

Pos logit contributions
ement+0.037
bridge+0.032
irling+0.030
aw+0.029
 swings+0.029
Neg logit contributions
working-0.030
inky-0.030
ny-0.030
 Claus-0.029
ro-0.028
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
working+0.002
 Claus+0.002
inky+0.002
ppy+0.002
ny+0.002
Neg logit contributions
ement-0.003
bridge-0.002
aw-0.002
 swings-0.002
 amaz-0.002
Token park
Token ID3952
Feature activation+3.63e-01

Pos logit contributions
ement+0.029
bridge+0.020
 amaz+0.019
uct+0.019
atted+0.018
Neg logit contributions
ny-0.030
working-0.029
inky-0.027
ro-0.027
 Claus-0.027
Token.
Token ID13
Feature activation-9.96e-01

Pos logit contributions
ement+0.013
bridge+0.010
 amaz+0.010
irling+0.010
uct+0.010
Neg logit contributions
working-0.010
ny-0.010
 Claus-0.010
ro-0.010
ppy-0.010
Token Spot
Token ID15899
Feature activation-7.69e-01

Pos logit contributions
working+0.028
ppy+0.028
pp+0.027
ley+0.027
 Claus+0.026
Neg logit contributions
ement-0.034
 swings-0.032
aw-0.029
 sliding-0.029
 waves-0.028
Token would
Token ID561
Feature activation-2.24e-01

Pos logit contributions
working+0.026
inky+0.026
 Claus+0.025
ley+0.024
ppy+0.024
Neg logit contributions
ement-0.021
 swings-0.017
aw-0.017
 sliding-0.016
 waves-0.016
Token throw
Token ID3714
Feature activation-1.09e+00

Pos logit contributions
working+0.006
 Claus+0.006
inky+0.006
ny+0.006
ppy+0.006
Neg logit contributions
ement-0.008
bridge-0.006
aw-0.006
 amaz-0.006
 swings-0.006
Token the
Token ID262
Feature activation+1.47e+00

Pos logit contributions
 Claus+0.047
working+0.047
inky+0.045
ppy+0.045
ley+0.043
Neg logit contributions
ement-0.022
 swings-0.018
aw-0.018
 waves-0.016
 sliding-0.016
Token pipe
Token ID12656
Feature activation+7.26e-01

Pos logit contributions
ement+0.049
bridge+0.037
aw+0.036
 amaz+0.036
irling+0.035
Neg logit contributions
working-0.046
ny-0.045
inky-0.044
 Claus-0.044
ppy-0.044
Token and
Token ID290
Feature activation-1.01e-01

Pos logit contributions
ement+0.024
bridge+0.019
 swings+0.018
aw+0.018
 sliding+0.018
Neg logit contributions
working-0.022
 Claus-0.021
inky-0.021
ppy-0.021
ley-0.021
Token then
Token ID788
Feature activation-6.38e-02

Pos logit contributions
working+0.003
inky+0.003
 Claus+0.003
ppy+0.003
ny+0.003
Neg logit contributions
ement-0.003
 swings-0.003
bridge-0.003
 sliding-0.003
 amaz-0.003
Token run
Token ID1057
Feature activation-9.56e-01

Pos logit contributions
inky+0.002
working+0.002
 Claus+0.002
ppy+0.002
ley+0.002
Neg logit contributions
ement-0.002
 swings-0.002
bridge-0.002
 sliding-0.002
aw-0.002
Token to
Token ID284
Feature activation-7.07e-01

Pos logit contributions
 Claus+0.032
working+0.031
ppy+0.031
inky+0.030
ley+0.030
Neg logit contributions
ement-0.027
 swings-0.023
aw-0.022
 sliding-0.022
bridge-0.021
Token She
Token ID1375
Feature activation+5.45e-01

Pos logit contributions
ement+0.001
aw+0.001
 swings+0.001
bridge+0.001
 amaz+0.001
Neg logit contributions
working-0.001
 Claus-0.001
ley-0.001
ppy-0.001
ny-0.001
Token said
Token ID531
Feature activation+9.37e-01

Pos logit contributions
ement+0.017
bridge+0.014
aw+0.013
 swings+0.013
 amaz+0.013
Neg logit contributions
working-0.017
 Claus-0.017
ppy-0.016
inky-0.016
ny-0.016
Token,
Token ID11
Feature activation-2.63e-01

Pos logit contributions
ement+0.035
bridge+0.029
aw+0.028
 swings+0.028
 amaz+0.028
Neg logit contributions
working-0.024
 Claus-0.023
inky-0.023
ppy-0.022
ny-0.022
Token "
Token ID366
Feature activation+6.09e-02

Pos logit contributions
working+0.008
inky+0.008
 Claus+0.007
ny+0.007
ley+0.007
Neg logit contributions
ement-0.009
bridge-0.007
 swings-0.007
 sliding-0.007
aw-0.007
TokenI
Token ID40
Feature activation-4.46e-01

Pos logit contributions
ement+0.002
aw+0.002
bridge+0.002
 swings+0.001
 waves+0.001
Neg logit contributions
working-0.002
inky-0.002
 Claus-0.002
ppy-0.002
ley-0.002
Token want
Token ID765
Feature activation+6.16e-01

Pos logit contributions
inky+0.014
ley+0.013
 Claus+0.013
 Cotton+0.012
ppy+0.012
Neg logit contributions
ement-0.012
 amaz-0.011
 swings-0.011
aw-0.010
 sliding-0.010
Token to
Token ID284
Feature activation+9.72e-01

Pos logit contributions
ement+0.023
bridge+0.018
aw+0.018
 swings+0.018
 amaz+0.018
Neg logit contributions
working-0.016
 Claus-0.016
inky-0.016
ppy-0.016
ny-0.016
Token look
Token ID804
Feature activation+7.08e-01

Pos logit contributions
ement+0.030
 swings+0.026
bridge+0.025
 amaz+0.025
aw+0.024
Neg logit contributions
working-0.029
ley-0.029
inky-0.029
 Claus-0.029
ppy-0.028
Token like
Token ID588
Feature activation+9.01e-01

Pos logit contributions
ement+0.022
bridge+0.017
aw+0.016
 swings+0.016
 amaz+0.016
Neg logit contributions
working-0.023
 Claus-0.023
inky-0.023
ppy-0.022
ny-0.022
Token a
Token ID257
Feature activation+9.13e-02

Pos logit contributions
ement+0.031
bridge+0.023
irling+0.023
irled+0.023
uct+0.023
Neg logit contributions
working-0.026
 Claus-0.026
ppy-0.025
inky-0.025
 Ho-0.025
Token peac
Token ID41961
Feature activation-5.86e-01

Pos logit contributions
ement+0.003
 swings+0.002
bridge+0.002
aw+0.002
 amaz+0.002
Neg logit contributions
working-0.003
ppy-0.003
inky-0.003
ley-0.003
 Claus-0.003
Token.
Token ID13
Feature activation+6.04e-02

Pos logit contributions
working+0.036
 Claus+0.035
inky+0.035
ppy+0.035
ny+0.034
Neg logit contributions
ement-0.028
bridge-0.021
aw-0.021
 swings-0.021
 amaz-0.020
Token
Token ID198
Feature activation+2.79e-02

Pos logit contributions
ement+0.002
 swings+0.002
aw+0.002
 amaz+0.002
bridge+0.002
Neg logit contributions
working-0.001
 Claus-0.001
ley-0.001
ppy-0.001
ny-0.001
Token
Token ID198
Feature activation-8.19e-02

Pos logit contributions
ement+0.001
 swings+0.001
aw+0.001
bridge+0.001
 sliding+0.001
Neg logit contributions
working-0.001
 Claus-0.001
ppy-0.001
ley-0.001
inky-0.001
Token"
Token ID1
Feature activation+6.00e-01

Pos logit contributions
working+0.003
 Claus+0.003
ley+0.003
inky+0.003
ppy+0.002
Neg logit contributions
ement-0.002
aw-0.002
 sliding-0.002
 swings-0.002
aming-0.002
TokenNow
Token ID3844
Feature activation-3.09e-01

Pos logit contributions
ement+0.020
bridge+0.016
 amaz+0.015
aw+0.015
 swings+0.015
Neg logit contributions
working-0.018
 Claus-0.018
inky-0.017
ny-0.017
ppy-0.017
Token you
Token ID345
Feature activation-6.93e-01

Pos logit contributions
working+0.009
inky+0.008
 Claus+0.008
ny+0.008
ppy+0.008
Neg logit contributions
ement-0.011
 swings-0.009
bridge-0.009
aw-0.009
 amaz-0.009
Token have
Token ID423
Feature activation-2.41e-01

Pos logit contributions
working+0.019
ley+0.018
inky+0.018
 Claus+0.018
ny+0.018
Neg logit contributions
ement-0.024
 swings-0.020
bridge-0.020
aw-0.020
 amaz-0.019
Token no
Token ID645
Feature activation+1.02e+00

Pos logit contributions
working+0.006
 Claus+0.006
inky+0.005
ppy+0.005
ny+0.005
Neg logit contributions
ement-0.010
bridge-0.008
 amaz-0.008
irling-0.008
aw-0.007
Token red
Token ID2266
Feature activation+5.74e-01

Pos logit contributions
ement+0.037
bridge+0.030
uct+0.030
aw+0.029
aming+0.028
Neg logit contributions
working-0.029
ny-0.027
 Claus-0.027
inky-0.026
ro-0.026
Token car
Token ID1097
Feature activation-2.27e-01

Pos logit contributions
ement+0.016
 swings+0.013
bridge+0.013
aw+0.012
 sliding+0.012
Neg logit contributions
working-0.020
 Claus-0.020
ppy-0.020
inky-0.019
ny-0.019
Token.
Token ID13
Feature activation+2.34e-01

Pos logit contributions
working+0.007
inky+0.007
 Claus+0.007
ppy+0.007
ley+0.007
Neg logit contributions
ement-0.007
aw-0.005
bridge-0.005
 swings-0.005
 sliding-0.005
Token little
Token ID1310
Feature activation-4.30e-03

Pos logit contributions
ement+0.019
 swings+0.015
aw+0.015
bridge+0.014
 sliding+0.014
Neg logit contributions
working-0.020
ppy-0.020
inky-0.020
 Claus-0.020
ley-0.020
Token boy
Token ID2933
Feature activation+6.61e-01

Pos logit contributions
working+0.000
 Claus+0.000
inky+0.000
ppy+0.000
isk+0.000
Neg logit contributions
ement-0.000
 swings-0.000
aw-0.000
 waves-0.000
 sliding-0.000
Token named
Token ID3706
Feature activation-1.04e+00

Pos logit contributions
ement+0.022
bridge+0.017
 amaz+0.016
 swings+0.016
aw+0.016
Neg logit contributions
working-0.021
 Claus-0.020
inky-0.020
ppy-0.020
ny-0.020
Token Jack
Token ID3619
Feature activation+2.49e-01

Pos logit contributions
working+0.037
 Claus+0.035
ley+0.035
inky+0.034
ro+0.034
Neg logit contributions
ement-0.026
 swings-0.024
 sliding-0.024
 waves-0.021
bridge-0.021
Token.
Token ID13
Feature activation+6.08e-02

Pos logit contributions
ement+0.007
bridge+0.005
aw+0.005
 swings+0.005
 amaz+0.005
Neg logit contributions
working-0.009
inky-0.009
 Claus-0.009
ppy-0.008
ny-0.008
Token He
Token ID679
Feature activation-5.37e-01

Pos logit contributions
ement+0.002
bridge+0.002
 amaz+0.002
 sliding+0.002
 swings+0.002
Neg logit contributions
inky-0.002
 Claus-0.002
working-0.002
ley-0.002
ppy-0.002
Token loved
Token ID6151
Feature activation+1.03e-01

Pos logit contributions
working+0.019
inky+0.018
 Claus+0.018
ppy+0.018
ley+0.018
Neg logit contributions
ement-0.014
 swings-0.011
bridge-0.011
aw-0.011
 sliding-0.011
Token to
Token ID284
Feature activation-1.26e-01

Pos logit contributions
ement+0.004
bridge+0.003
 amaz+0.003
aw+0.003
irling+0.003
Neg logit contributions
working-0.003
 Claus-0.002
inky-0.002
ny-0.002
ppy-0.002
Token tell
Token ID1560
Feature activation-6.04e-01

Pos logit contributions
working+0.003
 Claus+0.003
inky+0.003
ny+0.003
ppy+0.003
Neg logit contributions
ement-0.005
bridge-0.004
aw-0.004
 amaz-0.004
 swings-0.004
Token jokes
Token ID14532
Feature activation-1.26e+00

Pos logit contributions
working+0.020
 Claus+0.020
inky+0.019
ppy+0.019
ny+0.019
Neg logit contributions
ement-0.018
bridge-0.014
 swings-0.014
aw-0.014
 amaz-0.013
Token to
Token ID284
Feature activation-6.70e-01

Pos logit contributions
inky+0.046
working+0.046
 Claus+0.045
ppy+0.045
ley+0.045
Neg logit contributions
ement-0.033
bridge-0.024
aw-0.024
 swings-0.024
 sliding-0.023
Token more
Token ID517
Feature activation+1.86e-01

Pos logit contributions
inky+0.062
working+0.061
 Claus+0.061
ppy+0.060
ny+0.059
Neg logit contributions
ement-0.039
bridge-0.028
 swings-0.027
aw-0.027
 sliding-0.026
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
ement+0.006
bridge+0.005
 amaz+0.005
 swings+0.005
aded+0.005
Neg logit contributions
working-0.006
 Claus-0.005
inky-0.005
ppy-0.005
ny-0.005
Token Her
Token ID2332
Feature activation+2.49e-01

Pos logit contributions
ement+0.009
 swings+0.007
uct+0.007
 amaz+0.007
aw+0.007
Neg logit contributions
working-0.007
ley-0.007
pp-0.007
ppy-0.007
 Claus-0.007
Token mom
Token ID1995
Feature activation+2.58e-01

Pos logit contributions
ement+0.009
bridge+0.008
aw+0.007
alled+0.007
irling+0.007
Neg logit contributions
inky-0.007
 Claus-0.007
working-0.007
 Ho-0.007
ro-0.007
Tokenmy
Token ID1820
Feature activation-1.22e-01

Pos logit contributions
ement+0.011
bridge+0.009
 amaz+0.009
 soaring+0.009
irling+0.009
Neg logit contributions
 Claus-0.006
ppy-0.006
ny-0.006
ley-0.006
y-0.005
Token took
Token ID1718
Feature activation-1.30e+00

Pos logit contributions
 Claus+0.004
ppy+0.003
ley+0.003
ny+0.003
inky+0.003
Neg logit contributions
ement-0.005
bridge-0.004
 amaz-0.004
irling-0.004
 awesome-0.003
Token her
Token ID607
Feature activation-6.94e-01

Pos logit contributions
working+0.045
 Claus+0.045
inky+0.043
ppy+0.042
pp+0.042
Neg logit contributions
ement-0.036
aw-0.029
bridge-0.028
 swings-0.028
 cal-0.027
Token to
Token ID284
Feature activation-1.35e+00

Pos logit contributions
working+0.018
 Claus+0.018
inky+0.018
ppy+0.018
ny+0.018
Neg logit contributions
ement-0.026
bridge-0.021
aw-0.020
 swings-0.020
 amaz-0.020
Token the
Token ID262
Feature activation-7.49e-02

Pos logit contributions
working+0.045
 Claus+0.044
inky+0.044
ppy+0.043
ny+0.043
Neg logit contributions
ement-0.041
bridge-0.031
aw-0.030
 swings-0.030
 amaz-0.030
Token hospital
Token ID4436
Feature activation-3.01e-01

Pos logit contributions
working+0.002
 Claus+0.002
inky+0.002
ny+0.002
ppy+0.002
Neg logit contributions
ement-0.002
bridge-0.002
aw-0.002
 amaz-0.002
 swings-0.002
Token.
Token ID13
Feature activation-3.58e-01

Pos logit contributions
inky+0.009
working+0.009
ppy+0.009
ny+0.009
ley+0.009
Neg logit contributions
ement-0.010
 swings-0.007
 sliding-0.007
 amaz-0.007
bridge-0.007
Token of
Token ID286
Feature activation-5.41e-01

Pos logit contributions
ement+0.017
bridge+0.012
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.031
inky-0.030
 Claus-0.030
ny-0.030
ppy-0.030
Token the
Token ID262
Feature activation-2.17e-01

Pos logit contributions
working+0.018
 Claus+0.018
inky+0.018
ny+0.018
ley+0.018
Neg logit contributions
ement-0.016
bridge-0.012
aw-0.012
 swings-0.012
 amaz-0.011
Token night
Token ID1755
Feature activation-4.82e-02

Pos logit contributions
working+0.006
 Claus+0.006
inky+0.006
ny+0.006
ppy+0.006
Neg logit contributions
ement-0.008
bridge-0.006
aw-0.006
 swings-0.006
 amaz-0.006
Token,
Token ID11
Feature activation+2.07e-01

Pos logit contributions
inky+0.001
working+0.001
ppy+0.001
 Claus+0.001
ny+0.001
Neg logit contributions
ement-0.002
bridge-0.001
aw-0.001
 swings-0.001
 amaz-0.001
Token all
Token ID477
Feature activation+3.45e-01

Pos logit contributions
ement+0.006
 swings+0.004
 amaz+0.004
 sliding+0.004
bridge+0.004
Neg logit contributions
inky-0.007
working-0.007
ppy-0.007
ny-0.007
 Claus-0.007
Token of
Token ID286
Feature activation-5.25e-01

Pos logit contributions
ement+0.010
bridge+0.008
 swings+0.008
aw+0.008
irling+0.008
Neg logit contributions
working-0.011
ley-0.011
ny-0.011
ppy-0.011
 Claus-0.011
Token the
Token ID262
Feature activation+5.69e-02

Pos logit contributions
working+0.018
 Claus+0.018
inky+0.018
ny+0.018
ppy+0.018
Neg logit contributions
ement-0.015
bridge-0.011
 swings-0.011
aw-0.011
 amaz-0.011
Token girl
Token ID2576
Feature activation+9.28e-01

Pos logit contributions
ement+0.002
bridge+0.001
aw+0.001
 amaz+0.001
 swings+0.001
Neg logit contributions
working-0.002
 Claus-0.002
inky-0.002
ley-0.002
ny-0.002
Tokenâ
Token ID22940
Feature activation-5.30e-01

Pos logit contributions
ement+0.033
bridge+0.027
 amaz+0.025
 swings+0.025
aw+0.025
Neg logit contributions
 Claus-0.026
working-0.025
ppy-0.025
ny-0.025
ley-0.025
Token€
Token ID26391
Feature activation+5.68e-01

Pos logit contributions
working+0.015
 Claus+0.015
inky+0.015
ppy+0.014
ny+0.014
Neg logit contributions
ement-0.018
bridge-0.015
aw-0.014
 swings-0.014
 amaz-0.014
Tokenâ„¢
Token ID8151
Feature activation+1.66e+00

Pos logit contributions
ement+0.021
bridge+0.017
 swings+0.016
 amaz+0.016
aw+0.016
Neg logit contributions
 Claus-0.015
working-0.015
inky-0.015
ppy-0.014
ny-0.014
Token and
Token ID290
Feature activation+6.16e-01

Pos logit contributions
working+0.018
 Claus+0.018
ny+0.017
ppy+0.017
ley+0.017
Neg logit contributions
ement-0.028
bridge-0.023
aw-0.022
 swings-0.022
irling-0.022
Token cl
Token ID537
Feature activation-9.33e-02

Pos logit contributions
ement+0.023
bridge+0.018
aw+0.017
 amaz+0.017
 swings+0.017
Neg logit contributions
working-0.018
 Claus-0.017
ny-0.016
ley-0.016
ppy-0.015
Tokenapped
Token ID6320
Feature activation-1.32e+00

Pos logit contributions
working+0.003
inky+0.003
 Claus+0.003
ppy+0.003
ny+0.003
Neg logit contributions
ement-0.003
bridge-0.002
 swings-0.002
aw-0.002
 amaz-0.002
Token his
Token ID465
Feature activation-4.98e-01

Pos logit contributions
working+0.033
ny+0.032
ppy+0.032
inky+0.031
 Claus+0.031
Neg logit contributions
ement-0.050
bridge-0.040
 swings-0.040
aw-0.039
 amaz-0.038
Token paws
Token ID49193
Feature activation+3.87e-01

Pos logit contributions
ny+0.018
inky+0.018
 Claus+0.018
working+0.018
ppy+0.018
Neg logit contributions
ement-0.014
bridge-0.010
aw-0.010
 sliding-0.009
 swings-0.009
Token together
Token ID1978
Feature activation-3.28e-01

Pos logit contributions
ement+0.014
bridge+0.011
aw+0.011
 swings+0.011
 amaz+0.011
Neg logit contributions
working-0.011
ny-0.011
 Claus-0.010
inky-0.010
ppy-0.010
Token to
Token ID284
Feature activation+7.75e-01

Pos logit contributions
working+0.009
ny+0.009
 Claus+0.009
ppy+0.009
ro+0.009
Neg logit contributions
ement-0.011
bridge-0.009
aw-0.009
 swings-0.009
irled-0.009
Token applaud
Token ID22517
Feature activation-6.96e-01

Pos logit contributions
ement+0.029
bridge+0.023
aw+0.022
irled+0.021
aming+0.021
Neg logit contributions
working-0.021
 Claus-0.020
ny-0.019
ppy-0.019
ro-0.019
Token the
Token ID262
Feature activation+2.68e-02

Pos logit contributions
inky+0.025
working+0.025
 Claus+0.025
ppy+0.024
ny+0.023
Neg logit contributions
ement-0.019
aw-0.015
bridge-0.015
 swings-0.014
 amaz-0.014
Token train
Token ID4512
Feature activation+1.32e+00

Pos logit contributions
ement+0.001
aw+0.001
bridge+0.001
uct+0.001
irled+0.001
Neg logit contributions
working-0.001
ny-0.001
 Claus-0.001
ley-0.001
inky-0.001
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
ement+0.042
bridge+0.032
aw+0.032
 amaz+0.031
irling+0.031
Neg logit contributions
working-0.041
 Claus-0.041
ny-0.040
inky-0.039
ppy-0.039
Token.
Token ID13
Feature activation-6.31e-01

Pos logit contributions
working+0.011
 Claus+0.011
inky+0.011
ppy+0.011
ny+0.011
Neg logit contributions
ement-0.008
bridge-0.006
aw-0.006
 swings-0.006
 sliding-0.006
Token One
Token ID1881
Feature activation+5.49e-01

Pos logit contributions
working+0.018
 Claus+0.018
ley+0.017
ppy+0.017
inky+0.017
Neg logit contributions
ement-0.022
 swings-0.019
 circles-0.017
bridge-0.017
 sliding-0.017
Token day
Token ID1110
Feature activation-1.25e+00

Pos logit contributions
ement+0.020
bridge+0.016
aw+0.016
 swings+0.016
 sliding+0.016
Neg logit contributions
 Claus-0.015
working-0.014
inky-0.014
ppy-0.014
ley-0.014
Token,
Token ID11
Feature activation-8.89e-01

Pos logit contributions
 Claus+0.053
ley+0.050
ppy+0.050
ny+0.049
isk+0.049
Neg logit contributions
ement-0.025
 sliding-0.023
 swinging-0.020
irled-0.018
aw-0.017
Token Lily
Token ID20037
Feature activation-3.56e-01

Pos logit contributions
inky+0.030
 Claus+0.030
ny+0.030
ppy+0.029
ley+0.029
Neg logit contributions
ement-0.023
 swings-0.022
 sliding-0.021
 swinging-0.019
bridge-0.019
Token and
Token ID290
Feature activation-2.76e+00

Pos logit contributions
working+0.011
 Claus+0.010
inky+0.010
ppy+0.010
ny+0.010
Neg logit contributions
ement-0.012
bridge-0.009
aw-0.009
 swings-0.009
 amaz-0.009
Token her
Token ID607
Feature activation+7.55e-02

Pos logit contributions
inky+0.108
ub+0.104
ro+0.104
ppy+0.103
 Claus+0.103
Neg logit contributions
ement-0.060
 swings-0.055
 sliding-0.049
 swinging-0.048
uct-0.046
Token friends
Token ID2460
Feature activation-8.75e-01

Pos logit contributions
ement+0.002
bridge+0.002
uct+0.002
 amaz+0.002
aw+0.002
Neg logit contributions
inky-0.003
working-0.003
 Claus-0.003
ppy-0.002
ny-0.002
Token found
Token ID1043
Feature activation+1.03e+00

Pos logit contributions
working+0.026
 Claus+0.026
inky+0.026
ppy+0.025
ny+0.025
Neg logit contributions
ement-0.029
bridge-0.022
aw-0.022
 swings-0.022
 amaz-0.022
Token a
Token ID257
Feature activation-2.77e-01

Pos logit contributions
ement+0.035
bridge+0.027
irling+0.026
 amaz+0.026
 swings+0.026
Neg logit contributions
working-0.030
inky-0.030
 Claus-0.030
ppy-0.029
ny-0.029
Token big
Token ID1263
Feature activation+9.70e-01

Pos logit contributions
ppy+0.011
ley+0.011
working+0.011
ny+0.010
ro+0.010
Neg logit contributions
ement-0.006
 swings-0.005
 sliding-0.004
 soaring-0.004
 awesome-0.004
Token this
Token ID428
Feature activation-2.91e-01

Pos logit contributions
inky+0.023
working+0.023
 Claus+0.022
ny+0.022
ppy+0.022
Neg logit contributions
ement-0.027
bridge-0.022
 swings-0.022
aw-0.021
 amaz-0.021
Token is
Token ID318
Feature activation-1.85e+00

Pos logit contributions
working+0.010
 Claus+0.009
inky+0.009
ny+0.009
ppy+0.009
Neg logit contributions
ement-0.009
bridge-0.007
aw-0.006
 swings-0.006
 amaz-0.006
Token Mr
Token ID1770
Feature activation-1.21e+00

Pos logit contributions
inky+0.064
working+0.064
 Claus+0.063
ley+0.062
ny+0.062
Neg logit contributions
ement-0.049
 swings-0.040
 awesome-0.038
bridge-0.038
 sliding-0.038
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
working+0.051
inky+0.049
 While+0.048
ub+0.048
ro+0.047
Neg logit contributions
ement-0.023
aw-0.016
 swings-0.014
bridge-0.012
 cal-0.012
Token Jones
Token ID5437
Feature activation+1.07e-01

Pos logit contributions
inky+0.034
working+0.034
ppy+0.033
ny+0.031
pp+0.030
Neg logit contributions
ement-0.057
 amaz-0.052
 horror-0.047
bridge-0.046
 swings-0.046
Token.
Token ID13
Feature activation-2.62e+00

Pos logit contributions
ement+0.003
aw+0.002
 swings+0.002
bridge+0.002
 sliding+0.002
Neg logit contributions
working-0.004
inky-0.004
 Claus-0.003
ny-0.003
ppy-0.003
Token He
Token ID679
Feature activation-1.25e+00

Pos logit contributions
working+0.088
pp+0.076
by+0.074
ppy+0.074
ley+0.073
Neg logit contributions
ement-0.077
bridge-0.066
 amaz-0.062
 cheers-0.061
aw-0.060
Token is
Token ID318
Feature activation-1.32e+00

Pos logit contributions
inky+0.042
working+0.042
ppy+0.041
ro+0.040
ley+0.040
Neg logit contributions
ement-0.034
aw-0.027
 swings-0.027
bridge-0.025
 waves-0.025
Token a
Token ID257
Feature activation-8.42e-01

Pos logit contributions
inky+0.047
working+0.047
ley+0.046
ppy+0.046
ro+0.046
Neg logit contributions
ement-0.032
 swings-0.027
 sliding-0.026
 awesome-0.025
 soaring-0.025
Token friend
Token ID1545
Feature activation-1.19e-01

Pos logit contributions
ppy+0.031
inky+0.030
ley+0.030
working+0.029
ro+0.029
Neg logit contributions
ement-0.020
 swings-0.016
 amaz-0.016
bridge-0.015
 awesome-0.015
Token from
Token ID422
Feature activation-2.83e-01

Pos logit contributions
working+0.004
inky+0.004
 Claus+0.004
ppy+0.004
ny+0.004
Neg logit contributions
ement-0.004
bridge-0.003
aw-0.003
 swings-0.003
 sliding-0.003
Token!"
Token ID2474
Feature activation-6.56e-02

Pos logit contributions
ement+0.046
bridge+0.036
 amaz+0.035
aw+0.034
 swings+0.033
Neg logit contributions
working-0.045
inky-0.045
ny-0.045
 Claus-0.045
ppy-0.044
Token
Token ID198
Feature activation+3.49e-01

Pos logit contributions
working+0.002
 Claus+0.002
inky+0.002
ppy+0.002
ny+0.002
Neg logit contributions
ement-0.002
bridge-0.002
aw-0.002
 swings-0.002
 amaz-0.002
Token
Token ID198
Feature activation+3.66e-01

Pos logit contributions
ement+0.014
bridge+0.012
 amaz+0.011
 swings+0.011
aw+0.011
Neg logit contributions
inky-0.008
 Claus-0.008
working-0.008
ny-0.008
ppy-0.008
TokenBut
Token ID1537
Feature activation+4.71e-01

Pos logit contributions
ement+0.010
aw+0.008
 swings+0.008
bridge+0.008
irling+0.008
Neg logit contributions
working-0.013
 Claus-0.012
inky-0.012
ley-0.012
ppy-0.012
Token Ben
Token ID3932
Feature activation+5.53e-01

Pos logit contributions
ement+0.014
bridge+0.011
 swings+0.011
 sliding+0.011
aw+0.011
Neg logit contributions
working-0.016
inky-0.016
 Claus-0.015
ny-0.015
ppy-0.015
Token and
Token ID290
Feature activation-2.52e+00

Pos logit contributions
ement+0.020
bridge+0.017
 amaz+0.016
irling+0.016
 soaring+0.016
Neg logit contributions
ny-0.015
 Claus-0.015
ppy-0.014
ro-0.014
working-0.014
Token Mia
Token ID32189
Feature activation+9.08e-01

Pos logit contributions
working+0.085
 Claus+0.084
inky+0.084
ppy+0.081
ny+0.081
Neg logit contributions
ement-0.074
bridge-0.057
 swings-0.056
aw-0.055
 amaz-0.055
Token did
Token ID750
Feature activation+2.22e-01

Pos logit contributions
ement+0.035
bridge+0.030
irling+0.029
 amaz+0.029
 awesome+0.028
Neg logit contributions
ny-0.022
ppy-0.022
 Claus-0.021
ro-0.019
ley-0.019
Token not
Token ID407
Feature activation-2.14e-01

Pos logit contributions
ement+0.008
bridge+0.006
aw+0.006
 amaz+0.006
 swings+0.006
Neg logit contributions
working-0.006
 Claus-0.006
inky-0.006
ny-0.006
ppy-0.006
Token stop
Token ID2245
Feature activation+1.24e+00

Pos logit contributions
inky+0.006
ley+0.006
working+0.006
 Claus+0.006
 Cotton+0.006
Neg logit contributions
ement-0.006
 sliding-0.006
 cal-0.006
 swings-0.006
bridge-0.005
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
ement+0.041
bridge+0.034
aw+0.031
 amaz+0.030
 swings+0.030
Neg logit contributions
working-0.038
 Claus-0.037
ny-0.036
ppy-0.036
inky-0.036
Token<|endoftext|>
Token ID50256
Feature activation+4.34e-01

Pos logit contributions
ement+0.036
aw+0.028
 swings+0.027
bridge+0.027
 sliding+0.027
Neg logit contributions
working-0.034
ppy-0.032
 Claus-0.031
ley-0.031
inky-0.031
TokenOne
Token ID3198
Feature activation+9.32e-01

Pos logit contributions
ement+0.017
bridge+0.014
 amaz+0.014
 swings+0.014
aw+0.014
Neg logit contributions
working-0.010
 Claus-0.010
inky-0.010
ny-0.010
ppy-0.010
Token day
Token ID1110
Feature activation-6.18e-01

Pos logit contributions
ement+0.044
bridge+0.040
 wounds+0.037
irling+0.037
 swings+0.036
Neg logit contributions
working-0.017
ny-0.015
y-0.013
by-0.013
ory-0.012
Token,
Token ID11
Feature activation-9.88e-01

Pos logit contributions
 Claus+0.020
inky+0.019
working+0.019
ppy+0.019
ley+0.019
Neg logit contributions
ement-0.018
 sliding-0.015
irled-0.014
aw-0.014
aded-0.014
Token Chad
Token ID19800
Feature activation-6.03e-02

Pos logit contributions
 Claus+0.039
ppy+0.039
ley+0.038
working+0.038
inky+0.038
Neg logit contributions
ement-0.021
 sliding-0.018
 swings-0.016
bridge-0.016
aw-0.016
Token and
Token ID290
Feature activation-2.60e+00

Pos logit contributions
working+0.002
 Claus+0.002
ny+0.002
inky+0.002
ppy+0.002
Neg logit contributions
ement-0.002
bridge-0.002
 swings-0.002
 amaz-0.002
aw-0.002
Token his
Token ID465
Feature activation+1.43e-01

Pos logit contributions
inky+0.098
ppy+0.097
ro+0.093
working+0.093
pp+0.091
Neg logit contributions
ement-0.057
 waves-0.051
 swings-0.051
 sliding-0.049
 amaz-0.048
Token mom
Token ID1995
Feature activation-4.04e-01

Pos logit contributions
ement+0.004
bridge+0.003
aw+0.003
 swings+0.003
 amaz+0.003
Neg logit contributions
working-0.005
 Claus-0.005
inky-0.005
ppy-0.005
ny-0.005
Token went
Token ID1816
Feature activation-4.21e-01

Pos logit contributions
working+0.011
inky+0.011
 Claus+0.010
ppy+0.010
ro+0.010
Neg logit contributions
ement-0.014
aw-0.012
 swings-0.012
bridge-0.011
 sliding-0.011
Token to
Token ID284
Feature activation-5.90e-01

Pos logit contributions
ppy+0.013
inky+0.013
working+0.013
 Claus+0.013
ley+0.013
Neg logit contributions
ement-0.012
 sliding-0.010
 swings-0.010
 waves-0.010
 soaring-0.010
Token the
Token ID262
Feature activation+6.90e-01

Pos logit contributions
working+0.023
inky+0.023
ppy+0.023
 Claus+0.022
ny+0.022
Neg logit contributions
ement-0.014
 swings-0.010
 amaz-0.010
 sliding-0.010
bridge-0.010
Token became
Token ID2627
Feature activation-8.99e-01

Pos logit contributions
working+0.024
 Claus+0.024
ny+0.023
inky+0.023
ley+0.023
Neg logit contributions
ement-0.027
bridge-0.021
aw-0.020
 amaz-0.020
irling-0.020
Token too
Token ID1165
Feature activation+2.00e-01

Pos logit contributions
working+0.027
ny+0.026
 Claus+0.026
ppy+0.026
inky+0.025
Neg logit contributions
ement-0.031
bridge-0.024
aw-0.023
 amaz-0.023
 swings-0.022
Token hard
Token ID1327
Feature activation-2.34e-01

Pos logit contributions
ement+0.005
aw+0.004
 sliding+0.004
 swings+0.004
irling+0.004
Neg logit contributions
 Claus-0.007
ppy-0.007
inky-0.007
ley-0.007
working-0.007
Token.
Token ID13
Feature activation+1.33e-01

Pos logit contributions
inky+0.008
 Claus+0.008
ppy+0.008
ley+0.008
working+0.007
Neg logit contributions
ement-0.007
 sliding-0.005
 swings-0.005
aw-0.005
bridge-0.005
Token Andy
Token ID12382
Feature activation+2.07e-01

Pos logit contributions
ement+0.005
bridge+0.004
 swings+0.004
aw+0.004
 amaz+0.004
Neg logit contributions
working-0.004
 Claus-0.003
inky-0.003
ppy-0.003
ny-0.003
Token and
Token ID290
Feature activation-2.72e+00

Pos logit contributions
ement+0.007
bridge+0.006
 amaz+0.005
aw+0.005
 swings+0.005
Neg logit contributions
working-0.006
 Claus-0.006
ny-0.006
ppy-0.006
inky-0.006
Token Amy
Token ID14235
Feature activation-5.95e-01

Pos logit contributions
inky+0.095
working+0.094
 Claus+0.094
ppy+0.091
ley+0.090
Neg logit contributions
ement-0.076
bridge-0.059
 swings-0.057
 amaz-0.056
aw-0.055
Token tried
Token ID3088
Feature activation-4.18e-01

Pos logit contributions
working+0.017
ppy+0.016
 Claus+0.016
ny+0.016
inky+0.016
Neg logit contributions
ement-0.021
bridge-0.017
 swings-0.016
aw-0.016
 amaz-0.016
Token to
Token ID284
Feature activation+4.25e-01

Pos logit contributions
inky+0.013
working+0.012
 Claus+0.012
ppy+0.012
ley+0.012
Neg logit contributions
ement-0.014
 sliding-0.011
 swings-0.011
 amaz-0.011
aw-0.010
Token fix
Token ID4259
Feature activation+8.49e-02

Pos logit contributions
ement+0.016
bridge+0.013
aw+0.013
 swings+0.012
 amaz+0.012
Neg logit contributions
working-0.011
 Claus-0.011
inky-0.011
ppy-0.011
ny-0.011
Token it
Token ID340
Feature activation-5.29e-01

Pos logit contributions
ement+0.002
bridge+0.002
 swings+0.002
aw+0.002
 amaz+0.002
Neg logit contributions
working-0.003
 Claus-0.003
inky-0.003
ppy-0.003
ny-0.003