TOP ACTIVATIONS
MAX = 7.176

drove off together . <|endoftext|> " It 's time to go
. The end . <|endoftext|> " One day , Max and
with her friends . <|endoftext|> " M ama , can I
ier than before . <|endoftext|> " Martin and his mom my
for a ride . <|endoftext|> " Ring !" went the phone
to welcome her . <|endoftext|> " Mom my , look at
was too late . <|endoftext|> " Look , Mom my !"
follow their dreams . <|endoftext|> " Mom my , let 's
fishing trip ever . <|endoftext|> " Mom my , can you
the wild rock . <|endoftext|> " Where the horse ? ,"
provide something delicious . <|endoftext|> " Once there was a small
in the world ! <|endoftext|> " Once upon a time there
all the bugs ! <|endoftext|> " E than !" shouted his
in the garden . <|endoftext|> " Mom my , what 's
The end . <|endoftext|> " M ama , can I
high and dry . <|endoftext|> " Good morning , everyone !"
anything was possible . <|endoftext|> " Mom my , can I
could have something . <|endoftext|> " M um , where are
the right direction . <|endoftext|> " M ummy , I need
their lively adventure ! <|endoftext|> " Look , Mom ! It

MIN ACTIVATIONS
MIN = -6.137

. He kept throwing a tant rum . His mom was
before . Suddenly , a loud , harsh noise startled Mike
hear my whistle . Wh ist ling is not fun with
hall , there was a loud scream . A boy named
She cried and threw a tant rum . Her mom tried
scary eyes , and a loud voice . Freddy felt afraid
Suddenly , there was a loud noise , and lightning scattered
listen . She threw a tant rum in the store .
Suddenly , a loud voice came out of the
it . Suddenly , a loud noise came out of the
Suddenly , a loud noise came from the sky
Suddenly , a loud thunder cl ap interrupted them
switch . Suddenly , a loud noise came from the switch
Suddenly , a huge loud noise appeared and the cats
Suddenly , there was a loud noise and a bright flash
bigger . Suddenly , a loud voice came from the sky
Joe . Joe was a big and strong bear who always
Suddenly , there was a loud his sing noise . The
heard it again - a loud roar . Green was scared
Suddenly , there was a loud bang and the tree fell

INTERVAL 3.847 - 7.176
CONTAINS 0.652%

girl smiled and said , " That 's mighty busy of
said to his mom , " I want to go to
where her mom was . " Mom , mom , look
was doing and said , " No Jane , you must
hungry . She said , " Mom my , I 'm

INTERVAL 0.519 - 3.847
CONTAINS 32.150%

a treat . After that , Max and his owners would
play in the park with their daddy . One day ,
. Tim my was so happy ! He played with the
the wind blow . The car saw a way
Mom , what is this ? Why is it spicy ?

INTERVAL -2.809 - 0.519
CONTAINS 66.012%

this again . <|endoftext|> L ily and Tom were friends who
. It wants to erase everything . It waits for a
prove he was brave , and he had - but at
bar ber cut his hair short and made it look nice
their stamps with each other . They learn that sharing is

INTERVAL -6.137 - -2.809
CONTAINS 1.186%

<|endoftext|> Once there was a clever puppy . He wanted to
smelled good . It was an orange ! "
. He was a very strong swim mer and loved the
happened . Suddenly , a big wave came and knocked Tommy
ara . Z ara was three years old , and she
Token drove
Token ID10357
Feature activation+1.06e+00

Pos logit contributions
 lifetime+0.034
ups+0.034
yard+0.032
lands+0.032
 next+0.031
Neg logit contributions
 tant-0.041
 laughs-0.040
 scares-0.036
rum-0.035
 bang-0.035
Token off
Token ID572
Feature activation+1.29e+00

Pos logit contributions
ups+0.021
 lifetime+0.021
lands+0.020
yard+0.019
 next+0.019
Neg logit contributions
 laughs-0.030
 tant-0.030
 scares-0.027
 bang-0.027
 cry-0.027
Token together
Token ID1978
Feature activation+2.56e+00

Pos logit contributions
 lifetime+0.026
ups+0.025
yard+0.024
 next+0.024
lands+0.024
Neg logit contributions
 tant-0.036
 laughs-0.036
 scares-0.033
 bang-0.032
rum-0.031
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
ups+0.060
 lifetime+0.059
lands+0.057
yard+0.057
ider+0.054
Neg logit contributions
 laughs-0.064
 tant-0.063
 scares-0.055
 cry-0.055
 bang-0.054
Token<|endoftext|>
Token ID50256
Feature activation+1.34e+00

Pos logit contributions
 lifetime+0.026
ups+0.025
yard+0.025
lands+0.024
Just+0.023
Neg logit contributions
 tant-0.033
 laughs-0.032
 scares-0.029
 cry-0.028
 bang-0.028
Token"
Token ID1
Feature activation+7.18e+00

Pos logit contributions
 lifetime+0.025
ups+0.025
lands+0.024
yard+0.024
 next+0.024
Neg logit contributions
 tant-0.039
 laughs-0.038
 cry-0.034
 scares-0.034
 bang-0.034
TokenIt
Token ID1026
Feature activation+5.84e-01

Pos logit contributions
ups+0.155
yard+0.150
 lifetime+0.146
lands+0.139
lor+0.136
Neg logit contributions
 laughs-0.185
 tant-0.180
 snowball-0.174
 bang-0.166
 laugh-0.165
Token's
Token ID338
Feature activation+1.83e+00

Pos logit contributions
ups+0.010
 lifetime+0.010
yard+0.009
lands+0.009
 next+0.009
Neg logit contributions
 tant-0.019
 laughs-0.018
 cry-0.016
 bang-0.016
 scares-0.016
Token time
Token ID640
Feature activation+1.63e+00

Pos logit contributions
 lifetime+0.048
ups+0.048
yard+0.046
lands+0.046
 next+0.045
Neg logit contributions
 tant-0.041
 laughs-0.040
 scares-0.035
 cry-0.034
 bang-0.034
Token to
Token ID284
Feature activation+1.08e+00

Pos logit contributions
 lifetime+0.036
ups+0.036
lands+0.034
yard+0.034
 next+0.033
Neg logit contributions
 laughs-0.042
 tant-0.042
 scares-0.038
 bang-0.036
 cry-0.036
Token go
Token ID467
Feature activation+8.87e-01

Pos logit contributions
 lifetime+0.023
ups+0.022
yard+0.022
 next+0.022
lands+0.022
Neg logit contributions
 tant-0.029
 laughs-0.028
 scares-0.025
 snowball-0.024
rum-0.024
Token.
Token ID13
Feature activation+9.04e-01

Pos logit contributions
 lifetime+0.030
ups+0.030
lands+0.029
yard+0.028
 next+0.028
Neg logit contributions
 tant-0.039
 laughs-0.038
 scares-0.034
 cry-0.034
 bang-0.033
Token The
Token ID383
Feature activation+1.44e-01

Pos logit contributions
ups+0.023
 lifetime+0.023
lands+0.023
nuts+0.022
yard+0.022
Neg logit contributions
 laughs-0.020
 tant-0.020
 cry-0.017
 scares-0.017
 bang-0.017
Token end
Token ID886
Feature activation-9.90e-01

Pos logit contributions
ups+0.003
 lifetime+0.003
lands+0.003
yard+0.003
lor+0.003
Neg logit contributions
 laughs-0.004
 tant-0.004
 cry-0.004
 scares-0.004
 bang-0.004
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
 tant+0.030
 laughs+0.029
 cry+0.026
 scares+0.026
 bang+0.025
Neg logit contributions
ups-0.019
 lifetime-0.018
 next-0.018
lands-0.016
Just-0.016
Token<|endoftext|>
Token ID50256
Feature activation+1.06e+00

Pos logit contributions
ups+0.044
lands+0.044
 lifetime+0.043
yard+0.042
ider+0.042
Neg logit contributions
 laughs-0.039
 tant-0.039
 cry-0.034
 scares-0.034
 bang-0.033
Token"
Token ID1
Feature activation+7.15e+00

Pos logit contributions
ups+0.019
 lifetime+0.019
 next+0.018
yard+0.018
lands+0.018
Neg logit contributions
 tant-0.032
 laughs-0.031
 scares-0.028
 cry-0.028
 bang-0.028
TokenOne
Token ID3198
Feature activation+9.37e-01

Pos logit contributions
ups+0.149
 lifetime+0.143
yard+0.142
lands+0.137
ider+0.131
Neg logit contributions
 laughs-0.193
 tant-0.189
 snowball-0.178
 bang-0.175
 laugh-0.170
Token day
Token ID1110
Feature activation+8.09e-01

Pos logit contributions
ups+0.018
 lifetime+0.018
yard+0.017
lands+0.017
 next+0.017
Neg logit contributions
 tant-0.027
 laughs-0.026
 scares-0.024
 bang-0.023
 cry-0.023
Token,
Token ID11
Feature activation+1.63e+00

Pos logit contributions
 lifetime+0.024
ups+0.023
lands+0.023
yard+0.022
 next+0.022
Neg logit contributions
 tant-0.015
 laughs-0.015
 scares-0.013
 cry-0.012
 bang-0.012
Token Max
Token ID5436
Feature activation+3.60e-02

Pos logit contributions
 lifetime+0.030
ups+0.029
yard+0.029
lands+0.029
 next+0.028
Neg logit contributions
 laughs-0.048
 tant-0.047
 scares-0.042
 cry-0.042
rum-0.041
Token and
Token ID290
Feature activation+1.11e+00

Pos logit contributions
 next+0.001
ups+0.001
 lifetime+0.001
lan+0.001
yard+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 scares-0.001
 channel-0.001
 bang-0.001
Token with
Token ID351
Feature activation-2.02e+00

Pos logit contributions
 laughs+0.031
 tant+0.031
 scares+0.028
 cry+0.027
 bang+0.027
Neg logit contributions
ups-0.024
 lifetime-0.024
 next-0.023
lands-0.022
yard-0.022
Token her
Token ID607
Feature activation+1.56e+00

Pos logit contributions
 tant+0.047
 laughs+0.045
 scares+0.041
 bang+0.039
 cry+0.039
Neg logit contributions
ups-0.051
 lifetime-0.049
lands-0.048
 next-0.048
yard-0.047
Token friends
Token ID2460
Feature activation+1.40e+00

Pos logit contributions
ups+0.030
 lifetime+0.030
lands+0.028
yard+0.028
nuts+0.026
Neg logit contributions
 laughs-0.045
 tant-0.045
 scares-0.040
 cry-0.040
 bang-0.040
Token.
Token ID13
Feature activation+7.56e-01

Pos logit contributions
ups+0.034
 lifetime+0.033
lands+0.033
yard+0.032
nuts+0.031
Neg logit contributions
 laughs-0.033
 tant-0.033
 cry-0.028
 scares-0.028
 laugh-0.028
Token<|endoftext|>
Token ID50256
Feature activation+1.46e+00

Pos logit contributions
ups+0.018
 lifetime+0.017
lands+0.017
yard+0.017
nuts+0.017
Neg logit contributions
 laughs-0.019
 tant-0.018
 scares-0.016
 cry-0.016
 laugh-0.016
Token"
Token ID1
Feature activation+7.09e+00

Pos logit contributions
 lifetime+0.028
ups+0.027
lands+0.026
yard+0.026
 next+0.026
Neg logit contributions
 tant-0.043
 laughs-0.042
 scares-0.037
 cry-0.037
 bang-0.037
TokenM
Token ID44
Feature activation+3.12e+00

Pos logit contributions
ups+0.144
yard+0.139
 lifetime+0.137
lands+0.129
lor+0.124
Neg logit contributions
 laughs-0.189
 tant-0.187
 snowball-0.178
 bang-0.173
 laugh-0.170
Tokenama
Token ID1689
Feature activation+7.25e-01

Pos logit contributions
lands+0.055
yard+0.052
assion+0.052
ups+0.051
 lifetime+0.050
Neg logit contributions
 tant-0.087
 laughs-0.086
 cry-0.081
 g-0.080
 bang-0.079
Token,
Token ID11
Feature activation+2.65e+00

Pos logit contributions
ups+0.019
 lifetime+0.018
yard+0.018
 next+0.018
lands+0.018
Neg logit contributions
 tant-0.017
 laughs-0.016
 scares-0.014
 cry-0.014
 bang-0.013
Token can
Token ID460
Feature activation+2.39e+00

Pos logit contributions
 next+0.053
We+0.053
asure+0.050
 lifetime+0.049
ups+0.049
Neg logit contributions
 tant-0.071
 laughs-0.070
rum-0.062
 scares-0.061
 snowball-0.060
Token I
Token ID314
Feature activation+5.40e-01

Pos logit contributions
 lifetime+0.047
ups+0.044
lands+0.044
yard+0.042
ider+0.041
Neg logit contributions
 laughs-0.068
 tant-0.066
 cry-0.064
 laugh-0.064
 scares-0.063
Tokenier
Token ID959
Feature activation-9.25e-01

Pos logit contributions
 tant+0.029
 laughs+0.028
 snowball+0.024
 scares+0.024
 bang+0.023
Neg logit contributions
 lifetime-0.025
ups-0.025
 next-0.024
lands-0.024
yard-0.024
Token than
Token ID621
Feature activation-4.46e-01

Pos logit contributions
 laughs+0.023
 tant+0.023
 snowball+0.021
 bang+0.020
 scares+0.020
Neg logit contributions
ups-0.021
 lifetime-0.021
lands-0.020
 next-0.020
yard-0.020
Token before
Token ID878
Feature activation-1.77e-01

Pos logit contributions
 tant+0.012
 laughs+0.012
 scares+0.010
 cry+0.010
 bang+0.010
Neg logit contributions
ups-0.010
 lifetime-0.010
lands-0.009
yard-0.009
nuts-0.009
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
 laughs+0.004
 tant+0.004
 scares+0.004
 cry+0.004
 bang+0.004
Neg logit contributions
ups-0.004
 lifetime-0.004
lands-0.004
yard-0.004
ider-0.004
Token<|endoftext|>
Token ID50256
Feature activation+1.62e+00

Pos logit contributions
ups+0.004
 lifetime+0.004
lands+0.004
yard+0.004
nuts+0.004
Neg logit contributions
 laughs-0.005
 tant-0.005
 scares-0.004
 cry-0.004
 bang-0.004
Token"
Token ID1
Feature activation+7.02e+00

Pos logit contributions
 lifetime+0.030
ups+0.030
lands+0.029
yard+0.029
 next+0.029
Neg logit contributions
 tant-0.048
 laughs-0.046
 cry-0.042
 scares-0.042
 bang-0.041
TokenMartin
Token ID24778
Feature activation-2.13e-01

Pos logit contributions
ups+0.142
 lifetime+0.137
yard+0.136
lands+0.129
lor+0.125
Neg logit contributions
 laughs-0.190
 tant-0.188
 snowball-0.180
 bang-0.174
 laugh-0.171
Token and
Token ID290
Feature activation+1.09e+00

Pos logit contributions
 tant+0.005
 laughs+0.005
 scares+0.004
 cry+0.004
 bang+0.004
Neg logit contributions
 lifetime-0.005
ups-0.005
lands-0.005
 next-0.005
yard-0.005
Token his
Token ID465
Feature activation+2.45e+00

Pos logit contributions
 lifetime+0.024
yard+0.024
ups+0.023
lands+0.023
 next+0.023
Neg logit contributions
 tant-0.029
 laughs-0.027
 scares-0.023
rum-0.023
 snowball-0.023
Token mom
Token ID1995
Feature activation+1.67e+00

Pos logit contributions
 lifetime+0.054
ups+0.053
yard+0.051
lands+0.051
 next+0.049
Neg logit contributions
 tant-0.064
 laughs-0.064
 scares-0.057
 cry-0.055
 bang-0.055
Tokenmy
Token ID1820
Feature activation+1.47e+00

Pos logit contributions
ups+0.035
 lifetime+0.034
yard+0.034
lands+0.033
 next+0.032
Neg logit contributions
 tant-0.047
 laughs-0.045
 scares-0.041
 bang-0.039
 snowball-0.039
Token for
Token ID329
Feature activation-8.20e-01

Pos logit contributions
 lifetime+0.021
ups+0.020
lor+0.019
yard+0.019
lands+0.019
Neg logit contributions
 laughs-0.019
 tant-0.018
 scares-0.016
 cry-0.016
 laugh-0.016
Token a
Token ID257
Feature activation+1.12e+00

Pos logit contributions
 tant+0.023
 laughs+0.022
 scares+0.020
 cry+0.019
 bang+0.019
Neg logit contributions
 lifetime-0.017
ups-0.017
lands-0.016
yard-0.016
 next-0.015
Token ride
Token ID6594
Feature activation+1.02e+00

Pos logit contributions
ups+0.028
yard+0.027
lands+0.026
 lifetime+0.026
lor+0.026
Neg logit contributions
 tant-0.027
 laughs-0.026
 laugh-0.024
 bang-0.024
 cry-0.024
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
ups+0.024
 lifetime+0.024
lands+0.023
yard+0.023
nuts+0.021
Neg logit contributions
 laughs-0.025
 tant-0.025
 scares-0.022
 cry-0.022
 bang-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.21e+00

Pos logit contributions
 lifetime+0.029
ups+0.029
yard+0.028
lands+0.028
Just+0.026
Neg logit contributions
 tant-0.038
 laughs-0.037
 scares-0.033
 bang-0.033
 cry-0.033
Token"
Token ID1
Feature activation+7.00e+00

Pos logit contributions
 lifetime+0.021
ups+0.021
 next+0.020
lands+0.020
yard+0.020
Neg logit contributions
 tant-0.037
 laughs-0.036
 cry-0.033
 scares-0.032
 bang-0.032
TokenRing
Token ID39687
Feature activation-1.73e+00

Pos logit contributions
ups+0.142
 lifetime+0.138
yard+0.137
lands+0.128
ider+0.125
Neg logit contributions
 laughs-0.185
 tant-0.185
 snowball-0.176
 bang-0.170
 laugh-0.165
Token!"
Token ID2474
Feature activation-4.33e-01

Pos logit contributions
 tant+0.045
 laughs+0.044
 scares+0.039
 gasp+0.039
 cry+0.038
Neg logit contributions
ups-0.036
Just-0.035
 next-0.034
 lifetime-0.033
lor-0.033
Token went
Token ID1816
Feature activation+1.73e+00

Pos logit contributions
 laughs+0.010
 tant+0.010
 scares+0.009
 cry+0.008
 bang+0.008
Neg logit contributions
ups-0.011
 lifetime-0.011
yard-0.010
lands-0.010
Just-0.010
Token the
Token ID262
Feature activation+2.61e+00

Pos logit contributions
ups+0.030
 lifetime+0.029
yard+0.028
lands+0.028
 next+0.026
Neg logit contributions
 tant-0.054
 laughs-0.053
 scares-0.048
 cry-0.047
 bang-0.047
Token phone
Token ID3072
Feature activation+2.29e+00

Pos logit contributions
ups+0.067
 lifetime+0.067
lands+0.066
lor+0.064
yard+0.064
Neg logit contributions
 laughs-0.058
 tant-0.058
 cry-0.051
 bang-0.051
 laugh-0.050
Token to
Token ID284
Feature activation-8.15e-01

Pos logit contributions
 lifetime+0.013
ups+0.013
yard+0.012
lands+0.012
 next+0.012
Neg logit contributions
 tant-0.019
 laughs-0.019
 scares-0.017
 bang-0.017
 snowball-0.017
Token welcome
Token ID7062
Feature activation+6.46e-01

Pos logit contributions
 tant+0.021
 laughs+0.020
 scares+0.018
 snowball+0.017
rum+0.017
Neg logit contributions
 lifetime-0.019
ups-0.018
yard-0.018
 next-0.018
lands-0.018
Token her
Token ID607
Feature activation+1.15e+00

Pos logit contributions
ups+0.017
 lifetime+0.016
lands+0.016
yard+0.016
 next+0.016
Neg logit contributions
 tant-0.015
 laughs-0.014
 scares-0.013
 cry-0.012
 bang-0.012
Token.
Token ID13
Feature activation+6.65e-01

Pos logit contributions
 lifetime+0.025
ups+0.025
 next+0.023
lands+0.023
yard+0.023
Neg logit contributions
 tant-0.031
 laughs-0.031
 scares-0.027
 bang-0.027
 cry-0.026
Token<|endoftext|>
Token ID50256
Feature activation+1.69e+00

Pos logit contributions
ups+0.015
 lifetime+0.015
lands+0.014
yard+0.014
nuts+0.014
Neg logit contributions
 laughs-0.017
 tant-0.017
 scares-0.015
 cry-0.015
 bang-0.015
Token"
Token ID1
Feature activation+6.91e+00

Pos logit contributions
 lifetime+0.032
ups+0.032
lands+0.030
yard+0.030
 next+0.030
Neg logit contributions
 tant-0.050
 laughs-0.048
 cry-0.043
 scares-0.043
 bang-0.043
TokenMom
Token ID29252
Feature activation+1.25e+00

Pos logit contributions
ups+0.139
 lifetime+0.134
yard+0.133
lands+0.126
lor+0.123
Neg logit contributions
 laughs-0.187
 tant-0.185
 snowball-0.174
 bang-0.170
 laugh-0.167
Tokenmy
Token ID1820
Feature activation+5.57e-01

Pos logit contributions
ups+0.025
 lifetime+0.025
lands+0.024
yard+0.024
 next+0.024
Neg logit contributions
 tant-0.035
 laughs-0.034
 scares-0.032
 cry-0.030
 bang-0.030
Token,
Token ID11
Feature activation+2.32e+00

Pos logit contributions
 lifetime+0.014
 next+0.014
ups+0.014
yard+0.014
lands+0.013
Neg logit contributions
 tant-0.013
 laughs-0.012
 scares-0.011
 snowball-0.010
 cry-0.010
Token look
Token ID804
Feature activation-1.35e-01

Pos logit contributions
 next+0.042
We+0.040
asure+0.038
 lifetime+0.038
ups+0.037
Neg logit contributions
 laughs-0.067
 tant-0.066
 scares-0.061
rum-0.061
 snowball-0.059
Token at
Token ID379
Feature activation-1.24e-01

Pos logit contributions
 laughs+0.004
 scares+0.004
 tant+0.004
rum+0.004
 cry+0.003
Neg logit contributions
 next-0.002
ups-0.002
 lifetime-0.002
lands-0.002
Just-0.002
Token was
Token ID373
Feature activation+2.99e-01

Pos logit contributions
ups+0.020
 lifetime+0.020
yard+0.019
lands+0.019
 next+0.019
Neg logit contributions
 tant-0.022
 laughs-0.022
 scares-0.019
 bang-0.019
 cry-0.019
Token too
Token ID1165
Feature activation+7.65e-01

Pos logit contributions
 lifetime+0.006
ups+0.006
yard+0.006
lands+0.006
 next+0.006
Neg logit contributions
 tant-0.008
 laughs-0.008
 scares-0.007
 cry-0.007
 bang-0.007
Token late
Token ID2739
Feature activation+1.75e+00

Pos logit contributions
ups+0.017
 lifetime+0.017
yard+0.016
lands+0.016
nuts+0.015
Neg logit contributions
 laughs-0.020
 tant-0.020
 scares-0.017
 cry-0.017
 bang-0.017
Token.
Token ID13
Feature activation+8.11e-01

Pos logit contributions
 lifetime+0.045
ups+0.045
yard+0.043
lands+0.043
ich+0.041
Neg logit contributions
 laughs-0.039
 tant-0.037
 cry-0.033
 scares-0.032
 laugh-0.032
Token<|endoftext|>
Token ID50256
Feature activation+1.52e+00

Pos logit contributions
ups+0.020
 lifetime+0.020
lands+0.019
yard+0.019
nuts+0.019
Neg logit contributions
 laughs-0.019
 tant-0.019
 cry-0.016
 scares-0.016
 g-0.016
Token"
Token ID1
Feature activation+6.90e+00

Pos logit contributions
 lifetime+0.028
ups+0.028
yard+0.026
lands+0.026
 next+0.026
Neg logit contributions
 tant-0.046
 laughs-0.044
 cry-0.040
 scares-0.040
 bang-0.039
TokenLook
Token ID8567
Feature activation+1.13e-01

Pos logit contributions
ups+0.139
yard+0.135
 lifetime+0.132
lands+0.126
lor+0.123
Neg logit contributions
 laughs-0.184
 tant-0.183
 snowball-0.172
 bang-0.167
 laugh-0.164
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
ups+0.003
 lifetime+0.003
lands+0.003
 next+0.003
yard+0.002
Neg logit contributions
 laughs-0.003
 tant-0.003
 scares-0.002
 cry-0.002
 bang-0.002
Token Mom
Token ID11254
Feature activation+6.94e-01

Pos logit contributions
 lifetime+0.044
ups+0.043
lands+0.042
yard+0.042
 next+0.041
Neg logit contributions
 tant-0.045
 laughs-0.045
 scares-0.039
 cry-0.038
 bang-0.038
Tokenmy
Token ID1820
Feature activation+4.47e-01

Pos logit contributions
ups+0.013
 lifetime+0.013
lands+0.013
yard+0.013
 next+0.013
Neg logit contributions
 tant-0.021
 laughs-0.020
 scares-0.018
 bang-0.017
 cry-0.017
Token!"
Token ID2474
Feature activation-2.00e-01

Pos logit contributions
 lifetime+0.011
ups+0.011
yard+0.011
lands+0.011
 next+0.011
Neg logit contributions
 tant-0.010
 laughs-0.010
 scares-0.009
 bang-0.008
 snowball-0.008
Token follow
Token ID1061
Feature activation-8.38e-01

Pos logit contributions
 laughs+0.014
 tant+0.013
 scares+0.012
 cry+0.012
 bang+0.011
Neg logit contributions
ups-0.015
 lifetime-0.015
lands-0.014
yard-0.014
ider-0.013
Token their
Token ID511
Feature activation+2.19e+00

Pos logit contributions
 tant+0.022
 laughs+0.022
 scares+0.019
 snowball+0.019
 cry+0.019
Neg logit contributions
ups-0.019
 lifetime-0.018
 next-0.018
lands-0.018
yard-0.017
Token dreams
Token ID10625
Feature activation+6.05e-01

Pos logit contributions
ups+0.045
 lifetime+0.044
lands+0.043
yard+0.042
ider+0.040
Neg logit contributions
 laughs-0.061
 tant-0.060
 scares-0.054
 cry-0.053
 bang-0.053
Token.
Token ID13
Feature activation+7.66e-01

Pos logit contributions
 lifetime+0.016
ups+0.015
ich+0.015
yard+0.015
lands+0.015
Neg logit contributions
 laughs-0.012
 tant-0.012
 laugh-0.011
 cry-0.011
 scares-0.011
Token<|endoftext|>
Token ID50256
Feature activation+9.50e-01

Pos logit contributions
 lifetime+0.016
ups+0.016
yard+0.016
lands+0.016
Just+0.015
Neg logit contributions
 tant-0.021
 laughs-0.020
 scares-0.018
 bang-0.018
 cry-0.018
Token"
Token ID1
Feature activation+6.89e+00

Pos logit contributions
 lifetime+0.016
ups+0.016
 next+0.016
lands+0.016
yard+0.015
Neg logit contributions
 tant-0.030
 laughs-0.028
 cry-0.026
 bang-0.026
 scares-0.026
TokenMom
Token ID29252
Feature activation+7.74e-01

Pos logit contributions
ups+0.146
yard+0.142
 lifetime+0.136
lands+0.129
ider+0.126
Neg logit contributions
 laughs-0.180
 tant-0.174
 snowball-0.169
 bang-0.162
 laugh-0.160
Tokenmy
Token ID1820
Feature activation-4.78e-02

Pos logit contributions
ups+0.015
 lifetime+0.015
lands+0.014
yard+0.014
 next+0.014
Neg logit contributions
 tant-0.023
 laughs-0.022
 scares-0.020
 cry-0.020
 bang-0.019
Token,
Token ID11
Feature activation+2.05e+00

Pos logit contributions
 tant+0.001
 laughs+0.001
 scares+0.001
 snowball+0.001
 cry+0.001
Neg logit contributions
 lifetime-0.001
ups-0.001
 next-0.001
yard-0.001
lands-0.001
Token let
Token ID1309
Feature activation+2.11e+00

Pos logit contributions
 next+0.033
We+0.030
asure+0.029
ocular+0.029
ups+0.028
Neg logit contributions
 laughs-0.065
 tant-0.064
 scares-0.060
rum-0.058
 snowball-0.056
Token's
Token ID338
Feature activation+1.29e+00

Pos logit contributions
 lifetime+0.034
ups+0.034
lands+0.032
yard+0.032
ider+0.029
Neg logit contributions
 laughs-0.068
 tant-0.067
 scares-0.061
 cry-0.060
 bang-0.060
Token fishing
Token ID12478
Feature activation+8.56e-01

Pos logit contributions
ups+0.001
 lifetime+0.001
lands+0.001
 next+0.001
yard+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 scares-0.000
 cry-0.000
 bang-0.000
Token trip
Token ID5296
Feature activation+1.83e+00

Pos logit contributions
ups+0.019
 lifetime+0.019
lands+0.018
yard+0.018
 next+0.017
Neg logit contributions
 laughs-0.022
 tant-0.022
 scares-0.020
 cry-0.019
 bang-0.019
Token ever
Token ID1683
Feature activation+2.12e+00

Pos logit contributions
 lifetime+0.044
ups+0.043
lands+0.042
yard+0.042
ider+0.040
Neg logit contributions
 laughs-0.044
 tant-0.043
 scares-0.038
 cry-0.037
 laugh-0.037
Token.
Token ID13
Feature activation+2.48e-01

Pos logit contributions
yard+0.057
ups+0.057
 lifetime+0.057
lands+0.056
ider+0.055
Neg logit contributions
 laughs-0.044
 tant-0.040
 scares-0.035
 laugh-0.035
 cry-0.035
Token<|endoftext|>
Token ID50256
Feature activation+1.42e+00

Pos logit contributions
 lifetime+0.005
ups+0.005
yard+0.005
lands+0.004
Just+0.004
Neg logit contributions
 tant-0.007
 laughs-0.007
 scares-0.006
 bang-0.006
 cry-0.006
Token"
Token ID1
Feature activation+6.81e+00

Pos logit contributions
 lifetime+0.025
ups+0.025
 next+0.024
yard+0.024
lands+0.024
Neg logit contributions
 tant-0.043
 laughs-0.042
 cry-0.038
 scares-0.038
 bang-0.038
TokenMom
Token ID29252
Feature activation+1.05e+00

Pos logit contributions
ups+0.133
 lifetime+0.129
yard+0.129
lands+0.122
lor+0.120
Neg logit contributions
 laughs-0.188
 tant-0.186
 snowball-0.178
 bang-0.171
 laugh-0.169
Tokenmy
Token ID1820
Feature activation+3.58e-01

Pos logit contributions
ups+0.020
 lifetime+0.020
lands+0.020
yard+0.019
 next+0.019
Neg logit contributions
 tant-0.030
 laughs-0.030
 scares-0.028
 cry-0.026
 bang-0.026
Token,
Token ID11
Feature activation+2.46e+00

Pos logit contributions
 lifetime+0.009
ups+0.009
 next+0.009
yard+0.009
lands+0.009
Neg logit contributions
 tant-0.008
 laughs-0.008
 scares-0.007
 snowball-0.007
 cry-0.007
Token can
Token ID460
Feature activation+2.13e+00

Pos logit contributions
 next+0.045
We+0.043
ups+0.042
 lifetime+0.042
nuts+0.041
Neg logit contributions
 laughs-0.070
 tant-0.069
 scares-0.063
rum-0.062
 snowball-0.060
Token you
Token ID345
Feature activation-9.49e-01

Pos logit contributions
 lifetime+0.040
ups+0.038
lands+0.036
yard+0.035
lor+0.034
Neg logit contributions
 laughs-0.064
 tant-0.062
 cry-0.059
 bang-0.059
 laugh-0.059
Token the
Token ID262
Feature activation+8.70e-01

Pos logit contributions
 tant+0.017
 laughs+0.017
 scares+0.015
 bang+0.015
 cry+0.015
Neg logit contributions
ups-0.011
 lifetime-0.011
lands-0.011
yard-0.011
 next-0.010
Token wild
Token ID4295
Feature activation-1.69e+00

Pos logit contributions
ups+0.022
 lifetime+0.021
lands+0.021
yard+0.021
nuts+0.020
Neg logit contributions
 laughs-0.020
 tant-0.020
 scares-0.018
 cry-0.017
 bang-0.017
Token rock
Token ID3881
Feature activation+4.85e-01

Pos logit contributions
 tant+0.037
 laughs+0.036
 scares+0.031
 cry+0.030
 bang+0.030
Neg logit contributions
 lifetime-0.044
lands-0.043
ups-0.043
 next-0.043
yard-0.042
Token.
Token ID13
Feature activation+9.61e-01

Pos logit contributions
ups+0.012
 lifetime+0.012
lands+0.011
yard+0.011
Just+0.011
Neg logit contributions
 laughs-0.011
 tant-0.011
 scares-0.010
 cry-0.010
 laugh-0.010
Token<|endoftext|>
Token ID50256
Feature activation+1.35e+00

Pos logit contributions
 lifetime+0.019
ups+0.019
yard+0.018
lands+0.018
Just+0.017
Neg logit contributions
 tant-0.027
 laughs-0.027
 scares-0.024
 bang-0.024
 cry-0.023
Token"
Token ID1
Feature activation+6.80e+00

Pos logit contributions
 lifetime+0.025
ups+0.025
lands+0.024
yard+0.024
 next+0.023
Neg logit contributions
 tant-0.040
 laughs-0.039
 cry-0.035
 scares-0.035
 bang-0.035
TokenWhere
Token ID8496
Feature activation+1.04e+00

Pos logit contributions
ups+0.141
 lifetime+0.136
yard+0.135
lands+0.127
lor+0.125
Neg logit contributions
 laughs-0.179
 tant-0.178
 snowball-0.167
 bang-0.161
 laugh-0.159
Token the
Token ID262
Feature activation+2.56e+00

Pos logit contributions
ups+0.026
 lifetime+0.026
yard+0.025
lands+0.025
 next+0.024
Neg logit contributions
 tant-0.024
 laughs-0.023
 scares-0.020
 bang-0.020
 cry-0.020
Token horse
Token ID8223
Feature activation-7.07e-01

Pos logit contributions
ups+0.055
 lifetime+0.053
lands+0.053
yard+0.052
ider+0.052
Neg logit contributions
 laughs-0.069
 tant-0.068
 scares-0.061
 snowball-0.060
 bang-0.060
Token?
Token ID30
Feature activation+1.53e+00

Pos logit contributions
 tant+0.018
 laughs+0.017
 snowball+0.015
 bang+0.015
 scares+0.015
Neg logit contributions
 lifetime-0.016
ups-0.016
yard-0.016
 next-0.015
lands-0.015
Token,"
Token ID553
Feature activation-9.96e-01

Pos logit contributions
ups+0.039
 lifetime+0.039
lands+0.037
yard+0.037
ider+0.036
Neg logit contributions
 laughs-0.035
 tant-0.034
 scares-0.030
 cry-0.029
 bang-0.029
Token provide
Token ID2148
Feature activation-1.59e-01

Pos logit contributions
 laughs+0.018
 tant+0.017
 scares+0.016
 cry+0.016
 laugh+0.015
Neg logit contributions
 lifetime-0.018
ups-0.018
lands-0.018
yard-0.017
ider-0.017
Token something
Token ID1223
Feature activation+1.03e+00

Pos logit contributions
 tant+0.004
 laughs+0.004
 scares+0.004
 bang+0.004
 cry+0.004
Neg logit contributions
ups-0.003
 lifetime-0.003
yard-0.003
lands-0.003
 next-0.003
Token delicious
Token ID12625
Feature activation+8.47e-02

Pos logit contributions
 lifetime+0.021
ups+0.021
lands+0.021
yard+0.021
ider+0.019
Neg logit contributions
 laughs-0.028
 tant-0.027
 scares-0.025
 cry-0.024
 laugh-0.024
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
ups+0.002
 lifetime+0.002
lands+0.002
yard+0.002
 next+0.002
Neg logit contributions
 tant-0.002
 laughs-0.002
 scares-0.002
 cry-0.002
 bang-0.002
Token<|endoftext|>
Token ID50256
Feature activation+1.31e+00

Pos logit contributions
ups+0.028
 lifetime+0.028
lands+0.027
yard+0.027
nuts+0.025
Neg logit contributions
 laughs-0.035
 tant-0.035
 scares-0.031
 cry-0.030
 bang-0.030
Token"
Token ID1
Feature activation+6.77e+00

Pos logit contributions
 lifetime+0.022
ups+0.022
 next+0.021
lands+0.021
yard+0.021
Neg logit contributions
 tant-0.041
 laughs-0.040
 cry-0.036
 scares-0.036
 bang-0.036
TokenOnce
Token ID7454
Feature activation+1.05e+00

Pos logit contributions
ups+0.135
yard+0.131
 lifetime+0.129
lands+0.121
lor+0.121
Neg logit contributions
 laughs-0.182
 tant-0.180
 snowball-0.174
 bang-0.165
 laugh-0.163
Token there
Token ID612
Feature activation-7.67e-01

Pos logit contributions
 lifetime+0.020
ups+0.020
lands+0.019
yard+0.019
ider+0.018
Neg logit contributions
 laughs-0.030
 tant-0.030
 scares-0.027
 cry-0.027
 bang-0.027
Token was
Token ID373
Feature activation+1.76e+00

Pos logit contributions
 tant+0.017
 laughs+0.016
 scares+0.015
 bang+0.014
 cry+0.014
Neg logit contributions
 lifetime-0.019
ups-0.019
yard-0.019
lands-0.019
 next-0.019
Token a
Token ID257
Feature activation-9.38e-01

Pos logit contributions
ups+0.040
 lifetime+0.039
lands+0.038
yard+0.037
ider+0.036
Neg logit contributions
 laughs-0.046
 tant-0.045
 scares-0.040
 bang-0.040
 cry-0.039
Token small
Token ID1402
Feature activation-2.94e+00

Pos logit contributions
 laughs+0.025
 tant+0.024
rum+0.022
 scares+0.022
 cry+0.021
Neg logit contributions
 lifetime-0.021
 next-0.020
ups-0.019
ich-0.019
lands-0.019
Token in
Token ID287
Feature activation-1.60e+00

Pos logit contributions
 laughs+0.000
 tant+0.000
 scares+0.000
 cry+0.000
 laugh+0.000
Neg logit contributions
ups-0.000
 lifetime-0.000
lands-0.000
yard-0.000
nuts-0.000
Token the
Token ID262
Feature activation+1.53e+00

Pos logit contributions
 laughs+0.038
 tant+0.037
 snowball+0.033
 scares+0.032
 bang+0.032
Neg logit contributions
 next-0.040
 lifetime-0.039
yard-0.036
side-0.035
lands-0.035
Token world
Token ID995
Feature activation+3.29e-01

Pos logit contributions
ups+0.032
lands+0.030
yard+0.029
 lifetime+0.029
nuts+0.029
Neg logit contributions
 laughs-0.044
 tant-0.043
 cry-0.039
 scares-0.039
 snowball-0.039
Token!
Token ID0
Feature activation+6.84e-01

Pos logit contributions
ups+0.008
 lifetime+0.008
lands+0.008
yard+0.008
Just+0.007
Neg logit contributions
 laughs-0.008
 tant-0.007
 scares-0.007
 laugh-0.007
 cry-0.006
Token<|endoftext|>
Token ID50256
Feature activation+1.38e+00

Pos logit contributions
 lifetime+0.014
ups+0.014
yard+0.013
lands+0.013
Just+0.013
Neg logit contributions
 laughs-0.019
 tant-0.019
 scares-0.017
 bang-0.017
 cry-0.016
Token"
Token ID1
Feature activation+6.76e+00

Pos logit contributions
 lifetime+0.026
ups+0.026
lands+0.025
yard+0.024
 next+0.024
Neg logit contributions
 tant-0.041
 laughs-0.040
 cry-0.036
 scares-0.036
 bang-0.036
TokenOnce
Token ID7454
Feature activation+9.34e-01

Pos logit contributions
ups+0.139
yard+0.135
 lifetime+0.133
lands+0.125
lor+0.122
Neg logit contributions
 laughs-0.180
 tant-0.178
 snowball-0.168
 bang-0.161
 laugh-0.160
Token upon
Token ID2402
Feature activation+1.71e+00

Pos logit contributions
 lifetime+0.018
ups+0.018
lands+0.017
yard+0.017
nuts+0.017
Neg logit contributions
 laughs-0.027
 tant-0.026
 cry-0.023
 scares-0.023
 laugh-0.023
Token a
Token ID257
Feature activation-6.88e-01

Pos logit contributions
ups+0.048
 lifetime+0.047
lands+0.046
yard+0.046
ider+0.045
Neg logit contributions
 laughs-0.037
 tant-0.033
 snowball-0.032
 laugh-0.032
 g-0.032
Token time
Token ID640
Feature activation-2.57e-01

Pos logit contributions
 laughs+0.013
 tant+0.013
rum+0.012
 scares+0.012
 cry+0.011
Neg logit contributions
 lifetime-0.019
Just-0.018
 next-0.018
ups-0.018
Days-0.018
Token there
Token ID612
Feature activation-1.32e-01

Pos logit contributions
 tant+0.005
 laughs+0.005
 scares+0.004
 cry+0.004
 bang+0.004
Neg logit contributions
 lifetime-0.008
ups-0.007
lands-0.007
yard-0.007
ider-0.007
Token all
Token ID477
Feature activation-1.01e+00

Pos logit contributions
 tant+0.020
 laughs+0.020
 scares+0.017
 snowball+0.017
 bang+0.017
Neg logit contributions
ups-0.023
 lifetime-0.023
 next-0.022
yard-0.022
lands-0.022
Token the
Token ID262
Feature activation+1.64e+00

Pos logit contributions
 tant+0.025
 laughs+0.023
 bang+0.023
 snowball+0.022
 scares+0.022
Neg logit contributions
ups-0.024
 next-0.024
yard-0.022
lands-0.022
 lifetime-0.022
Token bugs
Token ID11316
Feature activation-5.57e-01

Pos logit contributions
ups+0.037
 lifetime+0.037
yard+0.037
lands+0.036
lor+0.035
Neg logit contributions
 laughs-0.042
 tant-0.041
 scares-0.036
 cry-0.036
 laugh-0.036
Token!
Token ID0
Feature activation+5.99e-01

Pos logit contributions
 laughs+0.014
 tant+0.014
 scares+0.012
 cry+0.012
 bang+0.012
Neg logit contributions
ups-0.012
 lifetime-0.012
lands-0.012
yard-0.012
nuts-0.011
Token<|endoftext|>
Token ID50256
Feature activation+1.47e+00

Pos logit contributions
 lifetime+0.012
ups+0.012
yard+0.012
lands+0.012
Just+0.011
Neg logit contributions
 tant-0.016
 laughs-0.016
 scares-0.015
 bang-0.014
 cry-0.014
Token"
Token ID1
Feature activation+6.74e+00

Pos logit contributions
 lifetime+0.026
ups+0.025
 next+0.025
lands+0.024
yard+0.024
Neg logit contributions
 tant-0.045
 laughs-0.043
 cry-0.040
 scares-0.039
 bang-0.039
TokenE
Token ID36
Feature activation-5.97e-01

Pos logit contributions
ups+0.138
yard+0.133
 lifetime+0.132
lands+0.124
ider+0.122
Neg logit contributions
 laughs-0.181
 tant-0.177
 snowball-0.168
 bang-0.163
 laugh-0.161
Tokenthan
Token ID14813
Feature activation+3.94e-01

Pos logit contributions
 laughs+0.015
 tant+0.015
 scares+0.013
 cry+0.013
rum+0.013
Neg logit contributions
 lifetime-0.014
ups-0.013
yard-0.013
lands-0.013
ocular-0.012
Token!"
Token ID2474
Feature activation-1.72e-01

Pos logit contributions
ups+0.010
 lifetime+0.010
 next+0.010
yard+0.009
lands+0.009
Neg logit contributions
 tant-0.009
 laughs-0.009
 scares-0.008
 snowball-0.007
 bang-0.007
Token shouted
Token ID17293
Feature activation+4.55e-01

Pos logit contributions
 laughs+0.004
 tant+0.004
 scares+0.004
 bang+0.004
 cry+0.004
Neg logit contributions
ups-0.004
 lifetime-0.004
lands-0.004
yard-0.004
Just-0.004
Token his
Token ID465
Feature activation+1.17e+00

Pos logit contributions
 next+0.009
yard+0.009
ups+0.009
lan+0.009
 lifetime+0.009
Neg logit contributions
 laughs-0.012
 tant-0.012
 scares-0.011
 snowball-0.010
rum-0.010
Token in
Token ID287
Feature activation-6.78e-01

Pos logit contributions
ups+0.025
 lifetime+0.025
yard+0.024
lands+0.024
nuts+0.023
Neg logit contributions
 laughs-0.028
 tant-0.028
 scares-0.025
 cry-0.024
 bang-0.024
Token the
Token ID262
Feature activation+2.21e+00

Pos logit contributions
 tant+0.016
 laughs+0.015
 scares+0.013
rum+0.013
 bang+0.013
Neg logit contributions
 next-0.017
 lifetime-0.017
yard-0.016
ups-0.016
side-0.015
Token garden
Token ID11376
Feature activation+1.53e+00

Pos logit contributions
lor+0.054
lands+0.053
nuts+0.052
ups+0.052
ider+0.051
Neg logit contributions
 laughs-0.054
 tant-0.051
 cry-0.048
 g-0.047
 snowball-0.047
Token.
Token ID13
Feature activation+2.75e-01

Pos logit contributions
ups+0.036
 lifetime+0.035
lands+0.034
yard+0.034
Just+0.033
Neg logit contributions
 laughs-0.037
 tant-0.037
 scares-0.032
 cry-0.032
 laugh-0.032
Token<|endoftext|>
Token ID50256
Feature activation+1.33e+00

Pos logit contributions
 lifetime+0.006
ups+0.006
yard+0.006
lands+0.006
Just+0.006
Neg logit contributions
 tant-0.007
 laughs-0.007
 scares-0.006
 bang-0.006
 cry-0.006
Token"
Token ID1
Feature activation+6.73e+00

Pos logit contributions
 lifetime+0.026
ups+0.026
lands+0.025
yard+0.025
 next+0.024
Neg logit contributions
 tant-0.038
 laughs-0.037
 scares-0.033
 cry-0.033
 bang-0.033
TokenMom
Token ID29252
Feature activation+1.16e+00

Pos logit contributions
ups+0.133
 lifetime+0.130
yard+0.128
lands+0.122
lor+0.119
Neg logit contributions
 laughs-0.184
 tant-0.183
 snowball-0.172
 bang-0.167
 laugh-0.164
Tokenmy
Token ID1820
Feature activation+3.15e-01

Pos logit contributions
ups+0.021
 lifetime+0.020
lands+0.020
 next+0.020
yard+0.020
Neg logit contributions
 tant-0.035
 laughs-0.034
 scares-0.032
 cry-0.030
 bang-0.030
Token,
Token ID11
Feature activation+2.22e+00

Pos logit contributions
 next+0.008
 lifetime+0.008
ups+0.008
yard+0.007
lands+0.007
Neg logit contributions
 tant-0.008
 laughs-0.007
 scares-0.006
 snowball-0.006
 cry-0.006
Token what
Token ID644
Feature activation+2.02e+00

Pos logit contributions
 next+0.040
We+0.038
ups+0.037
asure+0.035
 lifetime+0.035
Neg logit contributions
 laughs-0.064
 tant-0.062
 scares-0.058
rum-0.057
 snowball-0.055
Token's
Token ID338
Feature activation+5.26e-01

Pos logit contributions
ups+0.043
 lifetime+0.040
 next+0.040
lands+0.038
yard+0.038
Neg logit contributions
 tant-0.055
 laughs-0.054
 scares-0.048
rum-0.048
 bang-0.047
Token
Token ID198
Feature activation+1.74e+00

Pos logit contributions
ups+0.018
 lifetime+0.018
lands+0.017
yard+0.017
ider+0.016
Neg logit contributions
 laughs-0.022
 tant-0.022
 scares-0.019
 cry-0.019
 bang-0.019
TokenThe
Token ID464
Feature activation+1.24e+00

Pos logit contributions
yard+0.041
lands+0.040
ider+0.039
 lifetime+0.039
ocular+0.038
Neg logit contributions
 tant-0.040
 laughs-0.040
 laugh-0.037
 g-0.036
rum-0.035
Token end
Token ID886
Feature activation-1.01e+00

Pos logit contributions
ups+0.026
lor+0.026
lands+0.026
yard+0.025
 lifetime+0.024
Neg logit contributions
 laughs-0.035
 tant-0.033
 cry-0.031
 laugh-0.031
 shock-0.030
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
 tant+0.033
 laughs+0.031
 bang+0.028
 cry+0.028
 scares+0.028
Neg logit contributions
ups-0.018
 next-0.017
 lifetime-0.017
Just-0.015
lands-0.015
Token<|endoftext|>
Token ID50256
Feature activation+1.46e+00

Pos logit contributions
ups+0.050
lands+0.048
 lifetime+0.048
ider+0.047
yard+0.046
Neg logit contributions
 tant-0.038
 laughs-0.038
 cry-0.033
 scares-0.032
 laugh-0.032
Token"
Token ID1
Feature activation+6.73e+00

Pos logit contributions
 lifetime+0.028
ups+0.027
lands+0.026
yard+0.026
 next+0.026
Neg logit contributions
 tant-0.043
 laughs-0.042
 cry-0.037
 scares-0.037
 bang-0.037
TokenM
Token ID44
Feature activation+2.31e+00

Pos logit contributions
ups+0.146
yard+0.141
 lifetime+0.137
lands+0.132
lor+0.127
Neg logit contributions
 laughs-0.173
 tant-0.170
 snowball-0.162
 bang-0.158
 laugh-0.155
Tokenama
Token ID1689
Feature activation+3.96e-01

Pos logit contributions
lands+0.041
ups+0.040
yard+0.038
 lifetime+0.038
assion+0.038
Neg logit contributions
 tant-0.065
 laughs-0.065
 cry-0.060
 g-0.059
 laugh-0.059
Token,
Token ID11
Feature activation+2.28e+00

Pos logit contributions
ups+0.010
 next+0.010
yard+0.009
 lifetime+0.009
lands+0.009
Neg logit contributions
 tant-0.010
 laughs-0.009
 scares-0.008
 cry-0.008
 bang-0.007
Token can
Token ID460
Feature activation+2.13e+00

Pos logit contributions
 next+0.047
We+0.046
ups+0.045
asure+0.044
 lifetime+0.042
Neg logit contributions
 tant-0.060
 laughs-0.059
rum-0.052
 snowball-0.052
 scares-0.052
Token I
Token ID314
Feature activation+5.47e-01

Pos logit contributions
 lifetime+0.042
ups+0.039
lands+0.038
yard+0.037
ider+0.035
Neg logit contributions
 laughs-0.061
 tant-0.059
 cry-0.058
 bang-0.058
 laugh-0.058
Token high
Token ID1029
Feature activation+4.09e-02

Pos logit contributions
 lifetime+0.021
ups+0.020
yard+0.020
lands+0.020
 next+0.019
Neg logit contributions
 laughs-0.024
 tant-0.024
 scares-0.021
 bang-0.021
 cry-0.021
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
ups+0.001
 lifetime+0.001
lands+0.001
 next+0.001
yard+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 cry-0.001
 bang-0.001
 scares-0.001
Token dry
Token ID5894
Feature activation-1.53e-01

Pos logit contributions
 lifetime+0.025
ups+0.024
yard+0.024
lands+0.023
 next+0.023
Neg logit contributions
 tant-0.026
 laughs-0.026
 scares-0.023
 bang-0.023
rum-0.023
Token.
Token ID13
Feature activation+6.62e-01

Pos logit contributions
 laughs+0.004
 tant+0.004
 scares+0.004
 bang+0.004
 cry+0.004
Neg logit contributions
ups-0.003
 lifetime-0.003
lands-0.003
yard-0.003
 next-0.003
Token<|endoftext|>
Token ID50256
Feature activation+1.77e+00

Pos logit contributions
ups+0.015
 lifetime+0.015
lands+0.015
yard+0.014
nuts+0.014
Neg logit contributions
 laughs-0.017
 tant-0.017
 scares-0.015
 cry-0.014
 bang-0.014
Token"
Token ID1
Feature activation+6.67e+00

Pos logit contributions
 lifetime+0.035
ups+0.035
lands+0.034
yard+0.034
 next+0.032
Neg logit contributions
 tant-0.050
 laughs-0.049
 scares-0.043
 cry-0.043
 bang-0.043
TokenGood
Token ID10248
Feature activation+7.71e-01

Pos logit contributions
ups+0.135
yard+0.130
 lifetime+0.129
lands+0.123
lor+0.118
Neg logit contributions
 tant-0.181
 laughs-0.180
 snowball-0.171
 bang-0.165
 laugh-0.160
Token morning
Token ID3329
Feature activation+1.21e+00

Pos logit contributions
ups+0.018
 lifetime+0.017
lands+0.017
yard+0.017
nuts+0.016
Neg logit contributions
 laughs-0.020
 tant-0.020
 scares-0.017
 cry-0.017
 bang-0.017
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
 lifetime+0.032
ups+0.032
yard+0.031
lands+0.031
 next+0.030
Neg logit contributions
 laughs-0.026
 tant-0.026
 scares-0.022
 cry-0.021
 bang-0.021
Token everyone
Token ID2506
Feature activation-4.69e-01

Pos logit contributions
 lifetime+0.023
yard+0.022
ups+0.022
 next+0.022
lands+0.022
Neg logit contributions
 laughs-0.026
 tant-0.025
 scares-0.022
 cry-0.022
rum-0.022
Token!"
Token ID2474
Feature activation-4.45e-01

Pos logit contributions
 tant+0.013
 laughs+0.012
 snowball+0.011
 bang+0.011
 horror+0.011
Neg logit contributions
ups-0.009
 lifetime-0.009
We-0.009
 next-0.009
lan-0.008
Token anything
Token ID1997
Feature activation-8.20e-01

Pos logit contributions
 lifetime+0.001
ups+0.001
lands+0.001
yard+0.001
ider+0.001
Neg logit contributions
 laughs-0.002
 tant-0.002
 scares-0.001
 cry-0.001
 laugh-0.001
Token was
Token ID373
Feature activation-1.19e+00

Pos logit contributions
 tant+0.022
 laughs+0.021
 snowball+0.021
rum+0.020
 bang+0.020
Neg logit contributions
ups-0.018
 lifetime-0.017
 next-0.016
yard-0.016
lands-0.015
Token possible
Token ID1744
Feature activation+9.28e-01

Pos logit contributions
 tant+0.036
 laughs+0.034
 snowball+0.031
 bang+0.031
 cry+0.031
Neg logit contributions
ups-0.022
 lifetime-0.022
yard-0.021
lands-0.021
 next-0.021
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
ups+0.022
 lifetime+0.022
lands+0.021
yard+0.021
nuts+0.020
Neg logit contributions
 laughs-0.022
 tant-0.022
 scares-0.019
 cry-0.019
 bang-0.019
Token<|endoftext|>
Token ID50256
Feature activation+1.49e+00

Pos logit contributions
 lifetime+0.007
ups+0.007
yard+0.007
lands+0.007
Just+0.007
Neg logit contributions
 laughs-0.010
 tant-0.010
 scares-0.009
 bang-0.008
 cry-0.008
Token"
Token ID1
Feature activation+6.67e+00

Pos logit contributions
 lifetime+0.027
ups+0.027
lands+0.026
 next+0.026
yard+0.026
Neg logit contributions
 tant-0.045
 laughs-0.043
 cry-0.039
 scares-0.039
 bang-0.039
TokenMom
Token ID29252
Feature activation+1.04e+00

Pos logit contributions
ups+0.133
yard+0.129
 lifetime+0.127
lor+0.121
lands+0.117
Neg logit contributions
 laughs-0.178
 tant-0.176
 snowball-0.167
 bang-0.162
 laugh-0.162
Tokenmy
Token ID1820
Feature activation+3.06e-01

Pos logit contributions
ups+0.021
 lifetime+0.021
lands+0.021
yard+0.020
 next+0.020
Neg logit contributions
 tant-0.029
 laughs-0.028
 scares-0.026
 cry-0.025
 bang-0.025
Token,
Token ID11
Feature activation+2.31e+00

Pos logit contributions
 lifetime+0.008
ups+0.008
 next+0.008
yard+0.008
lands+0.007
Neg logit contributions
 tant-0.007
 laughs-0.007
 scares-0.006
 snowball-0.006
 cry-0.006
Token can
Token ID460
Feature activation+1.94e+00

Pos logit contributions
 next+0.043
ups+0.041
We+0.041
 lifetime+0.041
yard+0.039
Neg logit contributions
 laughs-0.065
 tant-0.064
rum-0.058
 scares-0.058
 snowball-0.057
Token I
Token ID314
Feature activation+5.38e-01

Pos logit contributions
 lifetime+0.035
ups+0.034
lands+0.032
yard+0.032
lor+0.030
Neg logit contributions
 laughs-0.059
 tant-0.058
 cry-0.054
 bang-0.054
 scares-0.054
Token could
Token ID714
Feature activation+1.20e+00

Pos logit contributions
 lifetime+0.039
lands+0.039
ups+0.037
yard+0.037
nuts+0.036
Neg logit contributions
 laughs-0.035
 tant-0.033
 scares-0.030
 cry-0.029
 laugh-0.029
Token have
Token ID423
Feature activation+1.73e+00

Pos logit contributions
 lifetime+0.031
ups+0.031
lands+0.030
yard+0.030
ider+0.029
Neg logit contributions
 laughs-0.026
 tant-0.025
 cry-0.023
 bang-0.022
 laugh-0.022
Token something
Token ID1223
Feature activation+1.42e+00

Pos logit contributions
lands+0.041
 lifetime+0.041
ups+0.040
yard+0.040
ider+0.039
Neg logit contributions
 laughs-0.043
 tant-0.041
 scares-0.037
 cry-0.037
 laugh-0.036
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 lifetime+0.030
ups+0.029
lands+0.029
yard+0.029
lor+0.027
Neg logit contributions
 laughs-0.039
 tant-0.038
 scares-0.034
 cry-0.033
 laugh-0.033
Token<|endoftext|>
Token ID50256
Feature activation+1.24e+00

Pos logit contributions
ups+0.024
 lifetime+0.024
lands+0.023
yard+0.023
ider+0.022
Neg logit contributions
 laughs-0.028
 tant-0.027
 scares-0.024
 cry-0.024
 bang-0.024
Token"
Token ID1
Feature activation+6.65e+00

Pos logit contributions
ups+0.021
 lifetime+0.021
 next+0.020
lands+0.020
yard+0.019
Neg logit contributions
 tant-0.039
 laughs-0.037
 cry-0.034
 scares-0.034
 bang-0.034
TokenM
Token ID44
Feature activation+2.72e+00

Pos logit contributions
yard+0.130
ups+0.128
 lifetime+0.128
lor+0.119
lands+0.117
Neg logit contributions
 laughs-0.179
 tant-0.178
 snowball-0.164
 laugh-0.161
 bang-0.160
Tokenum
Token ID388
Feature activation-8.20e-02

Pos logit contributions
lands+0.047
yard+0.045
assion+0.045
 lifetime+0.044
ups+0.044
Neg logit contributions
 tant-0.078
 laughs-0.077
 cry-0.071
 g-0.070
 laugh-0.070
Token,
Token ID11
Feature activation+2.17e+00

Pos logit contributions
 tant+0.002
 laughs+0.002
 scares+0.002
 cry+0.002
 snowball+0.002
Neg logit contributions
ups-0.002
 next-0.002
yard-0.002
lands-0.002
 lifetime-0.002
Token where
Token ID810
Feature activation+2.47e+00

Pos logit contributions
ups+0.044
 next+0.043
 lifetime+0.042
yard+0.041
We+0.040
Neg logit contributions
 tant-0.058
 laughs-0.058
 snowball-0.052
rum-0.052
 scares-0.051
Token are
Token ID389
Feature activation+2.62e+00

Pos logit contributions
 lifetime+0.065
ups+0.064
lands+0.063
yard+0.062
ider+0.060
Neg logit contributions
 laughs-0.055
 tant-0.054
 cry-0.047
 scares-0.047
 laugh-0.046
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
 laughs+0.045
 tant+0.044
 snowball+0.038
 scares+0.038
 bang+0.038
Neg logit contributions
 lifetime-0.048
ups-0.046
 next-0.046
yard-0.046
lands-0.045
Token right
Token ID826
Feature activation-3.18e-01

Pos logit contributions
ups+0.027
lands+0.026
nuts+0.025
ider+0.025
uddled+0.025
Neg logit contributions
 laughs-0.037
 tant-0.037
 cry-0.034
 scares-0.033
 g-0.033
Token direction
Token ID4571
Feature activation-5.39e-01

Pos logit contributions
 laughs+0.008
 tant+0.008
 bang+0.008
 cry+0.007
 scares+0.007
Neg logit contributions
ups-0.007
 lifetime-0.007
 next-0.007
lands-0.007
yard-0.007
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
 tant+0.013
 laughs+0.013
 scares+0.011
 cry+0.011
 bang+0.011
Neg logit contributions
ups-0.013
 lifetime-0.013
lands-0.012
yard-0.012
 next-0.012
Token<|endoftext|>
Token ID50256
Feature activation+1.25e+00

Pos logit contributions
ups+0.033
 lifetime+0.033
lands+0.032
yard+0.032
ider+0.030
Neg logit contributions
 laughs-0.038
 tant-0.038
 scares-0.034
 cry-0.033
 bang-0.033
Token"
Token ID1
Feature activation+6.62e+00

Pos logit contributions
 lifetime+0.023
ups+0.023
lands+0.022
yard+0.022
 next+0.022
Neg logit contributions
 tant-0.038
 laughs-0.037
 cry-0.033
 scares-0.033
 bang-0.033
TokenM
Token ID44
Feature activation+2.56e+00

Pos logit contributions
ups+0.132
yard+0.126
 lifetime+0.124
lands+0.117
lor+0.114
Neg logit contributions
 laughs-0.178
 tant-0.175
 snowball-0.168
 bang-0.163
 laugh-0.159
Tokenummy
Token ID13513
Feature activation-4.12e-02

Pos logit contributions
lands+0.045
ups+0.043
yard+0.043
assion+0.042
 lifetime+0.042
Neg logit contributions
 laughs-0.074
 tant-0.074
 cry-0.067
 bang-0.066
 g-0.066
Token,
Token ID11
Feature activation+1.80e+00

Pos logit contributions
 tant+0.001
 laughs+0.001
 scares+0.001
 snowball+0.001
 cry+0.001
Neg logit contributions
 lifetime-0.001
yard-0.001
 next-0.001
ups-0.001
lands-0.001
Token I
Token ID314
Feature activation-5.81e-01

Pos logit contributions
 next+0.035
We+0.034
ups+0.033
 lifetime+0.033
yard+0.032
Neg logit contributions
 laughs-0.049
 tant-0.049
rum-0.043
 scares-0.043
 snowball-0.043
Token need
Token ID761
Feature activation+2.03e+00

Pos logit contributions
 tant+0.013
 laughs+0.013
 scares+0.011
rum+0.011
 snowball+0.011
Neg logit contributions
 lifetime-0.015
 next-0.014
We-0.014
Just-0.014
ups-0.014
Token their
Token ID511
Feature activation+1.71e+00

Pos logit contributions
 tant+0.037
 laughs+0.034
 scares+0.032
 snowball+0.031
 cry+0.031
Neg logit contributions
ups-0.037
 lifetime-0.037
 next-0.035
yard-0.035
lands-0.035
Token lively
Token ID29696
Feature activation-5.32e-01

Pos logit contributions
 lifetime+0.035
ups+0.034
lands+0.033
yard+0.033
nuts+0.031
Neg logit contributions
 laughs-0.048
 tant-0.047
 scares-0.042
 cry-0.042
 bang-0.041
Token adventure
Token ID8855
Feature activation+1.38e+00

Pos logit contributions
 laughs+0.015
 tant+0.015
 scares+0.013
 cry+0.013
 bang+0.013
Neg logit contributions
 lifetime-0.011
ups-0.010
lands-0.010
yard-0.010
 next-0.009
Token!
Token ID0
Feature activation+8.97e-01

Pos logit contributions
ups+0.035
 lifetime+0.035
lands+0.033
yard+0.033
ider+0.032
Neg logit contributions
 laughs-0.031
 tant-0.031
 scares-0.027
 cry-0.026
 bang-0.026
Token<|endoftext|>
Token ID50256
Feature activation+1.48e+00

Pos logit contributions
ups+0.020
 lifetime+0.020
lands+0.020
yard+0.019
ider+0.019
Neg logit contributions
 laughs-0.023
 tant-0.023
 scares-0.020
 cry-0.020
 bang-0.019
Token"
Token ID1
Feature activation+6.61e+00

Pos logit contributions
 lifetime+0.028
ups+0.027
lands+0.026
yard+0.026
 next+0.026
Neg logit contributions
 tant-0.044
 laughs-0.042
 cry-0.038
 scares-0.038
 bang-0.038
TokenLook
Token ID8567
Feature activation+1.55e-01

Pos logit contributions
ups+0.137
 lifetime+0.130
yard+0.129
lands+0.123
ider+0.120
Neg logit contributions
 laughs-0.178
 tant-0.176
 snowball-0.164
 bang-0.160
 laugh-0.158
Token,
Token ID11
Feature activation+1.74e+00

Pos logit contributions
ups+0.004
 lifetime+0.003
lands+0.003
 next+0.003
nuts+0.003
Neg logit contributions
 laughs-0.004
 tant-0.004
 scares-0.004
 cry-0.003
 snowball-0.003
Token Mom
Token ID11254
Feature activation+6.42e-01

Pos logit contributions
 lifetime+0.036
lands+0.035
ups+0.035
 next+0.035
yard+0.035
Neg logit contributions
 tant-0.046
 laughs-0.046
 scares-0.040
 cry-0.039
rum-0.039
Token!
Token ID0
Feature activation+2.53e+00

Pos logit contributions
ups+0.013
 lifetime+0.013
lands+0.013
yard+0.013
 next+0.012
Neg logit contributions
 tant-0.018
 laughs-0.017
 scares-0.016
 cry-0.015
 bang-0.015
Token It
Token ID632
Feature activation+9.01e-01

Pos logit contributions
 lifetime+0.065
ups+0.065
lands+0.063
yard+0.063
ider+0.060
Neg logit contributions
 laughs-0.056
 tant-0.056
 scares-0.048
 cry-0.047
 bang-0.046
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
ups+0.017
 lifetime+0.016
lands+0.016
yard+0.016
 next+0.015
Neg logit contributions
 laughs-0.021
 tant-0.021
 scares-0.019
 bang-0.018
 cry-0.018
Token He
Token ID679
Feature activation-1.14e+00

Pos logit contributions
 laughs+0.038
 tant+0.037
 laugh+0.033
 scares+0.033
 bang+0.033
Neg logit contributions
yard-0.030
ups-0.030
 next-0.029
Just-0.029
ider-0.028
Token kept
Token ID4030
Feature activation+2.32e-01

Pos logit contributions
 tant+0.031
 laughs+0.029
rum+0.028
 cry+0.026
 scares+0.026
Neg logit contributions
ups-0.024
Just-0.024
 next-0.023
yard-0.022
uddled-0.022
Token throwing
Token ID9644
Feature activation-1.26e+00

Pos logit contributions
 next+0.004
ups+0.004
ich+0.004
yard+0.004
 lifetime+0.004
Neg logit contributions
 tant-0.007
 laughs-0.006
 scares-0.006
rum-0.006
 snowball-0.006
Token a
Token ID257
Feature activation-5.48e-01

Pos logit contributions
 laughs+0.033
rum+0.032
 scares+0.031
 laugh+0.030
 cry+0.030
Neg logit contributions
 next-0.025
ups-0.023
nuts-0.022
ocular-0.021
 skies-0.021
Token tant
Token ID24246
Feature activation-6.14e+00

Pos logit contributions
 laughs+0.015
rum+0.013
 scares+0.013
 Ali+0.012
 horror+0.012
Neg logit contributions
 lifetime-0.011
 next-0.010
ups-0.010
nuts-0.009
bar-0.009
Tokenrum
Token ID6582
Feature activation-6.18e-01

Pos logit contributions
 laughs+0.072
 tant+0.063
 snowball+0.058
 scares+0.057
 shock+0.055
Neg logit contributions
ups-0.220
we-0.204
Just-0.203
lands-0.201
nuts-0.200
Token.
Token ID13
Feature activation-6.74e-01

Pos logit contributions
 laughs+0.015
 tant+0.015
 scares+0.013
 cry+0.013
 bang+0.012
Neg logit contributions
 lifetime-0.015
ups-0.015
lands-0.014
yard-0.014
nuts-0.014
Token His
Token ID2399
Feature activation+1.18e+00

Pos logit contributions
 laughs+0.016
 tant+0.016
 scares+0.014
 laugh+0.014
 cry+0.013
Neg logit contributions
ups-0.016
yard-0.016
 lifetime-0.016
Just-0.016
lands-0.016
Token mom
Token ID1995
Feature activation-8.43e-01

Pos logit contributions
ups+0.020
 next+0.020
 lifetime+0.020
yard+0.019
ich+0.018
Neg logit contributions
 laughs-0.036
 tant-0.035
 scares-0.032
rum-0.032
 bang-0.031
Token was
Token ID373
Feature activation-5.05e-01

Pos logit contributions
 tant+0.021
 laughs+0.020
 scares+0.018
rum+0.018
 cry+0.017
Neg logit contributions
ups-0.020
 next-0.019
 lifetime-0.018
Just-0.018
yard-0.018
Token before
Token ID878
Feature activation+1.05e-01

Pos logit contributions
 lifetime+0.042
lands+0.040
ups+0.040
yard+0.039
nuts+0.039
Neg logit contributions
 laughs-0.049
 tant-0.043
 scares-0.042
 laugh-0.040
 cry-0.040
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
ups+0.003
 lifetime+0.003
lands+0.003
yard+0.002
ider+0.002
Neg logit contributions
 laughs-0.002
 tant-0.002
 scares-0.002
 cry-0.002
 bang-0.002
Token Suddenly
Token ID24975
Feature activation-6.15e-01

Pos logit contributions
ups+0.005
 lifetime+0.005
lands+0.005
yard+0.005
nuts+0.005
Neg logit contributions
 laughs-0.004
 tant-0.004
 scares-0.004
 cry-0.004
 bang-0.004
Token,
Token ID11
Feature activation+8.60e-01

Pos logit contributions
 tant+0.011
 laughs+0.011
 scares+0.009
 cry+0.009
 bang+0.009
Neg logit contributions
ups-0.018
 lifetime-0.018
lands-0.018
yard-0.018
 next-0.017
Token a
Token ID257
Feature activation-1.62e+00

Pos logit contributions
ups+0.016
 lifetime+0.016
lands+0.016
yard+0.016
 next+0.015
Neg logit contributions
 tant-0.025
 laughs-0.025
 scares-0.022
 cry-0.022
 bang-0.022
Token loud
Token ID7812
Feature activation-6.10e+00

Pos logit contributions
 laughs+0.040
 tant+0.039
rum+0.034
 scares+0.034
 cry+0.033
Neg logit contributions
 lifetime-0.039
ups-0.037
yard-0.036
lands-0.036
 next-0.035
Token,
Token ID11
Feature activation-3.20e-01

Pos logit contributions
 tant+0.162
 laughs+0.146
rum+0.127
 scares+0.112
 channel+0.110
Neg logit contributions
yard-0.134
 skies-0.130
 next-0.129
bar-0.122
ich-0.121
Token harsh
Token ID11859
Feature activation-3.81e+00

Pos logit contributions
 tant+0.007
 laughs+0.007
rum+0.007
 laugh+0.006
 bang+0.006
Neg logit contributions
 next-0.008
 lifetime-0.008
ups-0.007
yard-0.007
 skies-0.007
Token noise
Token ID7838
Feature activation-4.58e-01

Pos logit contributions
 tant+0.106
 laughs+0.103
rum+0.089
 scares+0.083
 pret+0.082
Neg logit contributions
yard-0.078
 skies-0.076
 next-0.073
ich-0.072
lands-0.071
Token startled
Token ID36249
Feature activation-5.93e-01

Pos logit contributions
 tant+0.013
 laughs+0.012
rum+0.011
 cry+0.011
 laugh+0.010
Neg logit contributions
ups-0.010
 next-0.009
lands-0.009
 lifetime-0.009
yard-0.009
Token Mike
Token ID4995
Feature activation+4.57e-01

Pos logit contributions
 tant+0.014
 laughs+0.013
 scares+0.012
 cry+0.012
 bang+0.011
Neg logit contributions
ups-0.015
 lifetime-0.015
lands-0.015
 next-0.014
yard-0.014
Token hear
Token ID3285
Feature activation-3.72e-01

Pos logit contributions
 tant+0.039
 laughs+0.037
 scares+0.031
 snowball+0.031
rum+0.030
Neg logit contributions
ups-0.037
 lifetime-0.037
 next-0.037
Just-0.036
lands-0.036
Token my
Token ID616
Feature activation-4.37e-01

Pos logit contributions
 tant+0.010
 laughs+0.010
 snowball+0.009
 laugh+0.009
rum+0.009
Neg logit contributions
ups-0.008
 next-0.007
 lifetime-0.007
yard-0.007
 skies-0.007
Token whistle
Token ID16121
Feature activation-1.79e+00

Pos logit contributions
 tant+0.010
 laughs+0.010
rum+0.010
 scares+0.009
 snowball+0.008
Neg logit contributions
 next-0.010
 lifetime-0.010
ups-0.010
ich-0.009
yard-0.009
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
 laughs+0.051
 tant+0.051
 snowball+0.044
 horror+0.044
 scares+0.044
Neg logit contributions
 next-0.035
ups-0.034
lands-0.030
bar-0.030
yard-0.029
Token Wh
Token ID854
Feature activation-1.92e+00

Pos logit contributions
ups+0.007
yard+0.007
Just+0.007
ider+0.007
 lifetime+0.007
Neg logit contributions
 tant-0.011
 laughs-0.010
 laugh-0.009
 scares-0.009
 cry-0.009
Tokenist
Token ID396
Feature activation-6.07e+00

Pos logit contributions
 tant+0.049
 laughs+0.049
 scares+0.043
 cry+0.042
 bang+0.042
Neg logit contributions
ups-0.044
 lifetime-0.043
lands-0.042
yard-0.042
ider-0.040
Tokenling
Token ID1359
Feature activation-2.44e+00

Pos logit contributions
 snowball+0.129
 horror+0.128
 tant+0.125
 shock+0.122
 channel+0.117
Neg logit contributions
ups-0.130
bar-0.127
we-0.126
lands-0.119
 next-0.115
Token is
Token ID318
Feature activation-1.16e+00

Pos logit contributions
 tant+0.055
 laughs+0.050
 snowball+0.047
 horror+0.046
 shock+0.045
Neg logit contributions
ups-0.063
 next-0.059
yard-0.054
lands-0.054
Just-0.052
Token not
Token ID407
Feature activation-1.19e+00

Pos logit contributions
 tant+0.033
 laughs+0.030
rum+0.029
 snowball+0.026
 cry+0.026
Neg logit contributions
 next-0.023
ups-0.022
yard-0.021
ich-0.020
her-0.020
Token fun
Token ID1257
Feature activation-1.27e+00

Pos logit contributions
 tant+0.033
 laughs+0.031
 horror+0.028
 scares+0.028
 snowball+0.027
Neg logit contributions
ups-0.023
 lifetime-0.023
 next-0.023
ich-0.023
lands-0.022
Token with
Token ID351
Feature activation-2.38e+00

Pos logit contributions
 tant+0.038
 laughs+0.038
 snowball+0.035
 scares+0.034
 shock+0.033
Neg logit contributions
ups-0.022
 next-0.022
lands-0.020
ider-0.019
 lifetime-0.019
Token hall
Token ID6899
Feature activation+5.71e-01

Pos logit contributions
 lifetime+0.003
ups+0.002
lands+0.002
yard+0.002
nuts+0.002
Neg logit contributions
 laughs-0.003
 tant-0.003
 scares-0.002
 cry-0.002
 bang-0.002
Token,
Token ID11
Feature activation+2.28e-01

Pos logit contributions
 lifetime+0.021
ups+0.020
lor+0.020
nuts+0.020
lands+0.020
Neg logit contributions
 laughs-0.007
 tant-0.005
 scares-0.005
 laugh-0.004
 cry-0.004
Token there
Token ID612
Feature activation-1.60e+00

Pos logit contributions
ups+0.005
 lifetime+0.005
lor+0.005
lands+0.005
yard+0.005
Neg logit contributions
 laughs-0.006
 tant-0.005
 scares-0.005
 cry-0.005
 laugh-0.005
Token was
Token ID373
Feature activation+1.07e+00

Pos logit contributions
 tant+0.047
 laughs+0.043
 scares+0.039
 bang+0.038
 cry+0.038
Neg logit contributions
yard-0.032
 next-0.031
ups-0.031
lands-0.031
 lifetime-0.031
Token a
Token ID257
Feature activation-1.71e+00

Pos logit contributions
 lifetime+0.028
ups+0.027
lands+0.027
lor+0.026
ich+0.025
Neg logit contributions
 laughs-0.024
 tant-0.023
 scares-0.021
 snowball-0.020
 bang-0.020
Token loud
Token ID7812
Feature activation-5.90e+00

Pos logit contributions
 laughs+0.046
 tant+0.045
rum+0.042
 scares+0.039
 cry+0.037
Neg logit contributions
 lifetime-0.038
 next-0.036
ich-0.035
ups-0.034
ider-0.033
Token scream
Token ID8196
Feature activation-6.74e-01

Pos logit contributions
 tant+0.158
 laughs+0.149
rum+0.138
 scares+0.123
 horror+0.119
Neg logit contributions
 next-0.123
yard-0.118
 skies-0.114
 lifetime-0.110
ich-0.109
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
 laughs+0.019
 tant+0.019
 cry+0.017
 scares+0.016
 laugh+0.016
Neg logit contributions
ups-0.013
yard-0.013
 next-0.013
 lifetime-0.013
lands-0.013
Token A
Token ID317
Feature activation-1.25e+00

Pos logit contributions
 tant+0.032
 laughs+0.030
 scares+0.026
 cry+0.026
 snowball+0.026
Neg logit contributions
yard-0.022
 lifetime-0.021
ups-0.021
lands-0.020
Just-0.020
Token boy
Token ID2933
Feature activation-1.97e+00

Pos logit contributions
 laughs+0.035
 tant+0.034
rum+0.033
rs+0.029
ez+0.029
Neg logit contributions
 lifetime-0.026
 next-0.024
ups-0.024
ich-0.024
ider-0.022
Token named
Token ID3706
Feature activation+8.10e-01

Pos logit contributions
 tant+0.068
 laughs+0.059
 shock+0.053
 horror+0.053
rum+0.053
Neg logit contributions
 next-0.034
We-0.030
ups-0.029
yard-0.029
we-0.028
Token She
Token ID1375
Feature activation-1.55e-01

Pos logit contributions
 laughs+0.005
 tant+0.005
 cry+0.004
 scares+0.004
 g+0.004
Neg logit contributions
 lifetime-0.008
nuts-0.008
lands-0.008
ich-0.008
lor-0.008
Token cried
Token ID16896
Feature activation-1.19e+00

Pos logit contributions
 laughs+0.004
 tant+0.004
 scares+0.003
 cry+0.003
 bang+0.003
Neg logit contributions
ups-0.004
 lifetime-0.004
lands-0.003
yard-0.003
ider-0.003
Token and
Token ID290
Feature activation+1.99e-01

Pos logit contributions
 laughs+0.025
 tant+0.024
 scares+0.021
 cry+0.020
 bang+0.020
Neg logit contributions
ups-0.032
 lifetime-0.032
lands-0.031
yard-0.031
 next-0.030
Token threw
Token ID9617
Feature activation-9.87e-01

Pos logit contributions
ups+0.005
 lifetime+0.005
yard+0.005
lands+0.005
 next+0.005
Neg logit contributions
 laughs-0.005
 tant-0.005
 scares-0.004
 snowball-0.004
 bang-0.004
Token a
Token ID257
Feature activation-4.97e-01

Pos logit contributions
rum+0.027
 laughs+0.026
 scares+0.026
 gasp+0.023
 laugh+0.023
Neg logit contributions
 next-0.018
ups-0.017
 plenty-0.015
nuts-0.015
ocular-0.015
Token tant
Token ID24246
Feature activation-5.88e+00

Pos logit contributions
 laughs+0.009
rum+0.009
 scares+0.008
rs+0.007
 horror+0.007
Neg logit contributions
 lifetime-0.014
ups-0.013
 next-0.013
bar-0.013
 owner-0.012
Tokenrum
Token ID6582
Feature activation-6.50e-01

Pos logit contributions
 laughs+0.075
 tant+0.063
 snowball+0.062
 scares+0.060
 shock+0.058
Neg logit contributions
ups-0.202
we-0.194
Just-0.187
lands-0.186
ider-0.183
Token.
Token ID13
Feature activation-6.99e-03

Pos logit contributions
 laughs+0.016
 tant+0.015
 scares+0.013
 cry+0.013
 bang+0.013
Neg logit contributions
 lifetime-0.016
ups-0.016
lands-0.015
yard-0.015
nuts-0.014
Token Her
Token ID2332
Feature activation+1.21e+00

Pos logit contributions
 tant+0.000
 laughs+0.000
 cry+0.000
 bang+0.000
 scares+0.000
Neg logit contributions
 lifetime-0.000
ups-0.000
lands-0.000
nuts-0.000
ider-0.000
Token mom
Token ID1995
Feature activation-2.25e-01

Pos logit contributions
ups+0.023
 lifetime+0.022
 next+0.021
yard+0.021
lands+0.020
Neg logit contributions
 laughs-0.035
 tant-0.034
 scares-0.032
rum-0.031
 bang-0.031
Token tried
Token ID3088
Feature activation+3.21e-01

Pos logit contributions
 tant+0.006
 laughs+0.006
 scares+0.005
rum+0.005
 snowball+0.005
Neg logit contributions
ups-0.005
 lifetime-0.005
 next-0.005
yard-0.005
Just-0.005
Token scary
Token ID14343
Feature activation-1.55e+00

Pos logit contributions
 lifetime+0.028
ups+0.028
lands+0.027
yard+0.027
ider+0.026
Neg logit contributions
 laughs-0.032
 tant-0.031
 scares-0.028
 cry-0.028
 bang-0.028
Token eyes
Token ID2951
Feature activation-1.05e+00

Pos logit contributions
 tant+0.038
 laughs+0.034
 snowball+0.031
rum+0.031
 scares+0.031
Neg logit contributions
ups-0.035
 skies-0.034
yard-0.034
lands-0.034
 lifetime-0.033
Token,
Token ID11
Feature activation-3.96e-01

Pos logit contributions
 tant+0.024
 laughs+0.023
 scares+0.020
 cry+0.020
 snowball+0.020
Neg logit contributions
ups-0.026
lands-0.026
 next-0.025
yard-0.025
ocular-0.025
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 tant+0.011
 laughs+0.010
rum+0.009
 scares+0.009
 bang+0.009
Neg logit contributions
 next-0.008
yard-0.008
ups-0.008
lands-0.008
 lifetime-0.007
Token a
Token ID257
Feature activation-1.86e+00

Pos logit contributions
 tant+0.029
 laughs+0.027
rum+0.025
 channel+0.024
 bang+0.024
Neg logit contributions
yard-0.022
 next-0.022
 lifetime-0.021
ups-0.021
nuts-0.020
Token loud
Token ID7812
Feature activation-5.86e+00

Pos logit contributions
 laughs+0.047
 tant+0.043
rum+0.042
 scares+0.039
rs+0.037
Neg logit contributions
 lifetime-0.045
ich-0.040
 next-0.038
Just-0.037
bar-0.037
Token voice
Token ID3809
Feature activation-1.84e+00

Pos logit contributions
 tant+0.140
 laughs+0.129
 scares+0.107
rum+0.103
 channel+0.100
Neg logit contributions
 next-0.123
bar-0.122
yard-0.119
 skies-0.116
Just-0.112
Token.
Token ID13
Feature activation-2.12e+00

Pos logit contributions
 tant+0.060
 laughs+0.053
 snowball+0.051
rum+0.048
 cry+0.046
Neg logit contributions
 next-0.030
ups-0.030
yard-0.028
we-0.028
 lifetime-0.027
Token Freddy
Token ID45437
Feature activation-1.80e+00

Pos logit contributions
 laughs+0.047
 tant+0.046
 scares+0.040
 cry+0.039
 bang+0.039
Neg logit contributions
ups-0.055
 lifetime-0.055
lands-0.053
yard-0.053
ider-0.051
Token felt
Token ID2936
Feature activation-2.00e+00

Pos logit contributions
 tant+0.050
 laughs+0.047
 scares+0.041
rum+0.041
 snowball+0.041
Neg logit contributions
ups-0.038
Just-0.037
 next-0.036
 lifetime-0.036
lands-0.035
Token afraid
Token ID7787
Feature activation-3.62e-01

Pos logit contributions
 tant+0.051
 laughs+0.046
 channel+0.043
rum+0.042
 snowball+0.042
Neg logit contributions
 next-0.044
yard-0.044
ups-0.042
Just-0.041
Rest-0.041
Token Suddenly
Token ID24975
Feature activation-1.25e+00

Pos logit contributions
 laughs+0.026
 tant+0.026
 scares+0.023
 bang+0.022
 cry+0.022
Neg logit contributions
 lifetime-0.033
ups-0.033
lands-0.031
yard-0.030
lor-0.030
Token,
Token ID11
Feature activation+1.99e-02

Pos logit contributions
 tant+0.025
 laughs+0.024
 scares+0.020
 cry+0.020
rum+0.020
Neg logit contributions
ups-0.034
 lifetime-0.034
lands-0.034
yard-0.033
 next-0.033
Token there
Token ID612
Feature activation-5.94e-01

Pos logit contributions
ups+0.000
 lifetime+0.000
lands+0.000
yard+0.000
nuts+0.000
Neg logit contributions
 laughs-0.000
 tant-0.000
 scares-0.000
 cry-0.000
 bang-0.000
Token was
Token ID373
Feature activation+6.55e-01

Pos logit contributions
 tant+0.017
 laughs+0.016
rum+0.015
 scares+0.014
 channel+0.014
Neg logit contributions
ups-0.012
yard-0.011
 next-0.011
 skies-0.011
 lifetime-0.010
Token a
Token ID257
Feature activation-2.86e+00

Pos logit contributions
 lifetime+0.015
ups+0.015
lands+0.014
yard+0.014
ider+0.014
Neg logit contributions
 laughs-0.017
 tant-0.016
 scares-0.015
 bang-0.015
 cry-0.014
Token loud
Token ID7812
Feature activation-5.86e+00

Pos logit contributions
 laughs+0.073
 tant+0.070
rum+0.066
 scares+0.059
ez+0.057
Neg logit contributions
 lifetime-0.069
 next-0.062
ich-0.062
yard-0.061
ups-0.060
Token noise
Token ID7838
Feature activation-1.06e+00

Pos logit contributions
 tant+0.157
 laughs+0.147
rum+0.126
 scares+0.115
 channel+0.108
Neg logit contributions
 next-0.121
yard-0.119
 skies-0.117
ich-0.110
bar-0.109
Token,
Token ID11
Feature activation-4.14e-01

Pos logit contributions
 tant+0.033
 laughs+0.032
rum+0.028
 cry+0.027
 laugh+0.026
Neg logit contributions
 next-0.019
ups-0.018
lands-0.017
yard-0.017
Rest-0.017
Token and
Token ID290
Feature activation-5.28e-01

Pos logit contributions
 tant+0.010
 laughs+0.009
rum+0.008
 laugh+0.008
 scares+0.008
Neg logit contributions
 next-0.010
yard-0.010
Just-0.010
 lifetime-0.010
lands-0.010
Token lightning
Token ID14357
Feature activation-1.08e+00

Pos logit contributions
 tant+0.012
 laughs+0.012
rum+0.010
 scares+0.010
 cry+0.010
Neg logit contributions
ups-0.013
 lifetime-0.013
yard-0.013
 next-0.013
lands-0.012
Token scattered
Token ID16830
Feature activation-3.23e-01

Pos logit contributions
 tant+0.027
 laughs+0.026
rum+0.023
 cry+0.022
 laugh+0.022
Neg logit contributions
ups-0.025
yard-0.023
lands-0.023
 lifetime-0.023
 next-0.023
Token listen
Token ID6004
Feature activation+1.29e+00

Pos logit contributions
 tant+0.042
 laughs+0.041
 snowball+0.036
 scares+0.035
rum+0.033
Neg logit contributions
ups-0.051
 next-0.049
 lifetime-0.048
lands-0.047
Just-0.047
Token.
Token ID13
Feature activation-8.56e-01

Pos logit contributions
 lifetime+0.025
ups+0.024
lands+0.023
yard+0.023
nuts+0.022
Neg logit contributions
 laughs-0.037
 tant-0.037
 scares-0.033
 cry-0.033
 bang-0.032
Token She
Token ID1375
Feature activation-9.29e-01

Pos logit contributions
 laughs+0.022
 tant+0.022
 scares+0.019
 cry+0.019
 bang+0.019
Neg logit contributions
 lifetime-0.020
ups-0.019
lands-0.019
yard-0.018
nuts-0.018
Token threw
Token ID9617
Feature activation-9.02e-01

Pos logit contributions
 tant+0.025
 laughs+0.024
rum+0.022
 scares+0.021
 cry+0.021
Neg logit contributions
ups-0.020
 lifetime-0.019
Just-0.019
 next-0.018
yard-0.018
Token a
Token ID257
Feature activation-4.07e-01

Pos logit contributions
rum+0.025
 scares+0.022
 laughs+0.022
 gasp+0.021
 channel+0.021
Neg logit contributions
 next-0.018
ups-0.016
 plenty-0.015
ocular-0.015
nuts-0.015
Token tant
Token ID24246
Feature activation-5.84e+00

Pos logit contributions
 laughs+0.007
rum+0.007
 scares+0.005
 Ali+0.005
 Ann+0.005
Neg logit contributions
 lifetime-0.011
 next-0.011
bar-0.011
 seas-0.011
ups-0.010
Tokenrum
Token ID6582
Feature activation-8.83e-01

Pos logit contributions
 laughs+0.074
 snowball+0.065
 tant+0.062
 shock+0.061
 scares+0.061
Neg logit contributions
ups-0.202
we-0.193
Just-0.187
ider-0.182
lands-0.181
Token in
Token ID287
Feature activation-2.04e+00

Pos logit contributions
 laughs+0.018
 tant+0.017
 cry+0.014
 scares+0.014
 bang+0.014
Neg logit contributions
 lifetime-0.026
ups-0.025
lands-0.024
yard-0.024
lor-0.023
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 laughs+0.050
 snowball+0.047
rum+0.047
 scares+0.046
 pret+0.046
Neg logit contributions
 next-0.045
ups-0.040
 plenty-0.036
 skies-0.036
There-0.035
Token store
Token ID3650
Feature activation+1.22e+00

Pos logit contributions
ups+0.026
 lifetime+0.026
 next+0.024
yard+0.024
lands+0.024
Neg logit contributions
 laughs-0.033
 tant-0.033
rum-0.030
 scares-0.029
 cry-0.029
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
 lifetime+0.037
ups+0.036
lands+0.035
lor+0.034
yard+0.034
Neg logit contributions
 laughs-0.022
 tant-0.022
 cry-0.018
 scares-0.018
 laugh-0.018
Token
Token ID198
Feature activation-8.15e-01

Pos logit contributions
 tant+0.003
 laughs+0.003
 scares+0.002
 cry+0.002
 snowball+0.002
Neg logit contributions
ups-0.002
 lifetime-0.002
yard-0.002
lands-0.002
Just-0.002
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
 laughs+0.022
 tant+0.022
 scares+0.019
 cry+0.019
 bang+0.019
Neg logit contributions
ups-0.017
 lifetime-0.017
lands-0.016
yard-0.016
Just-0.015
TokenSuddenly
Token ID38582
Feature activation-6.35e-01

Pos logit contributions
 laughs+0.007
 tant+0.006
 scares+0.006
 cry+0.006
 laugh+0.006
Neg logit contributions
 lifetime-0.005
ups-0.004
yard-0.004
lands-0.004
ider-0.004
Token,
Token ID11
Feature activation+8.61e-01

Pos logit contributions
 tant+0.015
 laughs+0.013
 scares+0.012
 bang+0.012
 snowball+0.011
Neg logit contributions
ups-0.016
 next-0.016
lands-0.016
 lifetime-0.016
yard-0.016
Token a
Token ID257
Feature activation-1.85e+00

Pos logit contributions
 next+0.016
ups+0.015
 lifetime+0.015
yard+0.015
lands+0.015
Neg logit contributions
 tant-0.026
 laughs-0.024
rum-0.023
 scares-0.022
 channel-0.022
Token loud
Token ID7812
Feature activation-5.83e+00

Pos logit contributions
 laughs+0.051
 tant+0.049
rum+0.045
 scares+0.042
 pret+0.040
Neg logit contributions
 lifetime-0.040
 next-0.037
ups-0.036
yard-0.035
ich-0.035
Token voice
Token ID3809
Feature activation-1.21e+00

Pos logit contributions
 tant+0.161
 laughs+0.148
rum+0.126
 scares+0.118
 channel+0.113
Neg logit contributions
 next-0.117
yard-0.109
 skies-0.107
bar-0.104
ich-0.101
Token came
Token ID1625
Feature activation-8.64e-02

Pos logit contributions
 tant+0.034
 laughs+0.031
 snowball+0.027
rum+0.027
 cry+0.027
Neg logit contributions
ups-0.026
 next-0.025
yard-0.024
lands-0.024
 lifetime-0.024
Token out
Token ID503
Feature activation-1.45e+00

Pos logit contributions
 tant+0.002
 laughs+0.002
 scares+0.002
 bang+0.002
 cry+0.002
Neg logit contributions
ups-0.002
lands-0.002
 next-0.002
 lifetime-0.002
yard-0.002
Token of
Token ID286
Feature activation-1.46e+00

Pos logit contributions
 tant+0.044
 laughs+0.042
 pret+0.037
 scares+0.036
 cry+0.034
Neg logit contributions
 next-0.029
ups-0.027
Just-0.025
lands-0.025
ocular-0.025
Token the
Token ID262
Feature activation+5.56e-01

Pos logit contributions
 tant+0.041
 laughs+0.036
 scares+0.033
rum+0.032
 pret+0.032
Neg logit contributions
 next-0.034
 skies-0.031
yard-0.029
lands-0.029
There-0.028
Token it
Token ID340
Feature activation+1.12e+00

Pos logit contributions
 laughs+0.080
 tant+0.079
 scares+0.072
 cry+0.070
rum+0.069
Neg logit contributions
lands-0.076
ups-0.075
 next-0.072
yard-0.071
nuts-0.070
Token.
Token ID13
Feature activation-1.83e+00

Pos logit contributions
ups+0.024
 lifetime+0.023
yard+0.023
lands+0.023
 next+0.022
Neg logit contributions
 tant-0.030
 laughs-0.030
 scares-0.026
 cry-0.026
 snowball-0.026
Token Suddenly
Token ID24975
Feature activation-1.43e+00

Pos logit contributions
 laughs+0.036
 tant+0.034
 scares+0.030
 cry+0.030
 bang+0.029
Neg logit contributions
 lifetime-0.053
ups-0.052
lands-0.051
ich-0.049
nuts-0.049
Token,
Token ID11
Feature activation-6.74e-01

Pos logit contributions
 laughs+0.024
 tant+0.024
 scares+0.020
 cry+0.019
 bang+0.019
Neg logit contributions
ups-0.045
 lifetime-0.045
lands-0.043
yard-0.043
ider-0.042
Token a
Token ID257
Feature activation-1.58e+00

Pos logit contributions
 laughs+0.017
 tant+0.017
 scares+0.015
 cry+0.015
 bang+0.015
Neg logit contributions
ups-0.016
 lifetime-0.016
lands-0.015
yard-0.015
lor-0.014
Token loud
Token ID7812
Feature activation-5.82e+00

Pos logit contributions
 laughs+0.042
 tant+0.040
rum+0.039
 scares+0.036
 cry+0.034
Neg logit contributions
 lifetime-0.036
ups-0.032
 next-0.031
ich-0.031
yard-0.030
Token noise
Token ID7838
Feature activation-9.58e-01

Pos logit contributions
 tant+0.153
 laughs+0.138
rum+0.124
 scares+0.112
 snowball+0.107
Neg logit contributions
 next-0.118
yard-0.110
 skies-0.110
bar-0.110
ich-0.103
Token came
Token ID1625
Feature activation+4.39e-02

Pos logit contributions
 tant+0.027
 laughs+0.025
rum+0.023
 cry+0.022
 snowball+0.021
Neg logit contributions
 next-0.020
ups-0.019
Rest-0.018
 skies-0.018
lands-0.018
Token out
Token ID503
Feature activation-1.37e+00

Pos logit contributions
ups+0.001
 lifetime+0.001
lands+0.001
yard+0.001
 next+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 scares-0.001
 cry-0.001
 bang-0.001
Token of
Token ID286
Feature activation-1.06e+00

Pos logit contributions
 tant+0.042
 laughs+0.040
 pret+0.037
 scares+0.034
rum+0.034
Neg logit contributions
 next-0.028
ups-0.025
ocular-0.024
Just-0.023
lands-0.023
Token the
Token ID262
Feature activation+1.81e+00

Pos logit contributions
 tant+0.027
 laughs+0.027
rum+0.024
 scares+0.024
 laugh+0.023
Neg logit contributions
 next-0.024
 skies-0.023
yard-0.022
side-0.021
lands-0.021
Token
Token ID220
Feature activation-2.58e-01

Pos logit contributions
 tant+0.001
 laughs+0.001
 scares+0.001
 cry+0.001
 bang+0.001
Neg logit contributions
ups-0.001
 lifetime-0.001
yard-0.001
lands-0.001
Just-0.001
Token
Token ID198
Feature activation-9.13e-02

Pos logit contributions
 laughs+0.006
 tant+0.006
 scares+0.006
 bang+0.005
 cry+0.005
Neg logit contributions
 lifetime-0.006
ups-0.006
lands-0.006
yard-0.006
ider-0.006
TokenSuddenly
Token ID38582
Feature activation-1.06e+00

Pos logit contributions
 tant+0.003
 laughs+0.002
 scares+0.002
 cry+0.002
 laugh+0.002
Neg logit contributions
ups-0.002
 lifetime-0.002
lands-0.002
Just-0.002
yard-0.002
Token,
Token ID11
Feature activation+2.06e-01

Pos logit contributions
 tant+0.023
 laughs+0.021
 cry+0.018
 scares+0.018
rum+0.017
Neg logit contributions
ups-0.029
 lifetime-0.028
lands-0.028
yard-0.028
 next-0.028
Token a
Token ID257
Feature activation-1.59e+00

Pos logit contributions
ups+0.004
 lifetime+0.004
yard+0.004
 next+0.004
lands+0.004
Neg logit contributions
 tant-0.006
 laughs-0.006
rum-0.005
 cry-0.005
 scares-0.005
Token loud
Token ID7812
Feature activation-5.80e+00

Pos logit contributions
 laughs+0.039
 tant+0.038
rum+0.034
 scares+0.032
 cry+0.032
Neg logit contributions
 lifetime-0.039
ups-0.037
yard-0.036
lands-0.035
 next-0.035
Token noise
Token ID7838
Feature activation-1.18e+00

Pos logit contributions
 tant+0.157
 laughs+0.139
rum+0.125
 channel+0.111
 scares+0.108
Neg logit contributions
 next-0.120
yard-0.116
 skies-0.116
ich-0.111
bar-0.107
Token came
Token ID1625
Feature activation-1.55e-02

Pos logit contributions
 tant+0.033
 laughs+0.031
rum+0.028
 cry+0.027
 laugh+0.026
Neg logit contributions
 next-0.024
ups-0.024
 skies-0.022
Rest-0.022
lands-0.022
Token from
Token ID422
Feature activation-1.51e+00

Pos logit contributions
 tant+0.000
 laughs+0.000
 scares+0.000
 cry+0.000
 bang+0.000
Neg logit contributions
ups-0.000
 lifetime-0.000
lands-0.000
yard-0.000
 next-0.000
Token the
Token ID262
Feature activation+2.04e+00

Pos logit contributions
 tant+0.042
 laughs+0.039
rum+0.035
 g+0.032
 cry+0.032
Neg logit contributions
 next-0.036
yard-0.031
lands-0.030
 skies-0.030
ich-0.029
Token sky
Token ID6766
Feature activation+1.13e+00

Pos logit contributions
 lifetime+0.051
iked+0.051
lands+0.050
lor+0.050
ups+0.050
Neg logit contributions
 laughs-0.046
 tant-0.044
 shock-0.044
 cry-0.043
 scares-0.042
Token
Token ID198
Feature activation-7.04e-01

Pos logit contributions
 tant+0.024
 laughs+0.024
 scares+0.020
 cry+0.020
 bang+0.020
Neg logit contributions
 lifetime-0.033
ups-0.033
yard-0.033
lands-0.032
Just-0.031
Token
Token ID198
Feature activation+6.51e-02

Pos logit contributions
 laughs+0.020
 tant+0.020
 scares+0.017
 cry+0.017
 bang+0.017
Neg logit contributions
ups-0.014
 lifetime-0.014
lands-0.014
yard-0.014
Just-0.013
TokenSuddenly
Token ID38582
Feature activation-1.41e+00

Pos logit contributions
ups+0.001
 lifetime+0.001
yard+0.001
lands+0.001
ocular+0.001
Neg logit contributions
 laughs-0.002
 tant-0.002
 scares-0.002
 bang-0.002
 snowball-0.002
Token,
Token ID11
Feature activation-1.59e-01

Pos logit contributions
 tant+0.031
 laughs+0.029
 scares+0.024
 cry+0.024
rum+0.024
Neg logit contributions
 lifetime-0.037
ups-0.037
lands-0.036
yard-0.036
 next-0.036
Token a
Token ID257
Feature activation-1.73e+00

Pos logit contributions
 tant+0.004
 laughs+0.004
rum+0.004
 scares+0.004
 cry+0.004
Neg logit contributions
 lifetime-0.003
 next-0.003
yard-0.003
ups-0.003
lands-0.003
Token loud
Token ID7812
Feature activation-5.80e+00

Pos logit contributions
 laughs+0.043
 tant+0.042
rum+0.038
 scares+0.036
 cry+0.035
Neg logit contributions
 lifetime-0.042
ups-0.039
yard-0.038
lands-0.038
 next-0.038
Token thunder
Token ID18355
Feature activation-2.05e+00

Pos logit contributions
 tant+0.157
 laughs+0.139
rum+0.123
 scares+0.110
 channel+0.106
Neg logit contributions
yard-0.120
 next-0.120
 skies-0.118
ich-0.111
lands-0.109
Token cl
Token ID537
Feature activation-9.29e-02

Pos logit contributions
 tant+0.055
 laughs+0.052
rum+0.047
 cry+0.043
 laugh+0.043
Neg logit contributions
 next-0.043
 skies-0.042
yard-0.042
lands-0.042
ups-0.041
Tokenap
Token ID499
Feature activation+2.88e-02

Pos logit contributions
 laughs+0.003
 tant+0.003
 scares+0.002
 bang+0.002
 cry+0.002
Neg logit contributions
 lifetime-0.002
ups-0.002
lands-0.002
yard-0.002
nuts-0.002
Token interrupted
Token ID19072
Feature activation-5.03e-01

Pos logit contributions
ups+0.001
 next+0.001
lands+0.001
 lifetime+0.001
yard+0.001
Neg logit contributions
 laughs-0.001
 tant-0.001
 cry-0.001
 scares-0.001
 pret-0.001
Token them
Token ID606
Feature activation+6.61e-01

Pos logit contributions
 laughs+0.013
 tant+0.013
 scares+0.012
 bang+0.011
 cry+0.011
Neg logit contributions
ups-0.011
 next-0.011
lands-0.011
 lifetime-0.011
Just-0.010
Token switch
Token ID5078
Feature activation-2.41e-01

Pos logit contributions
 tant+0.017
 laughs+0.017
rum+0.015
 snowball+0.015
 laugh+0.014
Neg logit contributions
 next-0.023
ups-0.023
lands-0.022
 lifetime-0.022
yard-0.021
Token.
Token ID13
Feature activation-6.69e-01

Pos logit contributions
 laughs+0.006
 tant+0.006
 scares+0.006
rum+0.006
 cry+0.006
Neg logit contributions
ups-0.005
 next-0.005
yard-0.005
lands-0.005
 lifetime-0.005
Token Suddenly
Token ID24975
Feature activation-9.38e-01

Pos logit contributions
 laughs+0.015
 tant+0.015
 scares+0.013
 bang+0.013
 cry+0.013
Neg logit contributions
 lifetime-0.017
ups-0.017
lands-0.016
yard-0.016
ider-0.016
Token,
Token ID11
Feature activation+2.32e-01

Pos logit contributions
 tant+0.019
 laughs+0.018
 scares+0.016
 cry+0.015
rum+0.015
Neg logit contributions
ups-0.026
 lifetime-0.026
yard-0.025
lands-0.025
 next-0.025
Token a
Token ID257
Feature activation-1.65e+00

Pos logit contributions
ups+0.005
 lifetime+0.005
yard+0.005
lands+0.005
 next+0.005
Neg logit contributions
 tant-0.006
 laughs-0.006
 scares-0.005
 cry-0.005
rum-0.005
Token loud
Token ID7812
Feature activation-5.79e+00

Pos logit contributions
 laughs+0.043
 tant+0.041
rum+0.038
 scares+0.036
 pret+0.034
Neg logit contributions
 lifetime-0.038
ups-0.034
 next-0.034
yard-0.034
ich-0.033
Token noise
Token ID7838
Feature activation-1.15e+00

Pos logit contributions
 tant+0.149
 laughs+0.136
rum+0.121
 scares+0.107
 snowball+0.106
Neg logit contributions
 next-0.120
bar-0.108
 skies-0.107
yard-0.106
sh-0.099
Token came
Token ID1625
Feature activation-6.34e-02

Pos logit contributions
 tant+0.033
 laughs+0.031
rum+0.029
 cry+0.027
 snowball+0.027
Neg logit contributions
 next-0.022
ups-0.022
 skies-0.020
Rest-0.020
uddled-0.020
Token from
Token ID422
Feature activation-1.15e+00

Pos logit contributions
 tant+0.001
 laughs+0.001
 scares+0.001
 cry+0.001
 bang+0.001
Neg logit contributions
ups-0.002
lands-0.002
 lifetime-0.002
 next-0.002
yard-0.002
Token the
Token ID262
Feature activation+1.64e+00

Pos logit contributions
 tant+0.032
 laughs+0.031
rum+0.028
 scares+0.026
ez+0.025
Neg logit contributions
 next-0.026
yard-0.023
 skies-0.022
lands-0.021
 underground-0.020
Token switch
Token ID5078
Feature activation+5.66e-01

Pos logit contributions
ups+0.033
 lifetime+0.033
yard+0.032
lands+0.032
 next+0.030
Neg logit contributions
 laughs-0.046
 tant-0.046
 scares-0.041
 cry-0.040
 bang-0.040
Token
Token ID198
Feature activation+6.49e-01

Pos logit contributions
ups+0.000
 lifetime+0.000
lands+0.000
yard+0.000
ider+0.000
Neg logit contributions
 laughs-0.000
 tant-0.000
 scares-0.000
 cry-0.000
 bang-0.000
TokenSuddenly
Token ID38582
Feature activation-9.58e-01

Pos logit contributions
yard+0.012
 lifetime+0.012
ocular+0.011
lands+0.011
ups+0.010
Neg logit contributions
 tant-0.019
 laughs-0.018
 bang-0.018
 scares-0.017
 snowball-0.017
Token,
Token ID11
Feature activation+5.58e-01

Pos logit contributions
 tant+0.018
 laughs+0.017
 scares+0.014
 cry+0.014
 bang+0.014
Neg logit contributions
ups-0.028
 lifetime-0.028
lands-0.027
yard-0.027
 next-0.026
Token a
Token ID257
Feature activation-1.56e+00

Pos logit contributions
ups+0.013
 lifetime+0.013
yard+0.012
lands+0.012
 next+0.012
Neg logit contributions
 tant-0.014
 laughs-0.014
 scares-0.012
 cry-0.012
 bang-0.012
Token huge
Token ID3236
Feature activation-4.60e+00

Pos logit contributions
 laughs+0.039
 tant+0.038
rum+0.035
 scares+0.033
 cry+0.031
Neg logit contributions
 lifetime-0.037
ups-0.035
yard-0.034
 next-0.033
lands-0.033
Token loud
Token ID7812
Feature activation-5.79e+00

Pos logit contributions
 tant+0.129
 laughs+0.123
rum+0.120
ez+0.102
 scares+0.101
Neg logit contributions
 next-0.086
 skies-0.081
yard-0.081
ich-0.079
 lifetime-0.077
Token noise
Token ID7838
Feature activation-9.72e-01

Pos logit contributions
 tant+0.149
 laughs+0.139
rum+0.121
 scares+0.106
 channel+0.103
Neg logit contributions
 next-0.121
yard-0.120
 skies-0.114
bar-0.112
ich-0.111
Token appeared
Token ID4120
Feature activation+1.22e+00

Pos logit contributions
 tant+0.028
 laughs+0.026
rum+0.024
 cry+0.023
 laugh+0.022
Neg logit contributions
 next-0.019
ups-0.019
 skies-0.018
Rest-0.018
we-0.017
Token and
Token ID290
Feature activation-1.35e-01

Pos logit contributions
 lifetime+0.034
ups+0.034
yard+0.033
lands+0.033
ider+0.031
Neg logit contributions
 laughs-0.024
 tant-0.024
 scares-0.020
 cry-0.020
 bang-0.020
Token the
Token ID262
Feature activation-8.54e-01

Pos logit contributions
 tant+0.003
 laughs+0.003
rum+0.003
 laugh+0.003
 cry+0.003
Neg logit contributions
ups-0.003
 lifetime-0.003
yard-0.003
 next-0.003
nuts-0.003
Token cats
Token ID11875
Feature activation-6.28e-01

Pos logit contributions
 laughs+0.020
 tant+0.020
 scares+0.017
 cry+0.017
 bang+0.017
Neg logit contributions
ups-0.021
 lifetime-0.021
yard-0.020
lands-0.020
 next-0.019
Token Suddenly
Token ID24975
Feature activation-1.11e+00

Pos logit contributions
 laughs+0.034
 tant+0.034
 scares+0.029
 cry+0.029
 bang+0.029
Neg logit contributions
 lifetime-0.043
ups-0.043
lands-0.041
yard-0.041
ider-0.040
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
 tant+0.021
 laughs+0.021
 scares+0.017
 cry+0.017
 bang+0.017
Neg logit contributions
ups-0.032
 lifetime-0.032
lands-0.031
yard-0.031
 next-0.030
Token there
Token ID612
Feature activation-6.52e-01

Pos logit contributions
 lifetime+0.000
ups+0.000
yard+0.000
lands+0.000
 next+0.000
Neg logit contributions
 laughs-0.000
 tant-0.000
 scares-0.000
 cry-0.000
 bang-0.000
Token was
Token ID373
Feature activation+1.24e+00

Pos logit contributions
 tant+0.021
 laughs+0.020
rum+0.018
 channel+0.018
 scares+0.018
Neg logit contributions
ups-0.010
 next-0.010
yard-0.010
uddled-0.010
 skies-0.010
Token a
Token ID257
Feature activation-2.52e+00

Pos logit contributions
 lifetime+0.031
ups+0.030
lands+0.029
lor+0.028
ider+0.028
Neg logit contributions
 laughs-0.030
 tant-0.029
 snowball-0.027
 bang-0.026
 scares-0.026
Token loud
Token ID7812
Feature activation-5.78e+00

Pos logit contributions
 laughs+0.064
 tant+0.061
rum+0.057
 scares+0.052
ez+0.050
Neg logit contributions
 lifetime-0.060
ich-0.055
 next-0.055
ups-0.053
yard-0.053
Token noise
Token ID7838
Feature activation-6.26e-01

Pos logit contributions
 tant+0.153
 laughs+0.142
rum+0.122
 scares+0.112
 channel+0.107
Neg logit contributions
 next-0.122
yard-0.116
 skies-0.114
ich-0.113
bar-0.108
Token and
Token ID290
Feature activation-7.86e-01

Pos logit contributions
 tant+0.019
 laughs+0.018
rum+0.016
 cry+0.016
 laugh+0.015
Neg logit contributions
ups-0.011
 next-0.011
lands-0.010
yard-0.010
we-0.010
Token a
Token ID257
Feature activation-1.56e+00

Pos logit contributions
 laughs+0.016
 tant+0.016
 scares+0.014
 cry+0.014
 bang+0.014
Neg logit contributions
ups-0.022
 lifetime-0.022
lands-0.021
yard-0.021
ider-0.020
Token bright
Token ID6016
Feature activation-4.30e+00

Pos logit contributions
 laughs+0.036
 tant+0.034
rum+0.032
 scares+0.029
 pret+0.027
Neg logit contributions
 lifetime-0.041
ich-0.037
ups-0.037
 next-0.036
yard-0.036
Token flash
Token ID7644
Feature activation-9.05e-01

Pos logit contributions
 laughs+0.120
 tant+0.116
rum+0.106
 pret+0.099
 scares+0.097
Neg logit contributions
 skies-0.079
 next-0.078
yard-0.076
 lifetime-0.073
bar-0.073
Token bigger
Token ID5749
Feature activation-7.65e-01

Pos logit contributions
lor+0.015
 lifetime+0.015
yard+0.014
lands+0.014
ups+0.014
Neg logit contributions
 laughs-0.014
 tant-0.013
 scares-0.012
 snowball-0.012
 bang-0.012
Token.
Token ID13
Feature activation-9.74e-01

Pos logit contributions
 tant+0.021
 laughs+0.021
 scares+0.018
 cry+0.018
 bang+0.018
Neg logit contributions
ups-0.016
 lifetime-0.016
lands-0.015
yard-0.015
 next-0.015
Token Suddenly
Token ID24975
Feature activation-1.31e+00

Pos logit contributions
 laughs+0.021
 tant+0.020
 bang+0.017
 scares+0.017
 cry+0.017
Neg logit contributions
 lifetime-0.027
ups-0.027
lands-0.026
lor-0.025
ich-0.025
Token,
Token ID11
Feature activation+1.26e-02

Pos logit contributions
 tant+0.028
 laughs+0.027
 scares+0.023
rum+0.023
 cry+0.023
Neg logit contributions
ups-0.034
 lifetime-0.034
 next-0.033
yard-0.033
lands-0.032
Token a
Token ID257
Feature activation-1.54e+00

Pos logit contributions
 lifetime+0.000
ups+0.000
yard+0.000
lands+0.000
 next+0.000
Neg logit contributions
 tant-0.000
 laughs-0.000
 scares-0.000
 cry-0.000
rum-0.000
Token loud
Token ID7812
Feature activation-5.77e+00

Pos logit contributions
 laughs+0.040
 tant+0.039
rum+0.037
 scares+0.034
 cry+0.032
Neg logit contributions
 lifetime-0.035
ups-0.032
 next-0.032
ich-0.031
yard-0.031
Token voice
Token ID3809
Feature activation-1.69e+00

Pos logit contributions
 tant+0.150
 laughs+0.139
rum+0.125
 scares+0.112
 horror+0.105
Neg logit contributions
 next-0.118
 skies-0.109
yard-0.108
bar-0.106
ich-0.104
Token came
Token ID1625
Feature activation-2.32e-01

Pos logit contributions
 tant+0.049
 laughs+0.045
 snowball+0.041
rum+0.040
 laugh+0.038
Neg logit contributions
ups-0.034
 next-0.033
yard-0.032
lands-0.031
Just-0.030
Token from
Token ID422
Feature activation-1.12e+00

Pos logit contributions
 tant+0.006
 laughs+0.006
 scares+0.005
 bang+0.005
 cry+0.005
Neg logit contributions
ups-0.006
 next-0.005
lands-0.005
 lifetime-0.005
yard-0.005
Token the
Token ID262
Feature activation+2.15e+00

Pos logit contributions
 tant+0.033
 laughs+0.030
rum+0.027
 scares+0.026
 bang+0.024
Neg logit contributions
 next-0.026
yard-0.021
lands-0.021
 skies-0.020
Rest-0.020
Token sky
Token ID6766
Feature activation+1.03e+00

Pos logit contributions
 lifetime+0.049
lands+0.048
ups+0.047
lor+0.046
Just+0.044
Neg logit contributions
 laughs-0.057
 tant-0.056
 cry-0.052
 bang-0.050
 laugh-0.050
Token Joe
Token ID5689
Feature activation+2.00e-01

Pos logit contributions
 lifetime+0.037
ups+0.037
lands+0.036
yard+0.036
 next+0.035
Neg logit contributions
 tant-0.032
 laughs-0.031
 scares-0.027
 cry-0.026
 bang-0.026
Token.
Token ID13
Feature activation-1.62e+00

Pos logit contributions
ups+0.004
lands+0.004
 next+0.003
 lifetime+0.003
yard+0.003
Neg logit contributions
 tant-0.006
 laughs-0.006
 scares-0.005
 cry-0.005
 shock-0.005
Token Joe
Token ID5689
Feature activation-1.41e+00

Pos logit contributions
 tant+0.039
 laughs+0.038
 scares+0.033
 cry+0.032
 bang+0.032
Neg logit contributions
lands-0.039
yard-0.039
 lifetime-0.039
ups-0.039
 next-0.037
Token was
Token ID373
Feature activation-7.65e-01

Pos logit contributions
 tant+0.041
 laughs+0.038
 scares+0.034
 cry+0.034
 bang+0.034
Neg logit contributions
ups-0.028
yard-0.027
 next-0.027
 lifetime-0.027
lands-0.026
Token a
Token ID257
Feature activation-3.11e+00

Pos logit contributions
 tant+0.022
 laughs+0.021
 scares+0.019
rum+0.019
 cry+0.018
Neg logit contributions
yard-0.015
ups-0.015
 lifetime-0.015
 next-0.014
lands-0.014
Token big
Token ID1263
Feature activation-5.76e+00

Pos logit contributions
 laughs+0.093
 tant+0.087
rum+0.081
 scares+0.080
 cry+0.074
Neg logit contributions
 lifetime-0.062
 next-0.061
ich-0.060
Just-0.055
ider-0.055
Token and
Token ID290
Feature activation-1.80e+00

Pos logit contributions
 tant+0.160
 laughs+0.159
rum+0.154
 scares+0.144
ez+0.125
Neg logit contributions
 next-0.125
 harbor-0.105
ich-0.105
 lifetime-0.100
 owner-0.098
Token strong
Token ID1913
Feature activation-5.14e+00

Pos logit contributions
 tant+0.051
 laughs+0.048
rum+0.044
 scares+0.043
 bang+0.042
Neg logit contributions
 lifetime-0.038
 next-0.038
yard-0.034
ups-0.033
Just-0.033
Token bear
Token ID6842
Feature activation-4.44e-01

Pos logit contributions
 laughs+0.135
 tant+0.126
 scares+0.119
rum+0.114
 gasp+0.104
Neg logit contributions
 next-0.112
yard-0.108
ich-0.107
 lifetime-0.104
lands-0.104
Token who
Token ID508
Feature activation-1.80e+00

Pos logit contributions
 laughs+0.011
 tant+0.011
 scares+0.010
 cry+0.010
 bang+0.009
Neg logit contributions
ups-0.010
 lifetime-0.010
lands-0.010
yard-0.010
nuts-0.009
Token always
Token ID1464
Feature activation-5.52e-01

Pos logit contributions
 tant+0.059
 laughs+0.055
 scares+0.050
rum+0.049
 cry+0.049
Neg logit contributions
yard-0.029
 lifetime-0.028
ups-0.028
 next-0.027
Rest-0.026
TokenSuddenly
Token ID38582
Feature activation-7.72e-01

Pos logit contributions
 lifetime+0.005
yard+0.005
ups+0.004
lands+0.004
ocular+0.004
Neg logit contributions
 laughs-0.009
 tant-0.009
 bang-0.008
 laugh-0.008
 scares-0.008
Token,
Token ID11
Feature activation+7.00e-01

Pos logit contributions
 tant+0.015
 laughs+0.015
 scares+0.012
 cry+0.012
 bang+0.012
Neg logit contributions
ups-0.022
 lifetime-0.022
lands-0.022
yard-0.021
 next-0.021
Token there
Token ID612
Feature activation-3.17e-01

Pos logit contributions
 lifetime+0.013
ups+0.013
yard+0.013
 next+0.013
lands+0.013
Neg logit contributions
 tant-0.020
 laughs-0.020
rum-0.018
 scares-0.017
 cry-0.017
Token was
Token ID373
Feature activation+1.16e+00

Pos logit contributions
 tant+0.009
 laughs+0.009
rum+0.008
 scares+0.008
 cry+0.008
Neg logit contributions
ups-0.006
yard-0.006
 next-0.006
lands-0.006
 lifetime-0.006
Token a
Token ID257
Feature activation-2.68e+00

Pos logit contributions
 lifetime+0.029
ups+0.028
lands+0.027
ider+0.027
lor+0.026
Neg logit contributions
 laughs-0.028
 tant-0.027
 snowball-0.024
 scares-0.024
 bang-0.024
Token loud
Token ID7812
Feature activation-5.74e+00

Pos logit contributions
 laughs+0.070
 tant+0.069
rum+0.064
 scares+0.057
ez+0.056
Neg logit contributions
 lifetime-0.063
 next-0.056
ich-0.055
yard-0.054
ups-0.054
Token his
Token ID465
Feature activation+4.27e-02

Pos logit contributions
 tant+0.155
 laughs+0.140
rum+0.122
 scares+0.109
 channel+0.104
Neg logit contributions
 next-0.122
yard-0.118
 skies-0.115
bar-0.109
ich-0.107
Tokensing
Token ID12215
Feature activation-2.06e+00

Pos logit contributions
 lifetime+0.001
yard+0.001
ups+0.001
lands+0.001
 next+0.001
Neg logit contributions
 laughs-0.001
 tant-0.001
 scares-0.001
rum-0.001
 bang-0.001
Token noise
Token ID7838
Feature activation-5.61e-01

Pos logit contributions
 tant+0.059
 laughs+0.057
 scares+0.048
rum+0.048
 pret+0.047
Neg logit contributions
 next-0.041
ups-0.037
Just-0.036
 lifetime-0.036
we-0.036
Token.
Token ID13
Feature activation-1.30e+00

Pos logit contributions
 tant+0.017
 laughs+0.016
rum+0.014
 cry+0.014
 scares+0.013
Neg logit contributions
ups-0.011
 next-0.011
lands-0.010
yard-0.010
 lifetime-0.010
Token The
Token ID383
Feature activation-4.46e-01

Pos logit contributions
 tant+0.032
 laughs+0.032
 scares+0.027
 cry+0.027
 laugh+0.027
Neg logit contributions
ups-0.030
yard-0.030
 lifetime-0.030
lands-0.029
Just-0.028
Token heard
Token ID2982
Feature activation+4.74e-01

Pos logit contributions
 lifetime+0.033
ups+0.033
lands+0.031
yard+0.031
ider+0.030
Neg logit contributions
 laughs-0.030
 tant-0.029
 scares-0.025
 cry-0.025
 bang-0.025
Token it
Token ID340
Feature activation+2.71e-01

Pos logit contributions
ups+0.010
 lifetime+0.010
lands+0.009
yard+0.009
 next+0.009
Neg logit contributions
 tant-0.013
 laughs-0.013
 scares-0.011
 cry-0.011
 bang-0.011
Token again
Token ID757
Feature activation+8.35e-01

Pos logit contributions
ups+0.006
 lifetime+0.006
lands+0.006
yard+0.006
 next+0.006
Neg logit contributions
 tant-0.007
 laughs-0.007
 scares-0.006
 snowball-0.006
rum-0.006
Token -
Token ID532
Feature activation+9.32e-01

Pos logit contributions
ups+0.018
 lifetime+0.018
lands+0.017
yard+0.017
 next+0.017
Neg logit contributions
 tant-0.023
 laughs-0.022
 scares-0.020
 bang-0.019
 cry-0.019
Token a
Token ID257
Feature activation-1.12e+00

Pos logit contributions
 lifetime+0.019
ups+0.019
lands+0.019
yard+0.019
 next+0.018
Neg logit contributions
 tant-0.026
 laughs-0.025
rum-0.022
 scares-0.022
 cry-0.021
Token loud
Token ID7812
Feature activation-5.74e+00

Pos logit contributions
 laughs+0.029
 tant+0.028
rum+0.026
 scares+0.024
 cry+0.023
Neg logit contributions
 lifetime-0.027
 next-0.024
ups-0.024
ich-0.024
yard-0.023
Token roar
Token ID34532
Feature activation-6.92e-02

Pos logit contributions
 tant+0.156
 laughs+0.142
rum+0.128
 scares+0.113
 pret+0.109
Neg logit contributions
 next-0.117
yard-0.113
 skies-0.110
ich-0.107
 lifetime-0.104
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
 tant+0.002
 laughs+0.002
rum+0.002
 cry+0.002
 scares+0.002
Neg logit contributions
ups-0.001
 lifetime-0.001
 next-0.001
lands-0.001
yard-0.001
Token Green
Token ID3469
Feature activation-6.01e-01

Pos logit contributions
 laughs+0.031
 tant+0.030
 scares+0.027
 bang+0.027
 cry+0.026
Neg logit contributions
ups-0.038
 lifetime-0.038
lands-0.036
yard-0.035
ider-0.035
Token was
Token ID373
Feature activation-4.70e-01

Pos logit contributions
 tant+0.016
 laughs+0.015
 scares+0.013
 cry+0.013
 snowball+0.013
Neg logit contributions
ups-0.014
 lifetime-0.013
lands-0.013
yard-0.013
 next-0.012
Token scared
Token ID12008
Feature activation-6.85e-01

Pos logit contributions
 tant+0.013
 laughs+0.011
rum+0.010
 pret+0.009
 scares+0.009
Neg logit contributions
 next-0.011
yard-0.011
ups-0.011
ich-0.010
Just-0.010
Token Suddenly
Token ID24975
Feature activation-9.90e-01

Pos logit contributions
 laughs+0.019
 tant+0.019
 scares+0.016
 cry+0.016
 bang+0.016
Neg logit contributions
ups-0.019
 lifetime-0.019
lands-0.018
yard-0.018
ider-0.017
Token,
Token ID11
Feature activation-4.05e-01

Pos logit contributions
 tant+0.020
 laughs+0.019
 scares+0.016
 cry+0.016
rum+0.016
Neg logit contributions
ups-0.028
 lifetime-0.028
lands-0.027
yard-0.027
 next-0.026
Token there
Token ID612
Feature activation-4.49e-01

Pos logit contributions
 tant+0.010
 laughs+0.010
 scares+0.009
 cry+0.009
rum+0.009
Neg logit contributions
 lifetime-0.009
ups-0.009
lands-0.009
yard-0.009
 next-0.008
Token was
Token ID373
Feature activation+8.83e-01

Pos logit contributions
 tant+0.012
 laughs+0.012
rum+0.011
 scares+0.011
 cry+0.010
Neg logit contributions
ups-0.009
yard-0.009
lands-0.009
 lifetime-0.009
 next-0.009
Token a
Token ID257
Feature activation-2.68e+00

Pos logit contributions
 lifetime+0.019
ups+0.019
lands+0.018
yard+0.018
ider+0.017
Neg logit contributions
 laughs-0.024
 tant-0.023
 scares-0.021
 bang-0.020
 cry-0.020
Token loud
Token ID7812
Feature activation-5.74e+00

Pos logit contributions
 laughs+0.068
 tant+0.067
rum+0.062
 scares+0.057
ez+0.053
Neg logit contributions
 lifetime-0.063
 next-0.057
yard-0.057
ups-0.056
ich-0.056
Token bang
Token ID20188
Feature activation-5.40e-01

Pos logit contributions
 tant+0.154
 laughs+0.137
rum+0.122
 scares+0.109
 channel+0.106
Neg logit contributions
 next-0.121
yard-0.118
 skies-0.115
bar-0.112
lands-0.105
Token and
Token ID290
Feature activation-8.52e-01

Pos logit contributions
 tant+0.014
 laughs+0.014
 cry+0.012
rum+0.012
 laugh+0.012
Neg logit contributions
ups-0.012
lands-0.011
 next-0.011
 lifetime-0.011
yard-0.011
Token the
Token ID262
Feature activation-6.63e-01

Pos logit contributions
 tant+0.021
 laughs+0.020
rum+0.018
 cry+0.018
 scares+0.017
Neg logit contributions
 lifetime-0.020
ups-0.019
yard-0.019
lands-0.019
 next-0.018
Token tree
Token ID5509
Feature activation-1.51e+00

Pos logit contributions
 tant+0.016
 laughs+0.016
 scares+0.014
rum+0.014
 cry+0.014
Neg logit contributions
 lifetime-0.015
ups-0.015
yard-0.015
lands-0.015
 next-0.014
Token fell
Token ID3214
Feature activation-1.61e-01

Pos logit contributions
 tant+0.039
 laughs+0.039
rum+0.034
 scares+0.034
 cry+0.033
Neg logit contributions
ups-0.034
 lifetime-0.032
yard-0.032
lands-0.031
 next-0.030
Token girl
Token ID2576
Feature activation-9.26e-01

Pos logit contributions
 laughs+0.010
 tant+0.010
 scares+0.009
 cry+0.009
 bang+0.008
Neg logit contributions
ups-0.012
 lifetime-0.012
lands-0.011
yard-0.011
ider-0.011
Token smiled
Token ID13541
Feature activation-4.45e-01

Pos logit contributions
 tant+0.022
 laughs+0.021
 scares+0.019
 bang+0.018
 cry+0.018
Neg logit contributions
ups-0.023
 lifetime-0.023
yard-0.022
lands-0.022
Just-0.021
Token and
Token ID290
Feature activation+4.83e-01

Pos logit contributions
 laughs+0.008
 tant+0.008
 scares+0.007
 cry+0.007
 bang+0.007
Neg logit contributions
ups-0.013
 lifetime-0.013
lands-0.013
yard-0.013
nuts-0.012
Token said
Token ID531
Feature activation+9.55e-01

Pos logit contributions
ups+0.012
 lifetime+0.012
lands+0.012
yard+0.012
nuts+0.011
Neg logit contributions
 laughs-0.011
 tant-0.011
 scares-0.010
 cry-0.010
 bang-0.009
Token,
Token ID11
Feature activation+2.09e+00

Pos logit contributions
ups+0.029
 lifetime+0.029
lands+0.028
yard+0.028
nuts+0.027
Neg logit contributions
 tant-0.017
 laughs-0.017
 scares-0.014
 cry-0.014
 bang-0.014
Token "
Token ID366
Feature activation+4.68e+00

Pos logit contributions
ups+0.053
 lifetime+0.052
lands+0.049
yard+0.049
ider+0.047
Neg logit contributions
 laughs-0.048
 tant-0.046
 bang-0.042
 laugh-0.042
 cry-0.041
TokenThat
Token ID2504
Feature activation+9.99e-01

Pos logit contributions
yard+0.094
ups+0.093
 lifetime+0.086
lands+0.083
uddled+0.083
Neg logit contributions
 laughs-0.126
 tant-0.119
 g-0.114
 laugh-0.112
 scares-0.107
Token's
Token ID338
Feature activation-6.39e-01

Pos logit contributions
 lifetime+0.021
ups+0.021
ider+0.021
lands+0.020
yard+0.020
Neg logit contributions
 laughs-0.027
 tant-0.025
 scares-0.024
 cry-0.024
 laugh-0.023
Token mighty
Token ID18680
Feature activation-1.88e+00

Pos logit contributions
 tant+0.017
 laughs+0.016
 scares+0.014
 bang+0.014
 cry+0.014
Neg logit contributions
 lifetime-0.015
ups-0.014
lands-0.014
yard-0.014
 next-0.014
Token busy
Token ID8179
Feature activation-1.02e+00

Pos logit contributions
 tant+0.045
 laughs+0.043
 bang+0.037
 scares+0.037
 cry+0.037
Neg logit contributions
 lifetime-0.046
ups-0.045
 next-0.044
yard-0.043
lands-0.043
Token of
Token ID286
Feature activation-6.28e-01

Pos logit contributions
 tant+0.026
 laughs+0.025
 scares+0.022
 bang+0.021
 cry+0.021
Neg logit contributions
ups-0.024
 lifetime-0.024
yard-0.023
lands-0.023
 next-0.022
Token said
Token ID531
Feature activation+2.15e+00

Pos logit contributions
ups+0.032
 lifetime+0.031
yard+0.029
lands+0.029
 next+0.029
Neg logit contributions
 tant-0.039
 laughs-0.039
 scares-0.034
rum-0.034
 bang-0.034
Token to
Token ID284
Feature activation-4.92e-01

Pos logit contributions
 lifetime+0.052
ups+0.051
lands+0.050
yard+0.049
ider+0.046
Neg logit contributions
 laughs-0.053
 tant-0.052
 scares-0.046
 cry-0.046
 bang-0.045
Token his
Token ID465
Feature activation+7.55e-01

Pos logit contributions
 tant+0.008
 laughs+0.008
 scares+0.007
 cry+0.006
 snowball+0.006
Neg logit contributions
ups-0.015
 next-0.015
yard-0.015
 lifetime-0.015
lands-0.015
Token mom
Token ID1995
Feature activation+1.02e+00

Pos logit contributions
ups+0.013
 lifetime+0.013
 next+0.013
yard+0.012
lands+0.012
Neg logit contributions
 laughs-0.023
 tant-0.023
 scares-0.021
rum-0.021
 cry-0.020
Token,
Token ID11
Feature activation+1.77e+00

Pos logit contributions
 lifetime+0.030
ups+0.030
lands+0.029
yard+0.029
ider+0.028
Neg logit contributions
 laughs-0.019
 tant-0.019
 cry-0.015
 scares-0.015
 bang-0.015
Token "
Token ID366
Feature activation+4.52e+00

Pos logit contributions
ups+0.036
 lifetime+0.036
lands+0.034
yard+0.034
 next+0.033
Neg logit contributions
 tant-0.049
 laughs-0.049
 scares-0.043
 cry-0.042
 bang-0.042
TokenI
Token ID40
Feature activation-1.09e+00

Pos logit contributions
 lifetime+0.078
yard+0.077
lands+0.075
ups+0.075
ider+0.070
Neg logit contributions
 tant-0.140
 laughs-0.138
 snowball-0.125
 cry-0.124
 bang-0.124
Token want
Token ID765
Feature activation+2.22e+00

Pos logit contributions
 laughs+0.025
 tant+0.025
rum+0.022
 scares+0.021
 channel+0.021
Neg logit contributions
 lifetime-0.025
 next-0.025
We-0.024
ups-0.024
 afford-0.024
Token to
Token ID284
Feature activation-3.36e-03

Pos logit contributions
ider+0.059
 lifetime+0.058
lor+0.054
lands+0.054
side+0.053
Neg logit contributions
 laughs-0.053
 bang-0.047
 scares-0.046
 tant-0.045
 g-0.045
Token go
Token ID467
Feature activation+3.76e-01

Pos logit contributions
 laughs+0.000
 tant+0.000
 cry+0.000
 bang+0.000
 laugh+0.000
Neg logit contributions
 lifetime-0.000
ups-0.000
lands-0.000
yard-0.000
ider-0.000
Token to
Token ID284
Feature activation+6.14e-02

Pos logit contributions
 lifetime+0.009
ups+0.009
yard+0.009
lands+0.009
lor+0.009
Neg logit contributions
 laughs-0.009
 tant-0.008
 laugh-0.008
 scares-0.008
 cry-0.008
Token where
Token ID810
Feature activation+1.68e+00

Pos logit contributions
 next+0.038
ups+0.038
yard+0.037
Just+0.037
lands+0.036
Neg logit contributions
 tant-0.056
 laughs-0.053
 scares-0.049
rum-0.048
 snowball-0.047
Token her
Token ID607
Feature activation+1.42e+00

Pos logit contributions
 lifetime+0.043
ups+0.043
lands+0.041
yard+0.041
ider+0.039
Neg logit contributions
 laughs-0.038
 tant-0.038
 scares-0.033
 cry-0.032
 bang-0.032
Token mom
Token ID1995
Feature activation+5.49e-01

Pos logit contributions
ups+0.029
 lifetime+0.029
lands+0.028
yard+0.028
nuts+0.026
Neg logit contributions
 laughs-0.039
 tant-0.039
 scares-0.035
 cry-0.034
 bang-0.034
Token was
Token ID373
Feature activation-1.02e-01

Pos logit contributions
ups+0.012
 lifetime+0.012
yard+0.012
lands+0.012
 next+0.012
Neg logit contributions
 tant-0.015
 laughs-0.014
 scares-0.012
rum-0.012
 cry-0.012
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
 laughs+0.003
 tant+0.003
 cry+0.003
 scares+0.003
 laugh+0.002
Neg logit contributions
 lifetime-0.002
ups-0.002
lands-0.002
yard-0.002
lor-0.002
Token "
Token ID366
Feature activation+4.11e+00

Pos logit contributions
 tant+0.032
 laughs+0.032
 scares+0.028
 snowball+0.028
 bang+0.028
Neg logit contributions
ups-0.024
yard-0.023
lands-0.023
 lifetime-0.022
Just-0.022
TokenMom
Token ID29252
Feature activation+1.69e-01

Pos logit contributions
yard+0.094
 lifetime+0.091
lands+0.089
ups+0.088
nuts+0.083
Neg logit contributions
 laughs-0.108
 tant-0.108
 cry-0.093
 g-0.093
 laugh-0.093
Token,
Token ID11
Feature activation+8.26e-01

Pos logit contributions
ups+0.004
 lifetime+0.004
 next+0.004
yard+0.004
lands+0.004
Neg logit contributions
 tant-0.004
 laughs-0.004
 scares-0.003
 snowball-0.003
rum-0.003
Token mom
Token ID1995
Feature activation-6.32e-01

Pos logit contributions
ups+0.019
 lifetime+0.018
 next+0.018
lands+0.018
yard+0.017
Neg logit contributions
 tant-0.021
 laughs-0.020
 scares-0.018
rum-0.017
 snowball-0.017
Token,
Token ID11
Feature activation+6.85e-01

Pos logit contributions
 tant+0.015
 laughs+0.013
 scares+0.012
 bang+0.011
 snowball+0.011
Neg logit contributions
ups-0.017
 lifetime-0.016
lands-0.016
 next-0.016
yard-0.016
Token look
Token ID804
Feature activation-1.45e+00

Pos logit contributions
ups+0.016
 lifetime+0.016
 next+0.015
lands+0.015
yard+0.015
Neg logit contributions
 tant-0.017
 laughs-0.016
 scares-0.014
rum-0.014
 snowball-0.014
Token was
Token ID373
Feature activation-1.41e+00

Pos logit contributions
 tant+0.034
 laughs+0.033
 scares+0.030
rum+0.029
 bang+0.029
Neg logit contributions
ups-0.026
 lifetime-0.026
yard-0.024
lands-0.024
 next-0.024
Token doing
Token ID1804
Feature activation-1.12e+00

Pos logit contributions
 laughs+0.038
 tant+0.038
 cry+0.034
 scares+0.033
 laugh+0.033
Neg logit contributions
ups-0.030
 lifetime-0.030
lands-0.028
yard-0.028
ider-0.027
Token and
Token ID290
Feature activation-5.35e-01

Pos logit contributions
 laughs+0.021
 tant+0.020
 scares+0.017
 cry+0.017
 laugh+0.016
Neg logit contributions
ups-0.033
 lifetime-0.033
lands-0.032
yard-0.032
nuts-0.031
Token said
Token ID531
Feature activation+1.19e+00

Pos logit contributions
 laughs+0.014
 tant+0.014
 scares+0.012
 cry+0.012
 bang+0.012
Neg logit contributions
ups-0.012
 lifetime-0.012
lands-0.012
yard-0.011
ider-0.011
Token,
Token ID11
Feature activation+7.77e-01

Pos logit contributions
 lifetime+0.027
ups+0.027
lands+0.026
yard+0.026
ich+0.025
Neg logit contributions
 laughs-0.031
 tant-0.030
 scares-0.026
 cry-0.026
 bang-0.026
Token "
Token ID366
Feature activation+4.68e+00

Pos logit contributions
 lifetime+0.020
ups+0.020
lands+0.019
yard+0.019
lor+0.018
Neg logit contributions
 laughs-0.017
 tant-0.017
 bang-0.015
 cry-0.015
 g-0.015
TokenNo
Token ID2949
Feature activation-4.65e-01

Pos logit contributions
yard+0.109
 lifetime+0.101
ider+0.099
lands+0.098
ich+0.097
Neg logit contributions
 laughs-0.118
 tant-0.115
 g-0.099
 laugh-0.098
 snowball-0.096
Token Jane
Token ID12091
Feature activation-1.05e+00

Pos logit contributions
 tant+0.010
 laughs+0.010
 scares+0.009
 bang+0.008
 snowball+0.008
Neg logit contributions
ups-0.012
 lifetime-0.012
yard-0.011
lands-0.011
 next-0.011
Token,
Token ID11
Feature activation-7.60e-02

Pos logit contributions
 tant+0.023
 laughs+0.022
 bang+0.019
 scares+0.019
 snowball+0.019
Neg logit contributions
ups-0.029
 lifetime-0.027
yard-0.027
lands-0.027
 next-0.026
Token you
Token ID345
Feature activation-1.52e+00

Pos logit contributions
 laughs+0.002
 tant+0.002
 scares+0.002
 cry+0.002
 bang+0.002
Neg logit contributions
ups-0.001
 lifetime-0.001
lands-0.001
yard-0.001
nuts-0.001
Token must
Token ID1276
Feature activation-6.14e-01

Pos logit contributions
 tant+0.033
 laughs+0.033
 scares+0.028
 snowball+0.027
 bang+0.027
Neg logit contributions
ups-0.040
 lifetime-0.039
yard-0.038
lands-0.038
nuts-0.037
Token hungry
Token ID14720
Feature activation+1.73e-01

Pos logit contributions
 tant+0.036
 laughs+0.036
rum+0.032
 scares+0.031
 bang+0.031
Neg logit contributions
ups-0.035
yard-0.033
 lifetime-0.033
 next-0.032
lands-0.032
Token.
Token ID13
Feature activation-6.83e-01

Pos logit contributions
 lifetime+0.004
ups+0.004
lands+0.004
yard+0.004
lor+0.004
Neg logit contributions
 laughs-0.004
 tant-0.004
 cry-0.004
 scares-0.004
 bang-0.003
Token She
Token ID1375
Feature activation-2.76e-01

Pos logit contributions
 laughs+0.017
 tant+0.016
 cry+0.014
 scares+0.014
 bang+0.014
Neg logit contributions
 lifetime-0.017
ups-0.016
lands-0.016
yard-0.015
ich-0.015
Token said
Token ID531
Feature activation+1.32e+00

Pos logit contributions
 tant+0.007
 laughs+0.007
 scares+0.006
 cry+0.006
 bang+0.006
Neg logit contributions
ups-0.006
 lifetime-0.006
yard-0.006
lands-0.006
Just-0.006
Token,
Token ID11
Feature activation+1.44e+00

Pos logit contributions
ups+0.036
 lifetime+0.035
lands+0.034
yard+0.034
 next+0.033
Neg logit contributions
 tant-0.027
 laughs-0.027
 scares-0.023
 cry-0.023
 bang-0.023
Token "
Token ID366
Feature activation+4.00e+00

Pos logit contributions
ups+0.033
 lifetime+0.032
lands+0.031
yard+0.031
nuts+0.029
Neg logit contributions
 laughs-0.037
 tant-0.037
 scares-0.032
 cry-0.032
 bang-0.032
TokenMom
Token ID29252
Feature activation+8.02e-01

Pos logit contributions
yard+0.086
 lifetime+0.084
lands+0.081
ups+0.079
ider+0.077
Neg logit contributions
 tant-0.109
 laughs-0.108
 cry-0.095
 laugh-0.094
 g-0.094
Tokenmy
Token ID1820
Feature activation-2.33e-01

Pos logit contributions
ups+0.016
 lifetime+0.016
lands+0.016
yard+0.016
 next+0.015
Neg logit contributions
 tant-0.022
 laughs-0.022
 scares-0.020
 cry-0.019
 bang-0.019
Token,
Token ID11
Feature activation+5.06e-01

Pos logit contributions
 tant+0.005
 laughs+0.005
 scares+0.004
 snowball+0.004
rum+0.004
Neg logit contributions
ups-0.006
 lifetime-0.006
 next-0.006
yard-0.006
lands-0.006
Token I
Token ID314
Feature activation-7.39e-01

Pos logit contributions
ups+0.010
 lifetime+0.010
 next+0.009
lands+0.009
yard+0.009
Neg logit contributions
 tant-0.014
 laughs-0.014
 scares-0.013
rum-0.012
 snowball-0.012
Token'm
Token ID1101
Feature activation-4.30e-01

Pos logit contributions
 tant+0.019
 laughs+0.018
rum+0.016
 snowball+0.016
 channel+0.015
Neg logit contributions
 next-0.015
ups-0.015
We-0.015
 lifetime-0.015
Just-0.014
Token a
Token ID257
Feature activation-6.28e-01

Pos logit contributions
 tant+0.009
 scares+0.008
 laughs+0.008
rum+0.008
 cry+0.007
Neg logit contributions
 next-0.011
 lifetime-0.010
lands-0.010
ups-0.010
Just-0.010
Token treat
Token ID2190
Feature activation+1.01e+00

Pos logit contributions
 laughs+0.016
 tant+0.015
rum+0.015
 scares+0.014
 cry+0.013
Neg logit contributions
 lifetime-0.015
 next-0.013
yard-0.012
ich-0.012
lands-0.012
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
ups+0.022
 lifetime+0.022
yard+0.021
lands+0.021
 next+0.020
Neg logit contributions
 tant-0.026
 laughs-0.026
 scares-0.023
 cry-0.023
 bang-0.023
Token After
Token ID2293
Feature activation+9.68e-01

Pos logit contributions
 lifetime+0.034
ups+0.033
yard+0.033
lands+0.032
Just+0.031
Neg logit contributions
 tant-0.038
 laughs-0.038
 scares-0.033
 cry-0.032
 bang-0.032
Token that
Token ID326
Feature activation-9.42e-01

Pos logit contributions
ups+0.021
 lifetime+0.020
lands+0.020
yard+0.019
ider+0.018
Neg logit contributions
 laughs-0.026
 tant-0.026
 scares-0.023
 cry-0.023
 bang-0.023
Token,
Token ID11
Feature activation+6.87e-01

Pos logit contributions
 laughs+0.023
 tant+0.022
rum+0.020
 bang+0.019
 scares+0.019
Neg logit contributions
 next-0.023
 lifetime-0.022
yard-0.021
bar-0.020
lands-0.020
Token Max
Token ID5436
Feature activation-2.18e-01

Pos logit contributions
 lifetime+0.017
ups+0.016
yard+0.016
lands+0.016
 next+0.016
Neg logit contributions
 laughs-0.016
 tant-0.016
 scares-0.014
rum-0.014
 bang-0.014
Token and
Token ID290
Feature activation+2.73e-02

Pos logit contributions
 tant+0.007
 laughs+0.006
rum+0.006
 scares+0.006
 snowball+0.006
Neg logit contributions
ups-0.004
yard-0.004
 next-0.004
 lifetime-0.004
Just-0.004
Token his
Token ID465
Feature activation+1.77e+00

Pos logit contributions
 next+0.001
 lifetime+0.001
ups+0.001
lan+0.001
yard+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
rum-0.001
 scares-0.001
 channel-0.001
Token owners
Token ID4393
Feature activation-6.82e-01

Pos logit contributions
 lifetime+0.032
ups+0.032
yard+0.031
lands+0.030
 next+0.030
Neg logit contributions
 tant-0.053
 laughs-0.052
 scares-0.047
rum-0.046
 bang-0.046
Token would
Token ID561
Feature activation+1.75e-01

Pos logit contributions
 tant+0.018
 laughs+0.018
 snowball+0.016
 scares+0.016
rum+0.016
Neg logit contributions
 lifetime-0.014
ups-0.014
yard-0.014
nuts-0.013
lands-0.013
Token play
Token ID711
Feature activation-6.37e-01

Pos logit contributions
ups+0.002
 lifetime+0.002
lands+0.002
yard+0.002
 next+0.002
Neg logit contributions
 tant-0.002
 laughs-0.002
 scares-0.002
rum-0.002
 cry-0.002
Token in
Token ID287
Feature activation-5.13e-01

Pos logit contributions
 laughs+0.016
 tant+0.016
 scares+0.014
 bang+0.014
 snowball+0.014
Neg logit contributions
 lifetime-0.015
ups-0.015
lands-0.014
yard-0.014
lor-0.013
Token the
Token ID262
Feature activation+2.46e+00

Pos logit contributions
 tant+0.011
 laughs+0.010
rum+0.009
 scares+0.009
 bang+0.008
Neg logit contributions
 next-0.014
ups-0.014
lands-0.014
 lifetime-0.014
yard-0.013
Token park
Token ID3952
Feature activation+1.39e+00

Pos logit contributions
ider+0.055
 lifetime+0.054
ups+0.054
lands+0.052
lor+0.052
Neg logit contributions
 laughs-0.064
 tant-0.062
 snowball-0.060
 scares-0.057
 bang-0.057
Token with
Token ID351
Feature activation-6.73e-01

Pos logit contributions
 lifetime+0.041
lor+0.040
ups+0.039
ich+0.038
Just+0.037
Neg logit contributions
 laughs-0.026
 tant-0.024
 laugh-0.023
 g-0.021
 cry-0.021
Token their
Token ID511
Feature activation+1.69e+00

Pos logit contributions
 tant+0.015
rum+0.015
 laughs+0.014
 scares+0.014
 bang+0.013
Neg logit contributions
ups-0.017
 next-0.016
lands-0.016
ocular-0.015
yard-0.015
Token daddy
Token ID35822
Feature activation+5.65e-01

Pos logit contributions
 lifetime+0.032
ups+0.032
 next+0.032
yard+0.031
lands+0.031
Neg logit contributions
 tant-0.047
 laughs-0.047
rum-0.044
 scares-0.043
 bang-0.042
Token.
Token ID13
Feature activation-7.87e-01

Pos logit contributions
ups+0.012
 lifetime+0.011
lands+0.011
 next+0.011
yard+0.011
Neg logit contributions
 tant-0.016
 laughs-0.015
 scares-0.014
 cry-0.014
 bang-0.014
Token One
Token ID1881
Feature activation+4.30e-01

Pos logit contributions
 laughs+0.024
 tant+0.024
 scares+0.022
rum+0.021
 cry+0.021
Neg logit contributions
ups-0.013
 lifetime-0.013
yard-0.013
lands-0.013
 next-0.012
Token day
Token ID1110
Feature activation+1.08e+00

Pos logit contributions
ups+0.009
 lifetime+0.009
lands+0.008
yard+0.008
 next+0.008
Neg logit contributions
 tant-0.012
 laughs-0.012
 scares-0.011
 bang-0.011
 cry-0.011
Token,
Token ID11
Feature activation+1.14e+00

Pos logit contributions
ups+0.032
 lifetime+0.032
lands+0.031
yard+0.031
ider+0.030
Neg logit contributions
 tant-0.020
 laughs-0.020
 scares-0.016
 cry-0.016
 bang-0.016
Token.
Token ID13
Feature activation-1.97e+00

Pos logit contributions
 lifetime+0.029
ups+0.027
lands+0.026
lor+0.026
Days+0.025
Neg logit contributions
 laughs-0.022
 tant-0.021
 bang-0.020
 scares-0.019
 cry-0.019
Token Tim
Token ID5045
Feature activation-9.75e-02

Pos logit contributions
 laughs+0.039
 tant+0.038
 scares+0.032
 cry+0.032
 bang+0.031
Neg logit contributions
ups-0.056
 lifetime-0.056
lands-0.054
yard-0.054
ider-0.052
Tokenmy
Token ID1820
Feature activation-2.56e-01

Pos logit contributions
 tant+0.003
 laughs+0.003
 scares+0.003
 bang+0.003
 shock+0.003
Neg logit contributions
ups-0.002
 lifetime-0.002
 next-0.002
lands-0.001
yard-0.001
Token was
Token ID373
Feature activation-4.98e-01

Pos logit contributions
 tant+0.006
 laughs+0.006
 scares+0.006
 cry+0.005
 bang+0.005
Neg logit contributions
ups-0.006
 lifetime-0.006
yard-0.006
lands-0.006
Just-0.006
Token so
Token ID523
Feature activation+1.04e-02

Pos logit contributions
 tant+0.015
 laughs+0.014
 scares+0.013
rum+0.012
 snowball+0.012
Neg logit contributions
yard-0.009
ups-0.009
 lifetime-0.009
 next-0.009
lands-0.009
Token happy
Token ID3772
Feature activation+1.65e+00

Pos logit contributions
 next+0.000
 lifetime+0.000
ups+0.000
Just+0.000
yard+0.000
Neg logit contributions
 tant-0.000
 laughs-0.000
 scares-0.000
 snowball-0.000
 bang-0.000
Token!
Token ID0
Feature activation-5.93e-01

Pos logit contributions
 lifetime+0.045
ups+0.043
lands+0.042
yard+0.042
lor+0.041
Neg logit contributions
 laughs-0.036
 tant-0.033
 scares-0.030
 cry-0.030
 laugh-0.029
Token He
Token ID679
Feature activation-4.77e-02

Pos logit contributions
 laughs+0.011
 tant+0.011
 scares+0.009
 cry+0.009
 bang+0.009
Neg logit contributions
 lifetime-0.018
ups-0.018
lands-0.017
yard-0.017
nuts-0.016
Token played
Token ID2826
Feature activation-6.77e-01

Pos logit contributions
 tant+0.001
 laughs+0.001
 scares+0.001
rum+0.001
 cry+0.001
Neg logit contributions
ups-0.001
 lifetime-0.001
yard-0.001
lands-0.001
Just-0.001
Token with
Token ID351
Feature activation-1.73e+00

Pos logit contributions
 tant+0.019
 laughs+0.019
 scares+0.017
 cry+0.017
rum+0.017
Neg logit contributions
 next-0.013
ups-0.013
 lifetime-0.013
yard-0.012
lands-0.012
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
 laughs+0.038
 tant+0.037
 scares+0.036
rum+0.034
 cry+0.034
Neg logit contributions
ups-0.041
 next-0.040
lands-0.038
 skies-0.037
yard-0.037
Token the
Token ID262
Feature activation+2.42e-01

Pos logit contributions
 tant+0.010
 laughs+0.010
 scares+0.009
 cry+0.008
rum+0.008
Neg logit contributions
ups-0.011
 lifetime-0.011
yard-0.011
lands-0.011
 next-0.010
Token wind
Token ID2344
Feature activation-1.01e+00

Pos logit contributions
ups+0.005
 lifetime+0.005
lands+0.005
yard+0.005
Just+0.005
Neg logit contributions
 tant-0.006
 laughs-0.006
 bang-0.006
 scares-0.006
 cry-0.006
Token blow
Token ID6611
Feature activation-9.99e-01

Pos logit contributions
 tant+0.024
 laughs+0.024
 scares+0.021
 cry+0.020
 bang+0.020
Neg logit contributions
ups-0.024
 lifetime-0.024
lands-0.023
yard-0.023
 next-0.022
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
 laughs+0.025
 tant+0.024
rum+0.022
 scares+0.022
 cry+0.022
Neg logit contributions
ups-0.023
 next-0.021
lands-0.021
 lifetime-0.021
bar-0.020
Token
Token ID198
Feature activation+4.21e-01

Pos logit contributions
 laughs+0.004
 tant+0.004
 scares+0.003
 cry+0.003
 bang+0.003
Neg logit contributions
ups-0.004
 lifetime-0.004
lands-0.004
yard-0.004
nuts-0.004
Token
Token ID198
Feature activation+1.09e+00

Pos logit contributions
ups+0.009
 lifetime+0.009
lands+0.008
yard+0.008
Just+0.008
Neg logit contributions
 laughs-0.012
 tant-0.012
 scares-0.010
 cry-0.010
 bang-0.010
TokenThe
Token ID464
Feature activation+6.64e-01

Pos logit contributions
yard+0.019
ocular+0.018
 lifetime+0.017
ups+0.017
lands+0.017
Neg logit contributions
 tant-0.033
 laughs-0.032
 snowball-0.031
 bang-0.031
 laugh-0.030
Token car
Token ID1097
Feature activation+6.50e-01

Pos logit contributions
ups+0.016
 lifetime+0.015
lands+0.015
lor+0.015
yard+0.015
Neg logit contributions
 laughs-0.017
 tant-0.016
 bang-0.015
 cry-0.015
 scares-0.014
Token saw
Token ID2497
Feature activation-8.15e-02

Pos logit contributions
 lifetime+0.015
ups+0.015
lands+0.015
yard+0.014
nuts+0.014
Neg logit contributions
 laughs-0.016
 tant-0.016
 scares-0.014
 cry-0.014
 bang-0.014
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
 tant+0.002
 laughs+0.002
 cry+0.002
 scares+0.002
 laugh+0.002
Neg logit contributions
ups-0.002
 lifetime-0.002
yard-0.002
lands-0.002
 next-0.002
Token way
Token ID835
Feature activation+4.13e-01

Pos logit contributions
 laughs+0.035
 tant+0.033
rum+0.031
 scares+0.030
 cry+0.028
Neg logit contributions
 lifetime-0.030
ich-0.027
ups-0.027
 next-0.027
lands-0.027
TokenMom
Token ID29252
Feature activation-4.85e-01

Pos logit contributions
 lifetime+0.049
ups+0.048
yard+0.047
lands+0.046
nuts+0.042
Neg logit contributions
 tant-0.098
 laughs-0.097
 scares-0.088
 cry-0.087
 bang-0.087
Token,
Token ID11
Feature activation+6.32e-01

Pos logit contributions
 tant+0.014
 laughs+0.012
rum+0.011
 snowball+0.011
 scares+0.011
Neg logit contributions
ups-0.011
 next-0.011
yard-0.010
nuts-0.009
lands-0.009
Token what
Token ID644
Feature activation+5.49e-01

Pos logit contributions
 next+0.014
ups+0.014
 lifetime+0.013
nuts+0.013
yard+0.013
Neg logit contributions
 tant-0.016
 laughs-0.015
 scares-0.014
rum-0.014
 snowball-0.013
Token is
Token ID318
Feature activation-5.23e-01

Pos logit contributions
ups+0.014
 next+0.013
nuts+0.012
We+0.012
yard+0.012
Neg logit contributions
 tant-0.013
 laughs-0.011
rum-0.010
 bang-0.010
 snowball-0.010
Token this
Token ID428
Feature activation-4.76e-01

Pos logit contributions
 laughs+0.014
 tant+0.014
 scares+0.013
 cry+0.013
 bang+0.012
Neg logit contributions
ups-0.011
 lifetime-0.011
lands-0.010
yard-0.010
nuts-0.010
Token?
Token ID30
Feature activation+1.43e+00

Pos logit contributions
 tant+0.012
 laughs+0.012
rum+0.010
 cry+0.010
 bang+0.010
Neg logit contributions
 next-0.011
ups-0.011
 lifetime-0.010
yard-0.010
ich-0.010
Token Why
Token ID4162
Feature activation-1.33e+00

Pos logit contributions
ups+0.026
ider+0.026
yard+0.026
 next+0.025
 lifetime+0.025
Neg logit contributions
 tant-0.041
 laughs-0.041
 laugh-0.035
 cry-0.035
 scares-0.035
Token is
Token ID318
Feature activation+1.46e-01

Pos logit contributions
 tant+0.035
 laughs+0.029
 horror+0.028
rum+0.028
 snowball+0.028
Neg logit contributions
ups-0.030
sters-0.028
nuts-0.028
 next-0.028
mons-0.027
Token it
Token ID340
Feature activation-5.33e-01

Pos logit contributions
ups+0.003
 lifetime+0.003
yard+0.003
lands+0.003
 next+0.003
Neg logit contributions
 tant-0.004
 laughs-0.004
 scares-0.003
 cry-0.003
 bang-0.003
Token spicy
Token ID26880
Feature activation+9.76e-02

Pos logit contributions
 tant+0.016
 laughs+0.015
rum+0.013
 scares+0.013
 bang+0.012
Neg logit contributions
 next-0.011
ups-0.011
yard-0.010
nuts-0.010
ich-0.010
Token?
Token ID30
Feature activation+1.16e+00

Pos logit contributions
ups+0.002
 next+0.002
nuts+0.002
yard+0.002
lands+0.002
Neg logit contributions
 tant-0.002
 laughs-0.002
 cry-0.002
 scares-0.002
 bang-0.002
Token this
Token ID428
Feature activation-1.36e-01

Pos logit contributions
 tant+0.017
 laughs+0.016
 scares+0.015
 cry+0.015
 bang+0.014
Neg logit contributions
ups-0.012
 lifetime-0.011
lands-0.011
yard-0.011
 next-0.010
Token again
Token ID757
Feature activation+2.96e-01

Pos logit contributions
 tant+0.004
 laughs+0.004
 scares+0.004
 cry+0.004
 bang+0.003
Neg logit contributions
 lifetime-0.003
ups-0.003
lands-0.002
yard-0.002
 next-0.002
Token.
Token ID13
Feature activation+3.08e-02

Pos logit contributions
ups+0.006
 lifetime+0.006
lands+0.006
yard+0.006
 next+0.005
Neg logit contributions
 laughs-0.008
 tant-0.008
 scares-0.007
 cry-0.007
 bang-0.007
Token<|endoftext|>
Token ID50256
Feature activation+1.07e+00

Pos logit contributions
ups+0.001
 lifetime+0.001
lands+0.001
yard+0.001
Just+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 scares-0.001
 bang-0.001
 cry-0.001
TokenL
Token ID43
Feature activation-1.05e+00

Pos logit contributions
ups+0.022
 lifetime+0.022
lands+0.021
yard+0.021
 next+0.020
Neg logit contributions
 tant-0.029
 laughs-0.029
 cry-0.026
 scares-0.026
 bang-0.026
Tokenily
Token ID813
Feature activation-3.83e-01

Pos logit contributions
 tant+0.024
 laughs+0.024
 scares+0.021
 cry+0.021
 bang+0.020
Neg logit contributions
ups-0.027
 lifetime-0.026
lands-0.025
yard-0.025
 next-0.024
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
 tant+0.011
 laughs+0.009
rum+0.009
 scares+0.009
 bang+0.009
Neg logit contributions
ups-0.008
 next-0.008
yard-0.008
lands-0.007
Just-0.007
Token Tom
Token ID4186
Feature activation-9.70e-01

Pos logit contributions
yard+0.030
ups+0.030
 next+0.030
 lifetime+0.029
We+0.029
Neg logit contributions
 tant-0.033
 laughs-0.031
rum-0.028
 snowball-0.028
 scares-0.028
Token were
Token ID547
Feature activation+2.03e+00

Pos logit contributions
 tant+0.031
rum+0.027
 laughs+0.027
 scares+0.026
 snowball+0.026
Neg logit contributions
 next-0.016
ups-0.015
We-0.015
Rest-0.014
yard-0.014
Token friends
Token ID2460
Feature activation+1.25e-01

Pos logit contributions
 lifetime+0.042
ups+0.042
lands+0.041
yard+0.039
lor+0.038
Neg logit contributions
 laughs-0.057
 tant-0.055
 cry-0.049
 laugh-0.049
 scares-0.049
Token who
Token ID508
Feature activation-1.47e+00

Pos logit contributions
 lifetime+0.003
ups+0.003
yard+0.003
lands+0.003
nuts+0.003
Neg logit contributions
 laughs-0.003
 tant-0.003
 laugh-0.002
 g-0.002
 cry-0.002
Token.
Token ID13
Feature activation-1.18e+00

Pos logit contributions
 tant+0.040
 laughs+0.040
 cry+0.037
rum+0.036
 scares+0.036
Neg logit contributions
ups-0.024
 next-0.024
 lifetime-0.022
lands-0.022
nuts-0.020
Token It
Token ID632
Feature activation-2.23e+00

Pos logit contributions
 tant+0.030
 laughs+0.030
 laugh+0.026
 cry+0.026
 scares+0.025
Neg logit contributions
ups-0.026
Just-0.025
yard-0.025
 lifetime-0.025
lands-0.025
Token wants
Token ID3382
Feature activation+1.32e+00

Pos logit contributions
 tant+0.044
rum+0.041
 laughs+0.036
 snowball+0.033
 laugh+0.032
Neg logit contributions
ups-0.063
 next-0.061
Just-0.056
yard-0.056
ider-0.056
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
ups+0.020
 lifetime+0.019
yard+0.018
lands+0.018
 next+0.017
Neg logit contributions
 tant-0.044
 laughs-0.043
 scares-0.039
 cry-0.039
rum-0.039
Token erase
Token ID28602
Feature activation-2.76e+00

Pos logit contributions
 tant+0.041
 laughs+0.038
rum+0.035
 snowball+0.035
 scares+0.034
Neg logit contributions
ups-0.032
 next-0.031
yard-0.031
 lifetime-0.031
lands-0.030
Token everything
Token ID2279
Feature activation-2.56e+00

Pos logit contributions
 tant+0.078
 laughs+0.072
 cry+0.069
 scares+0.067
 snowball+0.067
Neg logit contributions
ups-0.056
 next-0.052
lands-0.050
 lifetime-0.048
nuts-0.047
Token.
Token ID13
Feature activation-1.26e+00

Pos logit contributions
 tant+0.078
 laughs+0.073
 scares+0.066
 cry+0.066
 bang+0.065
Neg logit contributions
ups-0.048
 next-0.047
lands-0.044
 lifetime-0.043
yard-0.043
Token It
Token ID632
Feature activation-1.85e+00

Pos logit contributions
 tant+0.033
 laughs+0.032
 laugh+0.028
 cry+0.028
 scares+0.028
Neg logit contributions
ups-0.028
 lifetime-0.027
Just-0.027
yard-0.026
lands-0.026
Token waits
Token ID28364
Feature activation+6.02e-01

Pos logit contributions
 tant+0.034
rum+0.031
 laughs+0.029
 snowball+0.025
 laugh+0.025
Neg logit contributions
ups-0.054
 next-0.053
ider-0.049
yard-0.049
Just-0.049
Token for
Token ID329
Feature activation-1.38e+00

Pos logit contributions
ups+0.013
 lifetime+0.013
lands+0.013
yard+0.012
ider+0.012
Neg logit contributions
 laughs-0.016
 tant-0.016
 scares-0.014
 cry-0.014
 bang-0.014
Token a
Token ID257
Feature activation+2.67e-01

Pos logit contributions
 laughs+0.028
 tant+0.027
 scares+0.023
 cry+0.023
 bang+0.023
Neg logit contributions
ups-0.039
 lifetime-0.039
lands-0.037
yard-0.037
ider-0.036
Token prove
Token ID5879
Feature activation+8.57e-01

Pos logit contributions
 tant+0.037
 laughs+0.036
 scares+0.031
 snowball+0.030
rum+0.030
Neg logit contributions
ups-0.032
 lifetime-0.031
 next-0.030
yard-0.030
lands-0.030
Token he
Token ID339
Feature activation+5.58e-01

Pos logit contributions
ups+0.020
 lifetime+0.019
lands+0.018
yard+0.018
 next+0.018
Neg logit contributions
 tant-0.022
 laughs-0.022
 scares-0.019
 bang-0.019
 cry-0.019
Token was
Token ID373
Feature activation-5.78e-01

Pos logit contributions
ups+0.013
 lifetime+0.013
lands+0.013
yard+0.013
ider+0.012
Neg logit contributions
 laughs-0.013
 tant-0.013
 scares-0.012
 cry-0.011
 bang-0.011
Token brave
Token ID14802
Feature activation-1.12e+00

Pos logit contributions
 laughs+0.016
 tant+0.016
 scares+0.015
 cry+0.014
 bang+0.014
Neg logit contributions
ups-0.011
 lifetime-0.011
lands-0.011
yard-0.011
ider-0.010
Token,
Token ID11
Feature activation+2.84e-01

Pos logit contributions
 tant+0.028
 laughs+0.028
 scares+0.025
 bang+0.025
 snowball+0.024
Neg logit contributions
ups-0.025
 next-0.025
 lifetime-0.024
lands-0.023
yard-0.022
Token and
Token ID290
Feature activation+4.61e-01

Pos logit contributions
ups+0.006
 lifetime+0.006
lands+0.006
yard+0.006
 next+0.006
Neg logit contributions
 tant-0.008
 laughs-0.008
 scares-0.007
 bang-0.007
 cry-0.007
Token he
Token ID339
Feature activation+6.96e-02

Pos logit contributions
ups+0.009
 lifetime+0.009
yard+0.008
lands+0.008
 next+0.008
Neg logit contributions
 tant-0.013
 laughs-0.013
 scares-0.012
 bang-0.012
 cry-0.012
Token had
Token ID550
Feature activation+2.12e+00

Pos logit contributions
ups+0.002
 lifetime+0.001
yard+0.001
lands+0.001
 next+0.001
Neg logit contributions
 tant-0.002
 laughs-0.002
 scares-0.002
 bang-0.002
rum-0.002
Token -
Token ID532
Feature activation+9.28e-01

Pos logit contributions
 lifetime+0.043
lands+0.042
ider+0.041
yard+0.041
ups+0.041
Neg logit contributions
 laughs-0.060
 tant-0.057
 scares-0.052
 cry-0.052
 laugh-0.051
Token but
Token ID475
Feature activation-1.04e+00

Pos logit contributions
ups+0.019
 lifetime+0.019
lands+0.018
yard+0.018
 next+0.017
Neg logit contributions
 tant-0.026
 laughs-0.026
 scares-0.023
 cry-0.022
 bang-0.022
Token at
Token ID379
Feature activation-2.58e-01

Pos logit contributions
 tant+0.029
 laughs+0.029
 scares+0.026
 bang+0.025
 cry+0.025
Neg logit contributions
ups-0.021
 lifetime-0.021
yard-0.020
lands-0.020
 next-0.019
Token bar
Token ID2318
Feature activation+1.71e-01

Pos logit contributions
 next+0.041
ups+0.040
 lifetime+0.038
Just+0.038
ider+0.038
Neg logit contributions
 laughs-0.029
 tant-0.029
 scares-0.026
rum-0.026
 cry-0.024
Tokenber
Token ID527
Feature activation+5.03e-01

Pos logit contributions
ups+0.002
ider+0.002
 next+0.002
 lifetime+0.002
lands+0.002
Neg logit contributions
 laughs-0.006
 tant-0.006
 cry-0.005
 scares-0.005
 bang-0.005
Token cut
Token ID2005
Feature activation-1.07e+00

Pos logit contributions
ups+0.011
 lifetime+0.011
yard+0.011
lands+0.011
 next+0.011
Neg logit contributions
 tant-0.013
 laughs-0.013
 scares-0.011
 cry-0.011
rum-0.011
Token his
Token ID465
Feature activation+1.99e-01

Pos logit contributions
 laughs+0.027
 tant+0.026
 scares+0.025
 cry+0.025
 laugh+0.024
Neg logit contributions
ups-0.024
 next-0.023
bar-0.022
lands-0.021
yard-0.021
Token hair
Token ID4190
Feature activation-1.23e-01

Pos logit contributions
ups+0.004
 next+0.004
Just+0.004
yard+0.004
ider+0.004
Neg logit contributions
 laughs-0.005
 tant-0.005
 scares-0.005
rum-0.005
 bang-0.004
Token short
Token ID1790
Feature activation-7.01e-01

Pos logit contributions
 laughs+0.003
 tant+0.003
 scares+0.002
 cry+0.002
 bang+0.002
Neg logit contributions
ups-0.003
lands-0.003
 lifetime-0.003
yard-0.003
 next-0.003
Token and
Token ID290
Feature activation-1.36e-01

Pos logit contributions
 laughs+0.017
 scares+0.016
 tant+0.016
 cry+0.014
rum+0.014
Neg logit contributions
ups-0.016
 next-0.016
lands-0.015
bar-0.015
nuts-0.015
Token made
Token ID925
Feature activation-1.30e-01

Pos logit contributions
 tant+0.004
 laughs+0.003
 scares+0.003
rum+0.003
 cry+0.003
Neg logit contributions
ups-0.003
 lifetime-0.003
 next-0.003
yard-0.003
bar-0.003
Token it
Token ID340
Feature activation+1.50e-01

Pos logit contributions
 tant+0.003
 laughs+0.003
 scares+0.003
rum+0.003
 cry+0.003
Neg logit contributions
ups-0.003
 lifetime-0.003
yard-0.003
 next-0.003
lands-0.003
Token look
Token ID804
Feature activation-7.98e-01

Pos logit contributions
ups+0.004
 lifetime+0.004
lands+0.003
yard+0.003
 next+0.003
Neg logit contributions
 tant-0.004
 laughs-0.004
 scares-0.003
rum-0.003
 bang-0.003
Token nice
Token ID3621
Feature activation+8.19e-01

Pos logit contributions
 laughs+0.023
rum+0.022
 tant+0.022
 scares+0.021
 cry+0.020
Neg logit contributions
ups-0.014
 lifetime-0.014
 next-0.014
 prett-0.013
ocular-0.012
Token their
Token ID511
Feature activation+1.08e+00

Pos logit contributions
 tant+0.018
 laughs+0.017
 scares+0.016
 cry+0.016
rum+0.016
Neg logit contributions
ups-0.015
 next-0.015
lands-0.014
ocular-0.014
nuts-0.014
Token stamps
Token ID25560
Feature activation+3.06e-01

Pos logit contributions
ups+0.023
 lifetime+0.023
lands+0.022
yard+0.022
ider+0.021
Neg logit contributions
 laughs-0.029
 tant-0.029
 scares-0.025
 bang-0.025
 laugh-0.025
Token with
Token ID351
Feature activation-1.45e+00

Pos logit contributions
 lifetime+0.008
ups+0.008
yard+0.007
lands+0.007
ider+0.007
Neg logit contributions
 laughs-0.007
 tant-0.007
 scares-0.006
 cry-0.006
 laugh-0.006
Token each
Token ID1123
Feature activation-3.58e-01

Pos logit contributions
 tant+0.040
 laughs+0.039
 scares+0.037
 cry+0.036
rum+0.036
Neg logit contributions
ups-0.031
 next-0.027
lands-0.027
 lifetime-0.027
yard-0.026
Token other
Token ID584
Feature activation+3.91e-01

Pos logit contributions
 tant+0.012
 laughs+0.012
 scares+0.012
 cry+0.011
rum+0.011
Neg logit contributions
 next-0.005
ups-0.005
 lifetime-0.004
lands-0.004
yard-0.004
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
ups+0.008
 lifetime+0.008
lands+0.008
yard+0.008
 next+0.008
Neg logit contributions
 tant-0.010
 laughs-0.010
 scares-0.009
 bang-0.009
 cry-0.009
Token They
Token ID1119
Feature activation-1.52e+00

Pos logit contributions
 tant+0.006
 laughs+0.006
 scares+0.005
 cry+0.005
 bang+0.005
Neg logit contributions
ups-0.005
 lifetime-0.005
lands-0.005
yard-0.005
 next-0.005
Token learn
Token ID2193
Feature activation+1.36e+00

Pos logit contributions
 tant+0.030
 laughs+0.028
rum+0.026
 scares+0.025
 snowball+0.025
Neg logit contributions
ups-0.042
 lifetime-0.041
yard-0.041
lands-0.041
 next-0.040
Token that
Token ID326
Feature activation+1.53e+00

Pos logit contributions
 lifetime+0.028
ups+0.026
lands+0.026
yard+0.026
ider+0.025
Neg logit contributions
 laughs-0.039
 tant-0.038
 scares-0.034
 bang-0.033
 cry-0.033
Token sharing
Token ID7373
Feature activation-1.68e+00

Pos logit contributions
ups+0.031
 lifetime+0.031
lands+0.030
yard+0.030
nuts+0.028
Neg logit contributions
 laughs-0.042
 tant-0.042
 scares-0.037
 cry-0.037
 bang-0.037
Token is
Token ID318
Feature activation+2.91e-01

Pos logit contributions
 tant+0.039
 snowball+0.036
rum+0.036
 laughs+0.035
 cry+0.035
Neg logit contributions
ups-0.043
 next-0.042
lands-0.038
nuts-0.037
ocular-0.037
Token<|endoftext|>
Token ID50256
Feature activation+2.16e-01

Pos logit contributions
 lifetime+0.019
ups+0.019
yard+0.019
lands+0.018
Just+0.018
Neg logit contributions
 laughs-0.023
 tant-0.023
 scares-0.020
 cry-0.020
 bang-0.020
TokenOnce
Token ID7454
Feature activation-2.58e-01

Pos logit contributions
 lifetime+0.003
 next+0.003
ups+0.003
lor+0.003
lands+0.003
Neg logit contributions
 tant-0.007
 laughs-0.007
 cry-0.006
 bang-0.006
 scares-0.006
Token there
Token ID612
Feature activation-1.83e+00

Pos logit contributions
 laughs+0.008
 tant+0.008
 scares+0.008
 bang+0.007
 cry+0.007
Neg logit contributions
 lifetime-0.004
ups-0.004
lands-0.004
yard-0.004
 next-0.004
Token was
Token ID373
Feature activation+7.40e-01

Pos logit contributions
 tant+0.057
 laughs+0.053
 scares+0.052
 bang+0.052
rum+0.050
Neg logit contributions
 next-0.033
 lifetime-0.030
yard-0.029
lands-0.028
ups-0.028
Token a
Token ID257
Feature activation-2.05e+00

Pos logit contributions
ups+0.016
 lifetime+0.016
lands+0.015
yard+0.015
ider+0.014
Neg logit contributions
 laughs-0.020
 tant-0.020
 scares-0.017
 cry-0.017
 bang-0.017
Token clever
Token ID14169
Feature activation-4.04e+00

Pos logit contributions
 laughs+0.057
 tant+0.055
rum+0.051
 scares+0.051
 cry+0.047
Neg logit contributions
 lifetime-0.043
 next-0.042
ich-0.041
Just-0.039
ups-0.039
Token puppy
Token ID26188
Feature activation-8.54e-01

Pos logit contributions
 laughs+0.115
 tant+0.110
rum+0.106
 scares+0.104
 cry+0.097
Neg logit contributions
 next-0.077
ich-0.075
 lifetime-0.072
lands-0.071
ari-0.069
Token.
Token ID13
Feature activation-7.22e-01

Pos logit contributions
 laughs+0.017
 tant+0.017
 scares+0.015
 cry+0.015
 bang+0.014
Neg logit contributions
ups-0.024
 lifetime-0.024
lands-0.023
yard-0.023
nuts-0.022
Token He
Token ID679
Feature activation-1.31e+00

Pos logit contributions
 tant+0.021
 laughs+0.020
 scares+0.018
 cry+0.017
 bang+0.017
Neg logit contributions
yard-0.014
lands-0.014
 lifetime-0.014
ocular-0.013
 next-0.013
Token wanted
Token ID2227
Feature activation+2.13e+00

Pos logit contributions
 tant+0.040
 laughs+0.038
rum+0.035
 scares+0.034
 cry+0.034
Neg logit contributions
 next-0.024
 lifetime-0.024
Just-0.023
ups-0.023
yard-0.022
Token to
Token ID284
Feature activation-1.98e-01

Pos logit contributions
ider+0.051
 lifetime+0.051
lands+0.048
lor+0.048
ups+0.047
Neg logit contributions
 laughs-0.055
 tant-0.050
 bang-0.047
 cry-0.047
 laugh-0.047
Token smelled
Token ID37609
Feature activation-3.69e-01

Pos logit contributions
 tant+0.007
 laughs+0.006
rum+0.006
 scares+0.006
 cry+0.006
Neg logit contributions
ups-0.006
 lifetime-0.005
 next-0.005
lands-0.005
yard-0.005
Token good
Token ID922
Feature activation+4.38e-02

Pos logit contributions
 tant+0.010
 laughs+0.010
rum+0.009
 scares+0.009
 cry+0.009
Neg logit contributions
ups-0.007
 next-0.007
nuts-0.007
 skies-0.007
lands-0.007
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
ups+0.001
 lifetime+0.001
 next+0.001
lands+0.001
yard+0.001
Neg logit contributions
 tant-0.001
 laughs-0.001
 scares-0.001
 cry-0.001
 bang-0.001
Token It
Token ID632
Feature activation-6.77e-01

Pos logit contributions
 laughs+0.037
 tant+0.037
 scares+0.032
 cry+0.032
 bang+0.031
Neg logit contributions
ups-0.039
 lifetime-0.039
lands-0.038
yard-0.038
Just-0.036
Token was
Token ID373
Feature activation-5.26e-01

Pos logit contributions
 tant+0.022
rum+0.021
 laughs+0.019
 cry+0.018
 channel+0.018
Neg logit contributions
 next-0.012
ups-0.011
We-0.010
Just-0.010
ocular-0.010
Token an
Token ID281
Feature activation-3.39e+00

Pos logit contributions
 tant+0.015
 laughs+0.014
rum+0.013
 scares+0.013
 cry+0.013
Neg logit contributions
 next-0.010
ups-0.010
yard-0.010
lands-0.010
nuts-0.010
Token orange
Token ID10912
Feature activation-1.55e+00

Pos logit contributions
 laughs+0.091
 tant+0.091
 scares+0.081
 cry+0.078
 laugh+0.078
Neg logit contributions
ups-0.069
yard-0.068
 lifetime-0.068
lands-0.067
 next-0.066
Token!
Token ID0
Feature activation-9.96e-01

Pos logit contributions
 tant+0.038
 laughs+0.038
 scares+0.034
rum+0.032
 cry+0.032
Neg logit contributions
 next-0.035
 lifetime-0.034
yard-0.034
ups-0.034
ider-0.034
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
 laughs+0.027
 tant+0.026
 cry+0.023
 laugh+0.023
 scares+0.023
Neg logit contributions
ups-0.021
 lifetime-0.021
yard-0.020
lands-0.020
Just-0.020
Token
Token ID198
Feature activation-3.42e-01

Pos logit contributions
 laughs+0.030
 tant+0.029
 scares+0.026
 cry+0.026
 bang+0.025
Neg logit contributions
 lifetime-0.031
ups-0.030
yard-0.030
lands-0.029
nuts-0.028
Token"
Token ID1
Feature activation+4.14e+00

Pos logit contributions
 laughs+0.007
 tant+0.007
 scares+0.006
 snowball+0.006
 bang+0.006
Neg logit contributions
yard-0.010
 lifetime-0.009
lands-0.009
ocular-0.008
nuts-0.008
Token.
Token ID13
Feature activation-4.08e-01

Pos logit contributions
 lifetime+0.012
ups+0.012
yard+0.011
lands+0.011
lor+0.011
Neg logit contributions
 laughs-0.011
 tant-0.011
 scares-0.010
 cry-0.009
 laugh-0.009
Token He
Token ID679
Feature activation+3.64e-01

Pos logit contributions
 laughs+0.009
 tant+0.009
 bang+0.008
 snowball+0.007
 scares+0.007
Neg logit contributions
ups-0.011
 lifetime-0.011
ider-0.010
lands-0.010
ich-0.010
Token was
Token ID373
Feature activation-3.41e-01

Pos logit contributions
 lifetime+0.007
ups+0.007
lands+0.007
yard+0.007
 next+0.006
Neg logit contributions
 tant-0.010
 laughs-0.010
 cry-0.009
 scares-0.009
rum-0.009
Token a
Token ID257
Feature activation-1.67e+00

Pos logit contributions
 tant+0.010
 laughs+0.010
 scares+0.009
rum+0.009
 cry+0.009
Neg logit contributions
yard-0.006
 next-0.006
ups-0.006
 lifetime-0.006
lands-0.006
Token very
Token ID845
Feature activation-1.24e+00

Pos logit contributions
 laughs+0.045
 tant+0.044
 scares+0.039
rum+0.039
 cry+0.038
Neg logit contributions
 lifetime-0.037
ups-0.034
 next-0.034
ich-0.034
lands-0.034
Token strong
Token ID1913
Feature activation-4.45e+00

Pos logit contributions
 tant+0.033
 laughs+0.033
rum+0.029
 bang+0.028
 scares+0.028
Neg logit contributions
 lifetime-0.027
ups-0.026
 next-0.026
yard-0.025
ider-0.025
Token swim
Token ID9422
Feature activation-4.20e-02

Pos logit contributions
 laughs+0.123
 tant+0.118
rum+0.109
 scares+0.106
 cry+0.104
Neg logit contributions
 next-0.089
 lifetime-0.088
lands-0.087
ich-0.086
yard-0.085
Tokenmer
Token ID647
Feature activation+1.02e-01

Pos logit contributions
 laughs+0.001
 tant+0.001
 scares+0.001
 cry+0.001
 bang+0.001
Neg logit contributions
ups-0.001
 lifetime-0.001
lands-0.001
yard-0.001
 next-0.001
Token and
Token ID290
Feature activation+1.66e-02

Pos logit contributions
ups+0.002
 lifetime+0.002
 next+0.002
lands+0.002
yard+0.002
Neg logit contributions
 tant-0.002
 laughs-0.002
 cry-0.002
 scares-0.002
 bang-0.002
Token loved
Token ID6151
Feature activation+7.97e-01

Pos logit contributions
 lifetime+0.000
ups+0.000
yard+0.000
lands+0.000
 next+0.000
Neg logit contributions
 tant-0.000
 laughs-0.000
rum-0.000
 scares-0.000
 bang-0.000
Token the
Token ID262
Feature activation+5.31e-01

Pos logit contributions
ups+0.014
 lifetime+0.014
lands+0.013
yard+0.013
ider+0.013
Neg logit contributions
 laughs-0.024
 tant-0.024
 scares-0.022
 cry-0.021
 bang-0.021
Token happened
Token ID3022
Feature activation+1.98e+00

Pos logit contributions
 laughs+0.007
 tant+0.007
 scares+0.006
 cry+0.006
 bang+0.006
Neg logit contributions
ups-0.007
 lifetime-0.007
lands-0.007
yard-0.007
nuts-0.007
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
 lifetime+0.055
ups+0.054
yard+0.053
lands+0.052
lor+0.050
Neg logit contributions
 laughs-0.041
 tant-0.036
 scares-0.035
 cry-0.034
 laugh-0.034
Token Suddenly
Token ID24975
Feature activation-4.85e-01

Pos logit contributions
ups+0.006
 lifetime+0.006
lands+0.006
yard+0.006
ider+0.005
Neg logit contributions
 laughs-0.007
 tant-0.007
 scares-0.006
 cry-0.006
 bang-0.006
Token,
Token ID11
Feature activation+5.86e-01

Pos logit contributions
 tant+0.011
 laughs+0.011
 scares+0.009
 cry+0.009
 bang+0.009
Neg logit contributions
ups-0.013
 lifetime-0.013
lands-0.012
yard-0.012
 next-0.012
Token a
Token ID257
Feature activation-1.44e+00

Pos logit contributions
 lifetime+0.012
ups+0.012
yard+0.011
lands+0.011
 next+0.011
Neg logit contributions
 laughs-0.016
 tant-0.016
 scares-0.014
 cry-0.014
 bang-0.014
Token big
Token ID1263
Feature activation-4.65e+00

Pos logit contributions
 laughs+0.036
 tant+0.035
rum+0.033
 scares+0.030
 cry+0.030
Neg logit contributions
 lifetime-0.034
ups-0.033
 next-0.030
yard-0.030
ich-0.030
Token wave
Token ID6769
Feature activation+2.98e-01

Pos logit contributions
 tant+0.124
rum+0.122
 laughs+0.115
ez+0.104
 scares+0.100
Neg logit contributions
 next-0.093
 skies-0.089
 harbor-0.086
 island-0.079
yard-0.079
Token came
Token ID1625
Feature activation+2.19e-01

Pos logit contributions
 next+0.006
ups+0.006
 lifetime+0.006
bar+0.006
yard+0.006
Neg logit contributions
 tant-0.008
 laughs-0.008
rum-0.007
 snowball-0.006
 cry-0.006
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
ups+0.006
 lifetime+0.006
lands+0.006
yard+0.006
nuts+0.005
Neg logit contributions
 laughs-0.005
 tant-0.005
 scares-0.004
 cry-0.004
 bang-0.004
Token knocked
Token ID13642
Feature activation+2.24e-01

Pos logit contributions
ups+0.024
 lifetime+0.023
yard+0.022
 next+0.022
lands+0.022
Neg logit contributions
 tant-0.025
 laughs-0.025
rum-0.022
 cry-0.021
 scares-0.021
Token Tommy
Token ID19919
Feature activation+7.59e-01

Pos logit contributions
 next+0.006
ups+0.005
nuts+0.005
We+0.005
bar+0.005
Neg logit contributions
 tant-0.006
 laughs-0.005
 scares-0.005
 cry-0.005
 laugh-0.005
Tokenara
Token ID3301
Feature activation+5.53e-01

Pos logit contributions
ups+0.008
yard+0.008
 lifetime+0.008
nuts+0.008
lands+0.008
Neg logit contributions
 laughs-0.006
 tant-0.006
 snowball-0.005
 bang-0.005
 laugh-0.005
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
 lifetime+0.014
ups+0.014
yard+0.013
lands+0.013
ider+0.013
Neg logit contributions
 laughs-0.013
 tant-0.012
 cry-0.011
 laugh-0.011
 snowball-0.011
Token Z
Token ID1168
Feature activation-6.16e-01

Pos logit contributions
 tant+0.025
 laughs+0.024
 scares+0.021
 cry+0.021
 bang+0.021
Neg logit contributions
ups-0.024
 lifetime-0.024
lands-0.024
yard-0.023
 next-0.022
Tokenara
Token ID3301
Feature activation-1.65e+00

Pos logit contributions
 laughs+0.014
 tant+0.014
 scares+0.012
 cry+0.012
 bang+0.012
Neg logit contributions
ups-0.015
 lifetime-0.015
yard-0.015
lands-0.015
nuts-0.014
Token was
Token ID373
Feature activation-3.56e-01

Pos logit contributions
 laughs+0.039
 tant+0.038
 scares+0.034
 cry+0.033
 bang+0.033
Neg logit contributions
 lifetime-0.040
ups-0.040
lands-0.039
yard-0.039
nuts-0.037
Token three
Token ID1115
Feature activation-2.95e+00

Pos logit contributions
 tant+0.009
 laughs+0.009
 scares+0.008
 cry+0.008
 bang+0.008
Neg logit contributions
ups-0.008
 lifetime-0.008
yard-0.007
lands-0.007
 next-0.007
Token years
Token ID812
Feature activation-4.40e-01

Pos logit contributions
 tant+0.096
 laughs+0.095
 scares+0.092
 bang+0.090
 shock+0.089
Neg logit contributions
ups-0.046
 next-0.040
 lifetime-0.038
lands-0.038
ocular-0.036
Token old
Token ID1468
Feature activation-1.89e+00

Pos logit contributions
 tant+0.011
 laughs+0.011
 cry+0.009
 scares+0.009
 bang+0.009
Neg logit contributions
 lifetime-0.011
ups-0.010
lands-0.010
lor-0.010
nuts-0.010
Token,
Token ID11
Feature activation+1.43e-02

Pos logit contributions
 tant+0.043
 laughs+0.043
 scares+0.038
 bang+0.037
 cry+0.036
Neg logit contributions
ups-0.047
 lifetime-0.047
lands-0.046
yard-0.046
 next-0.044
Token and
Token ID290
Feature activation-1.48e+00

Pos logit contributions
ups+0.000
 lifetime+0.000
lands+0.000
yard+0.000
ider+0.000
Neg logit contributions
 laughs-0.000
 tant-0.000
 scares-0.000
 cry-0.000
 bang-0.000
Token she
Token ID673
Feature activation-7.06e-01

Pos logit contributions
 tant+0.047
 laughs+0.047
 scares+0.042
 bang+0.042
 cry+0.041
Neg logit contributions
 lifetime-0.024
ups-0.024
yard-0.023
lands-0.023
 next-0.022