TOP ACTIVATIONS
MAX = 0.179

. Her mom always said Mell ie was a " s
so surprised and couldn 't believe it . He said ,
the tide ." Carl thought for a moment .
very special toy for L ott ie . It was a
. When D ott ie arrived at the lab
oven . P enny and her mom my
just begun ! <|endoftext|> F inn was fishing with his dad
was seeing . P olly wanted to find out
. " C leaning the sheep is fun !"
and started leaping around ! Mell ie covered her eyes and
gun ! He couldn 't believe his eyes . He had
so cool and couldn 't believe what he had found .
believe it ! P apa explained that the coal
Weight : 15 kilograms . Average for age : 3 years
full of colourful things . Among them , there was a
happy ! She couldn 't believe she was getting candy in
invitation , she couldn 't believe how excited Tommy was .
was ! She couldn 't believe how different it was from
! The mouse couldn 't believe it ! The young boy
said goodbye and promised to believe in the magic of the

MIN ACTIVATIONS
MIN = -0.237

s pretend to be aer opl anes , â Jack
my all about the aer opl ane he saw and how
the sky . The aer opl ane makes a loud noise
opl ane . The aer opl ane was very generous .
like . Although the aer opl ane was a pretty sight
L ily watched the aer opl ane until it disappeared .
ily saw her broken aer opl ane and cried . She
The children loved the aer opl ane very much .
. She loved her aer opl ane and now it was
there was a big aer opl ane . The aer opl
, that is our aer opl ane , give it back
, Lily saw many aer opl anes parked outside . Her
They take the aer opl ane to the park .
laugh and throw the aer opl ane in the sky .
One day , the aer opl ane saw a little girl
help you paint the aer opl ane ?" Tim said ,
began flying around making aer opl ane noises . Jack soon
there was a humble aer opl ane . He lived on
, look ! An aer opl ane !" Her
saw Lily with his aer opl ane . He was not

INTERVAL 0.075 - 0.179
CONTAINS 1.097%

are twins ? You look very unique . Do you want
have fun . <|endoftext|> L ily and Sam were twins who
bumped into a table and knocked over a v ase .
the butterfly . They felt very bad for what they did
of hugs . Everyone was very happy to see how brave

INTERVAL -0.029 - 0.075
CONTAINS 86.487%

re ind eer laughs and n uzz les them . He
had lots of shiny tables and knew gadgets everywhere . She
'd moved far away from his old house . With his
When he reached a clearing in the forest , he saw
he snapped and bark ed . One day his dad gave

INTERVAL -0.133 - -0.029
CONTAINS 12.404%

, a lonely bird was flying in the sky . The
Mom , the bird ate my fry ! â
They chose to explore the land together . They wanted to
pretty her hair looked . She felt happy and proud that
store and buy some jam ? It is not far .

INTERVAL -0.237 - -0.133
CONTAINS 0.012%

Wh isk ers . Wh isk ers liked to imagine that
, still in his p aj amas . Everyone in town
small , has a bus hy tail , and likes to
a friendly cat named Wh isk ers . Wh isk ers
drawer to get her cr ay ons , but she saw
Token.
Token ID13
Feature activation+2.50e-03

Pos logit contributions
arp+0.033
 cubes+0.032
 island+0.029
 bulbs+0.027
 cube+0.026
Neg logit contributions
severe-0.056
 Deal-0.055
 amaz-0.055
adays-0.054
 grin-0.053
Token Her
Token ID2332
Feature activation+5.43e-02

Pos logit contributions
arp+0.004
 island+0.004
 cubes+0.004
 bulbs+0.004
place+0.004
Neg logit contributions
 grin-0.003
 amaz-0.003
severe-0.003
 Deal-0.003
opl-0.003
Token mom
Token ID1995
Feature activation+2.65e-02

Pos logit contributions
 cubes+0.048
 cube+0.044
 island+0.040
arp+0.040
 collections+0.040
Neg logit contributions
severe-0.114
opl-0.111
oled-0.109
istent-0.109
used-0.105
Token always
Token ID1464
Feature activation+7.51e-03

Pos logit contributions
 cubes+0.020
arp+0.019
 island+0.019
 bulbs+0.017
 cube+0.016
Neg logit contributions
 Deal-0.060
 amaz-0.057
severe-0.057
opl-0.056
adays-0.055
Token said
Token ID531
Feature activation-5.00e-03

Pos logit contributions
 cubes+0.006
 island+0.005
 cube+0.005
 ship+0.005
arp+0.004
Neg logit contributions
 Deal-0.016
adays-0.016
opl-0.016
severe-0.015
 amaz-0.015
Token Mell
Token ID32993
Feature activation+1.55e-01

Pos logit contributions
opl+0.011
 Deal+0.011
severe+0.010
 amaz+0.009
used+0.009
Neg logit contributions
 cubes-0.005
 bulbs-0.005
 boats-0.004
 crystals-0.004
 shells-0.004
Tokenie
Token ID494
Feature activation+1.18e-02

Pos logit contributions
arp+0.129
 island+0.108
 cubes+0.102
place+0.088
 bulbs+0.087
Neg logit contributions
 amaz-0.317
 grin-0.316
 Deal-0.313
opl-0.310
severe-0.310
Token was
Token ID373
Feature activation-3.98e-03

Pos logit contributions
 bulbs+0.013
arp+0.013
 cubes+0.012
 island+0.012
 creatures+0.011
Neg logit contributions
 Deal-0.024
 amaz-0.022
severe-0.022
opl-0.022
 grin-0.021
Token a
Token ID257
Feature activation-2.19e-03

Pos logit contributions
 amaz+0.007
severe+0.007
adays+0.007
opl+0.007
 grin+0.007
Neg logit contributions
 cubes-0.005
 bulbs-0.004
 island-0.004
 creatures-0.004
 boats-0.004
Token "
Token ID366
Feature activation+2.93e-02

Pos logit contributions
opl+0.003
severe+0.003
adays+0.003
 Deal+0.003
 amaz+0.003
Neg logit contributions
arp-0.003
 island-0.003
 cubes-0.003
 bulbs-0.002
place-0.002
Tokens
Token ID82
Feature activation+4.11e-03

Pos logit contributions
arp+0.037
 cubes+0.031
place+0.030
 island+0.029
 bulbs+0.028
Neg logit contributions
 amaz-0.052
 Deal-0.051
 grin-0.051
adays-0.049
 thank-0.049
Token so
Token ID523
Feature activation+9.13e-02

Pos logit contributions
 island+0.069
 underground+0.065
 cubes+0.063
 creatures+0.057
 bulbs+0.057
Neg logit contributions
adays-0.131
oled-0.130
severe-0.125
opl-0.124
Aud-0.123
Token surprised
Token ID6655
Feature activation+4.30e-02

Pos logit contributions
 cubes+0.072
 organized+0.070
 cube+0.065
 pans+0.061
 creatures+0.061
Neg logit contributions
severe-0.197
hered-0.195
oled-0.188
Aud-0.187
opl-0.186
Token and
Token ID290
Feature activation+5.63e-02

Pos logit contributions
arp+0.055
 island+0.054
 cubes+0.050
place+0.047
 bulbs+0.046
Neg logit contributions
 Deal-0.077
severe-0.073
opl-0.071
Aud-0.070
oled-0.069
Token couldn
Token ID3521
Feature activation+1.18e-02

Pos logit contributions
 island+0.049
 creatures+0.046
 pans+0.044
 ships+0.043
 f+0.043
Neg logit contributions
opl-0.120
 Deal-0.112
hered-0.106
oled-0.106
severe-0.106
Token't
Token ID470
Feature activation+3.56e-02

Pos logit contributions
arp+0.012
guard+0.010
place+0.010
 bulb+0.010
Tim+0.009
Neg logit contributions
 amaz-0.024
 Majesty-0.022
 grin-0.020
 reflex-0.020
 Deal-0.020
Token believe
Token ID1975
Feature activation+1.53e-01

Pos logit contributions
 island+0.050
arp+0.049
place+0.045
 cubes+0.041
 bulbs+0.040
Neg logit contributions
opl-0.055
Aud-0.054
 Deal-0.054
oled-0.053
severe-0.052
Token it
Token ID340
Feature activation+5.95e-02

Pos logit contributions
arp+0.244
 island+0.231
 cubes+0.227
 bulbs+0.212
place+0.203
Neg logit contributions
 Deal-0.202
severe-0.197
opl-0.196
 grin-0.191
Aud-0.190
Token.
Token ID13
Feature activation+3.85e-02

Pos logit contributions
 island+0.052
arp+0.048
place+0.045
 bulbs+0.043
 creatures+0.041
Neg logit contributions
 Deal-0.127
severe-0.123
opl-0.122
 grin-0.121
icks-0.119
Token He
Token ID679
Feature activation+1.44e-02

Pos logit contributions
arp+0.051
 cubes+0.048
 bulbs+0.044
 island+0.044
Tim+0.043
Neg logit contributions
severe-0.056
opl-0.055
icks-0.053
 grin-0.053
 amaz-0.052
Token said
Token ID531
Feature activation+5.68e-03

Pos logit contributions
 island+0.013
arp+0.011
 cubes+0.010
 ship+0.010
place+0.009
Neg logit contributions
opl-0.032
 Deal-0.032
severe-0.029
oled-0.028
icks-0.028
Token,
Token ID11
Feature activation+1.42e-02

Pos logit contributions
 cubes+0.006
 island+0.006
 cube+0.006
 shells+0.005
 bulbs+0.005
Neg logit contributions
opl-0.012
 Deal-0.012
istent-0.010
Aud-0.010
severe-0.010
Token the
Token ID262
Feature activation+5.68e-02

Pos logit contributions
 island+0.108
 cubes+0.107
 crystals+0.100
 creatures+0.099
 bulbs+0.097
Neg logit contributions
 Deal-0.180
severe-0.180
oled-0.178
istent-0.175
ung-0.168
Token tide
Token ID20013
Feature activation+6.20e-02

Pos logit contributions
 island+0.063
arp+0.056
 cubes+0.054
 bulbs+0.052
place+0.051
Neg logit contributions
 Deal-0.111
oled-0.111
istent-0.109
icks-0.109
severe-0.108
Token."
Token ID526
Feature activation-3.38e-03

Pos logit contributions
 island+0.066
 cubes+0.055
arp+0.053
place+0.052
 ship+0.050
Neg logit contributions
 Deal-0.142
severe-0.124
 amaz-0.120
Aud-0.117
icks-0.113
Token
Token ID198
Feature activation+3.56e-02

Pos logit contributions
 amaz+0.005
severe+0.005
opl+0.005
istent+0.005
icks+0.005
Neg logit contributions
arp-0.004
 cubes-0.004
 island-0.004
Tim-0.003
 bulbs-0.003
Token
Token ID198
Feature activation+2.69e-02

Pos logit contributions
arp+0.057
 island+0.050
 cubes+0.049
place+0.047
 bulbs+0.046
Neg logit contributions
 amaz-0.047
 grin-0.047
severe-0.047
adays-0.045
istent-0.044
TokenCarl
Token ID26886
Feature activation+1.50e-01

Pos logit contributions
arp+0.032
 island+0.028
 cubes+0.027
place+0.025
 bulbs+0.025
Neg logit contributions
 amaz-0.046
 grin-0.046
severe-0.045
opl-0.045
 Deal-0.045
Token thought
Token ID1807
Feature activation+4.53e-02

Pos logit contributions
 island+0.119
arp+0.117
 cubes+0.111
 cube+0.103
 f+0.094
Neg logit contributions
 Deal-0.304
Aud-0.296
opl-0.295
severe-0.286
 Paw-0.274
Token for
Token ID329
Feature activation-1.75e-02

Pos logit contributions
 cubes+0.052
 island+0.047
arp+0.047
 pipes+0.045
 bulbs+0.043
Neg logit contributions
opl-0.080
severe-0.079
 Deal-0.079
 amaz-0.077
Aud-0.076
Token a
Token ID257
Feature activation+8.66e-03

Pos logit contributions
 grin+0.016
opl+0.016
 amaz+0.016
 Deal+0.016
severe+0.015
Neg logit contributions
arp-0.035
 island-0.033
 cubes-0.032
place-0.031
 bulbs-0.031
Token moment
Token ID2589
Feature activation+3.68e-02

Pos logit contributions
arp+0.008
 island+0.007
 cubes+0.007
place+0.006
 bulbs+0.006
Neg logit contributions
opl-0.017
 amaz-0.017
 Deal-0.016
 grin-0.016
severe-0.016
Token.
Token ID13
Feature activation+2.95e-02

Pos logit contributions
 island+0.039
arp+0.038
 cubes+0.035
place+0.033
 bulbs+0.031
Neg logit contributions
severe-0.068
 Deal-0.068
opl-0.065
 Majesty-0.065
adays-0.064
Token very
Token ID845
Feature activation+8.73e-02

Pos logit contributions
opl+0.004
 Deal+0.004
severe+0.004
adays+0.004
istent+0.004
Neg logit contributions
arp-0.003
 island-0.003
 cubes-0.003
place-0.003
 bulbs-0.003
Token special
Token ID2041
Feature activation+2.09e-02

Pos logit contributions
arp+0.103
 island+0.096
 cubes+0.096
place+0.089
 bulbs+0.083
Neg logit contributions
severe-0.151
opl-0.151
oled-0.151
 Deal-0.148
 amaz-0.148
Token toy
Token ID13373
Feature activation+2.43e-02

Pos logit contributions
arp+0.027
 island+0.026
 cubes+0.025
 bulbs+0.023
place+0.023
Neg logit contributions
 Deal-0.034
severe-0.033
adays-0.033
opl-0.033
oled-0.033
Token for
Token ID329
Feature activation-4.01e-02

Pos logit contributions
arp+0.038
 island+0.035
 cubes+0.034
 bulbs+0.032
place+0.032
Neg logit contributions
 grin-0.032
 amaz-0.032
 Deal-0.031
 thank-0.031
opl-0.031
Token L
Token ID406
Feature activation+1.11e-02

Pos logit contributions
severe+0.056
 grin+0.056
 Deal+0.055
 amaz+0.055
opl+0.055
Neg logit contributions
arp-0.060
 cubes-0.060
 island-0.059
 bulbs-0.056
place-0.054
Tokenott
Token ID1252
Feature activation+1.49e-01

Pos logit contributions
arp+0.012
 island+0.012
 jackets+0.010
 cubes+0.009
place+0.009
Neg logit contributions
oled-0.019
 grin-0.018
opl-0.018
 amaz-0.018
 Once-0.018
Tokenie
Token ID494
Feature activation+1.74e-02

Pos logit contributions
arp+0.145
 island+0.129
 cubes+0.123
place+0.112
 bulbs+0.110
Neg logit contributions
opl-0.280
 grin-0.267
severe-0.263
 amaz-0.262
 Deal-0.261
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
arp+0.020
 island+0.018
 cubes+0.018
place+0.017
 bulbs+0.016
Neg logit contributions
 Deal-0.033
 amaz-0.032
severe-0.031
 grin-0.031
opl-0.031
Token It
Token ID632
Feature activation+3.95e-02

Pos logit contributions
arp+0.037
 cubes+0.034
 bulbs+0.032
 island+0.032
 pipes+0.031
Neg logit contributions
opl-0.023
 grin-0.022
 Deal-0.022
 amaz-0.021
severe-0.021
Token was
Token ID373
Feature activation+3.90e-04

Pos logit contributions
arp+0.032
 island+0.030
 bulbs+0.028
 cubes+0.026
place+0.023
Neg logit contributions
 Deal-0.091
severe-0.086
opl-0.085
 amaz-0.083
 grin-0.082
Token a
Token ID257
Feature activation+2.88e-05

Pos logit contributions
 cubes+0.000
 bulbs+0.000
 island+0.000
 crystals+0.000
arp+0.000
Neg logit contributions
severe-0.001
used-0.001
 Deal-0.001
opl-0.001
istent-0.001
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 Deal+0.004
severe+0.004
 grin+0.004
 amaz+0.004
opl+0.004
Neg logit contributions
 island-0.003
arp-0.003
place-0.003
 cubes-0.003
 bulbs-0.003
Token
Token ID198
Feature activation+5.93e-05

Pos logit contributions
arp+0.022
 island+0.020
 cubes+0.019
 bulbs+0.018
place+0.018
Neg logit contributions
 amaz-0.014
 grin-0.014
opl-0.013
severe-0.013
 Deal-0.013
Token
Token ID198
Feature activation+2.79e-03

Pos logit contributions
arp+0.000
 island+0.000
 cubes+0.000
 bulbs+0.000
place+0.000
Neg logit contributions
 grin-0.000
 Once-0.000
 amaz-0.000
 Deal-0.000
 Immediately-0.000
TokenWhen
Token ID2215
Feature activation-2.70e-02

Pos logit contributions
arp+0.005
 island+0.005
 cubes+0.004
 bulbs+0.004
 crystals+0.004
Neg logit contributions
 Once-0.003
adays-0.003
 Immediately-0.003
oled-0.003
Aud-0.003
Token D
Token ID360
Feature activation+1.09e-02

Pos logit contributions
 thank+0.024
 bye+0.023
adays+0.022
 Once+0.022
 Mitt+0.022
Neg logit contributions
arp-0.057
 island-0.052
 cubes-0.051
place-0.050
 bulbs-0.048
Tokenott
Token ID1252
Feature activation+1.49e-01

Pos logit contributions
 island+0.011
arp+0.010
 cubes+0.009
 jackets+0.008
 bulbs+0.008
Neg logit contributions
opl-0.020
 grin-0.020
 Once-0.019
 amaz-0.019
 Deal-0.019
Tokenie
Token ID494
Feature activation+2.02e-02

Pos logit contributions
arp+0.156
 cubes+0.137
 island+0.136
place+0.128
 bulbs+0.124
Neg logit contributions
opl-0.270
 amaz-0.252
severe-0.250
 grin-0.249
zing-0.248
Token arrived
Token ID5284
Feature activation+3.46e-02

Pos logit contributions
 island+0.025
arp+0.024
place+0.022
 ship+0.019
 cubes+0.019
Neg logit contributions
 Deal-0.037
opl-0.034
 grin-0.034
 amaz-0.034
severe-0.034
Token at
Token ID379
Feature activation+1.35e-03

Pos logit contributions
arp+0.060
 island+0.057
 cubes+0.057
 bulbs+0.053
place+0.052
Neg logit contributions
opl-0.041
 amaz-0.040
 Deal-0.040
severe-0.038
 grin-0.038
Token the
Token ID262
Feature activation+1.49e-02

Pos logit contributions
arp+0.002
 island+0.002
 cubes+0.002
 bulbs+0.002
place+0.002
Neg logit contributions
 grin-0.002
istent-0.002
 Deal-0.002
oled-0.002
severe-0.002
Token lab
Token ID2248
Feature activation+2.53e-02

Pos logit contributions
arp+0.020
 cubes+0.018
 island+0.018
 bulbs+0.017
place+0.015
Neg logit contributions
 amaz-0.023
 Deal-0.023
 thank-0.022
opl-0.022
 grin-0.022
Token oven
Token ID14361
Feature activation-3.73e-02

Pos logit contributions
arp+0.024
 island+0.022
 cubes+0.021
 bulbs+0.020
place+0.019
Neg logit contributions
 amaz-0.022
 grin-0.022
severe-0.021
 Deal-0.021
opl-0.021
Token.
Token ID13
Feature activation+2.95e-02

Pos logit contributions
 Deal+0.078
severe+0.077
 grin+0.075
Aud+0.075
opl+0.075
Neg logit contributions
arp-0.034
 island-0.033
 cubes-0.030
place-0.026
 bulbs-0.026
Token
Token ID220
Feature activation-8.13e-03

Pos logit contributions
arp+0.054
 island+0.049
 cubes+0.049
 bulbs+0.047
place+0.045
Neg logit contributions
opl-0.032
 amaz-0.030
 grin-0.030
severe-0.028
 Deal-0.028
Token
Token ID198
Feature activation+2.47e-02

Pos logit contributions
 amaz+0.014
 grin+0.014
severe+0.014
 bye+0.013
opl+0.013
Neg logit contributions
arp-0.010
 cubes-0.008
 bulbs-0.008
place-0.007
leaning-0.007
Token
Token ID198
Feature activation+2.42e-02

Pos logit contributions
arp+0.045
 island+0.042
 cubes+0.041
 bulbs+0.039
place+0.039
Neg logit contributions
 amaz-0.027
 grin-0.026
 Deal-0.025
opl-0.025
severe-0.025
TokenP
Token ID47
Feature activation+1.48e-01

Pos logit contributions
arp+0.038
 island+0.037
 cubes+0.036
 bulbs+0.033
place+0.031
Neg logit contributions
adays-0.033
 Deal-0.033
severe-0.032
oled-0.032
 Immediately-0.032
Tokenenny
Token ID11870
Feature activation+4.90e-02

Pos logit contributions
arp+0.230
 island+0.202
 cubes+0.200
place+0.197
 bulbs+0.185
Neg logit contributions
 amaz-0.202
 grin-0.201
opl-0.199
 Deal-0.189
 thank-0.188
Token and
Token ID290
Feature activation+2.27e-02

Pos logit contributions
arp+0.061
 island+0.057
 cubes+0.053
 bulbs+0.049
place+0.048
Neg logit contributions
 Deal-0.084
opl-0.083
severe-0.081
 amaz-0.081
 grin-0.078
Token her
Token ID607
Feature activation+2.62e-02

Pos logit contributions
arp+0.043
 island+0.040
 cubes+0.040
 bulbs+0.038
place+0.037
Neg logit contributions
 amaz-0.022
opl-0.022
 grin-0.022
 Deal-0.022
severe-0.021
Token mom
Token ID1995
Feature activation+4.49e-02

Pos logit contributions
arp+0.041
 island+0.037
 cubes+0.037
 bulbs+0.034
place+0.034
Neg logit contributions
 amaz-0.036
 grin-0.035
severe-0.035
 Deal-0.035
opl-0.035
Tokenmy
Token ID1820
Feature activation-3.82e-02

Pos logit contributions
arp+0.069
 island+0.062
 cubes+0.061
 bulbs+0.057
place+0.057
Neg logit contributions
 amaz-0.062
 grin-0.062
 Deal-0.061
severe-0.059
opl-0.059
Token just
Token ID655
Feature activation+4.46e-02

Pos logit contributions
place+0.099
 island+0.099
 treasures+0.095
 creatures+0.094
 bulbs+0.091
Neg logit contributions
 Deal-0.163
oled-0.147
opl-0.146
istent-0.145
severe-0.140
Token begun
Token ID9258
Feature activation+2.87e-02

Pos logit contributions
 island+0.052
place+0.051
 creatures+0.049
 treasures+0.047
 shells+0.046
Neg logit contributions
oled-0.080
 Deal-0.080
Aud-0.077
Sean-0.073
istent-0.070
Token!
Token ID0
Feature activation-5.13e-04

Pos logit contributions
 bulbs+0.028
 island+0.028
 creatures+0.027
place+0.027
 treasures+0.026
Neg logit contributions
 Deal-0.060
oled-0.058
istent-0.054
 grin-0.054
opl-0.054
Token<|endoftext|>
Token ID50256
Feature activation+8.36e-02

Pos logit contributions
 grin+0.001
oled+0.001
severe+0.001
 amaz+0.001
istent+0.001
Neg logit contributions
arp-0.000
 island-0.000
B-0.000
 bulbs-0.000
ney-0.000
TokenF
Token ID37
Feature activation+3.94e-02

Pos logit contributions
arp+0.090
 island+0.080
 cubes+0.079
 bulbs+0.071
place+0.068
Neg logit contributions
 amaz-0.151
severe-0.148
 grin-0.148
 Deal-0.147
istent-0.147
Tokeninn
Token ID3732
Feature activation+1.47e-01

Pos logit contributions
arp+0.046
 island+0.041
 cubes+0.038
place+0.036
 bulbs+0.035
Neg logit contributions
 amaz-0.069
 grin-0.067
severe-0.066
 Deal-0.066
Aud-0.065
Token was
Token ID373
Feature activation+7.01e-03

Pos logit contributions
arp+0.137
 island+0.129
 cubes+0.128
 bulbs+0.104
 pipes+0.098
Neg logit contributions
 Deal-0.313
 amaz-0.307
Aud-0.296
 grin-0.295
severe-0.290
Token fishing
Token ID12478
Feature activation+4.30e-02

Pos logit contributions
 underground+0.008
 island+0.007
 cubes+0.007
P+0.007
 bulbs+0.007
Neg logit contributions
adays-0.012
severe-0.012
 amaz-0.011
 grin-0.011
 thank-0.011
Token with
Token ID351
Feature activation+6.61e-03

Pos logit contributions
arp+0.051
 island+0.051
 cubes+0.050
place+0.046
 cube+0.041
Neg logit contributions
 Deal-0.078
 amaz-0.077
oled-0.075
Aud-0.075
 grin-0.075
Token his
Token ID465
Feature activation+4.22e-02

Pos logit contributions
 cubes+0.008
 shells+0.007
 island+0.007
 crystals+0.007
 boats+0.007
Neg logit contributions
oled-0.013
istent-0.013
severe-0.013
adays-0.012
 grin-0.012
Token dad
Token ID9955
Feature activation+2.09e-02

Pos logit contributions
 cubes+0.049
 island+0.045
arp+0.042
 cube+0.041
 boats+0.039
Neg logit contributions
oled-0.083
adays-0.080
severe-0.080
istent-0.079
opl-0.078
Token was
Token ID373
Feature activation+6.92e-02

Pos logit contributions
arp+0.032
 island+0.030
 cubes+0.029
place+0.028
 bulbs+0.028
Neg logit contributions
 amaz-0.020
 Deal-0.019
opl-0.019
Aud-0.018
severe-0.018
Token seeing
Token ID4379
Feature activation+8.28e-02

Pos logit contributions
 island+0.069
 underground+0.065
 cubes+0.063
 creatures+0.057
 bulbs+0.057
Neg logit contributions
adays-0.131
oled-0.130
severe-0.125
opl-0.124
Aud-0.123
Token.
Token ID13
Feature activation+6.66e-02

Pos logit contributions
 island+0.101
 cubes+0.096
 creatures+0.091
 shells+0.090
 bulbs+0.088
Neg logit contributions
 Deal-0.170
oled-0.157
severe-0.156
istent-0.156
Aud-0.152
Token
Token ID198
Feature activation+3.48e-02

Pos logit contributions
arp+0.081
 cubes+0.080
 bulbs+0.072
 island+0.071
Tim+0.071
Neg logit contributions
opl-0.098
severe-0.097
 amaz-0.094
 grin-0.094
zing-0.094
Token
Token ID198
Feature activation+2.23e-02

Pos logit contributions
arp+0.050
 cubes+0.043
 island+0.042
place+0.042
B+0.040
Neg logit contributions
 grin-0.051
severe-0.051
 amaz-0.050
adays-0.049
ishly-0.049
TokenP
Token ID47
Feature activation+1.47e-01

Pos logit contributions
arp+0.028
 cubes+0.024
 island+0.024
place+0.023
leaning+0.021
Neg logit contributions
 grin-0.037
 amaz-0.037
 thank-0.036
severe-0.035
opl-0.035
Tokenolly
Token ID5098
Feature activation+1.94e-02

Pos logit contributions
arp+0.192
 cubes+0.184
place+0.175
 island+0.167
 collections+0.162
Neg logit contributions
 amaz-0.221
severe-0.217
oled-0.216
opl-0.214
 grin-0.214
Token wanted
Token ID2227
Feature activation+2.73e-02

Pos logit contributions
 island+0.017
arp+0.014
 ship+0.013
 boy+0.013
 creatures+0.012
Neg logit contributions
opl-0.043
 Deal-0.041
severe-0.039
icks-0.038
upid-0.037
Token to
Token ID284
Feature activation+2.92e-02

Pos logit contributions
arp+0.031
 island+0.030
 cubes+0.030
place+0.028
 bulbs+0.027
Neg logit contributions
 Deal-0.050
opl-0.049
severe-0.049
oled-0.048
 grin-0.047
Token find
Token ID1064
Feature activation+7.13e-02

Pos logit contributions
 island+0.037
arp+0.035
place+0.034
 cubes+0.032
 cube+0.030
Neg logit contributions
oled-0.054
 Deal-0.047
Aud-0.046
severe-0.046
opl-0.046
Token out
Token ID503
Feature activation-2.90e-02

Pos logit contributions
arp+0.124
 island+0.115
 cubes+0.112
 bulbs+0.111
place+0.108
Neg logit contributions
 grin-0.089
oled-0.089
 Deal-0.087
opl-0.087
istent-0.086
Token.
Token ID13
Feature activation+2.85e-02

Pos logit contributions
 Deal+0.017
 amaz+0.017
 grin+0.016
Aud+0.016
severe+0.016
Neg logit contributions
arp-0.010
 cubes-0.009
 island-0.009
 bulbs-0.008
 pipes-0.008
Token
Token ID198
Feature activation+1.89e-02

Pos logit contributions
arp+0.043
 cubes+0.043
 island+0.039
place+0.037
leaning+0.036
Neg logit contributions
severe-0.037
 amaz-0.036
opl-0.036
 grin-0.035
used-0.034
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
arp+0.036
 island+0.033
 cubes+0.033
 bulbs+0.031
place+0.031
Neg logit contributions
 amaz-0.019
 grin-0.019
 Deal-0.018
severe-0.018
opl-0.018
Token"
Token ID1
Feature activation+2.33e-02

Pos logit contributions
arp+0.032
 island+0.029
 cubes+0.028
 bulbs+0.027
place+0.026
Neg logit contributions
 amaz-0.026
 grin-0.026
 Deal-0.025
severe-0.025
opl-0.025
TokenC
Token ID34
Feature activation+2.99e-02

Pos logit contributions
arp+0.034
 island+0.033
 cubes+0.029
 bulbs+0.029
 collections+0.028
Neg logit contributions
Aud-0.033
 Deal-0.033
 amaz-0.032
oled-0.032
adays-0.031
Tokenleaning
Token ID25909
Feature activation+1.47e-01

Pos logit contributions
 cubes+0.040
arp+0.038
 island+0.038
 bulbs+0.037
 crystals+0.036
Neg logit contributions
opl-0.043
severe-0.041
adays-0.040
Aud-0.039
istent-0.039
Token the
Token ID262
Feature activation+2.03e-02

Pos logit contributions
arp+0.234
 island+0.198
 cubes+0.198
 bulbs+0.195
 pipes+0.184
Neg logit contributions
 amaz-0.233
 grin-0.232
Aud-0.229
 Deal-0.228
oled-0.219
Token sheep
Token ID15900
Feature activation-6.29e-03

Pos logit contributions
arp+0.021
 island+0.019
 bulbs+0.016
 pipes+0.015
place+0.015
Neg logit contributions
 grin-0.042
 amaz-0.041
 Deal-0.040
adays-0.040
severe-0.040
Token is
Token ID318
Feature activation-2.68e-02

Pos logit contributions
 Deal+0.012
 amaz+0.012
Aud+0.012
 grin+0.012
severe+0.011
Neg logit contributions
arp-0.007
 island-0.007
 cubes-0.006
 bulbs-0.006
place-0.006
Token fun
Token ID1257
Feature activation+6.04e-02

Pos logit contributions
 amaz+0.042
 grin+0.042
 Deal+0.041
severe+0.041
opl+0.041
Neg logit contributions
arp-0.036
 cubes-0.033
 island-0.033
 bulbs-0.031
place-0.030
Token!"
Token ID2474
Feature activation-4.30e-02

Pos logit contributions
arp+0.106
 island+0.099
 cubes+0.097
 bulbs+0.092
place+0.091
Neg logit contributions
 amaz-0.071
 Deal-0.071
 grin-0.070
severe-0.069
opl-0.067
Token and
Token ID290
Feature activation+5.02e-03

Pos logit contributions
 island+0.021
arp+0.020
 cubes+0.018
 tunnel+0.015
 ship+0.015
Neg logit contributions
 Deal-0.051
severe-0.048
Aud-0.044
opl-0.043
 Majesty-0.042
Token started
Token ID2067
Feature activation+1.93e-02

Pos logit contributions
arp+0.005
 bulbs+0.005
 island+0.005
 creatures+0.005
 crystals+0.005
Neg logit contributions
opl-0.010
 Deal-0.010
urance-0.009
adays-0.009
istent-0.009
Token leaping
Token ID45583
Feature activation-6.32e-02

Pos logit contributions
 cubes+0.016
 pipes+0.016
 creatures+0.015
 f+0.014
 bulbs+0.014
Neg logit contributions
 Deal-0.042
opl-0.039
adays-0.039
severe-0.038
istent-0.037
Token around
Token ID1088
Feature activation+2.51e-03

Pos logit contributions
 Deal+0.135
opl+0.127
 Majesty+0.122
istent+0.121
 grin+0.118
Neg logit contributions
arp-0.064
 underground-0.055
 island-0.054
 tunnels-0.054
 bulbs-0.051
Token!
Token ID0
Feature activation-4.30e-02

Pos logit contributions
arp+0.003
 bulbs+0.003
 island+0.002
 creatures+0.002
 cubes+0.002
Neg logit contributions
 Deal-0.005
severe-0.005
opl-0.005
istent-0.005
 grin-0.005
Token Mell
Token ID32993
Feature activation+1.46e-01

Pos logit contributions
opl+0.062
Aud+0.055
severe+0.054
 Deal+0.052
 grin+0.052
Neg logit contributions
arp-0.066
 bulbs-0.062
 pipes-0.055
 crystals-0.054
 island-0.053
Tokenie
Token ID494
Feature activation+4.30e-03

Pos logit contributions
arp+0.141
 island+0.122
 cubes+0.121
place+0.103
 bulbs+0.097
Neg logit contributions
 grin-0.277
 amaz-0.277
adays-0.268
 Deal-0.267
oled-0.264
Token covered
Token ID5017
Feature activation+4.59e-02

Pos logit contributions
arp+0.003
 island+0.003
 creatures+0.002
 tunnel+0.002
B+0.002
Neg logit contributions
 Deal-0.010
opl-0.010
severe-0.009
Aud-0.009
 amaz-0.009
Token her
Token ID607
Feature activation+7.21e-03

Pos logit contributions
arp+0.068
 bulbs+0.066
 island+0.063
 cubes+0.060
 crystals+0.059
Neg logit contributions
opl-0.071
 Deal-0.069
severe-0.068
Aud-0.067
 grin-0.064
Token eyes
Token ID2951
Feature activation-3.02e-02

Pos logit contributions
 island+0.008
 cubes+0.007
 cube+0.007
arp+0.007
 tunnel+0.007
Neg logit contributions
oled-0.013
Aud-0.013
opl-0.013
severe-0.013
 Deal-0.013
Token and
Token ID290
Feature activation+1.10e-02

Pos logit contributions
 Deal+0.075
 Majesty+0.069
opl+0.066
 majesty+0.062
 Jeffrey+0.062
Neg logit contributions
 island-0.019
arp-0.018
 underground-0.016
 cubes-0.016
 in-0.015
Token gun
Token ID2485
Feature activation+3.86e-02

Pos logit contributions
arp+0.043
 cubes+0.041
 island+0.037
 bulbs+0.037
 pipes+0.034
Neg logit contributions
 Deal-0.076
 grin-0.070
severe-0.069
oled-0.069
used-0.069
Token!
Token ID0
Feature activation-1.63e-03

Pos logit contributions
 island+0.040
arp+0.040
 cubes+0.037
 ship+0.035
place+0.033
Neg logit contributions
 Deal-0.080
 amaz-0.079
Aud-0.072
 grin-0.071
 delight-0.070
Token He
Token ID679
Feature activation+2.90e-02

Pos logit contributions
 amaz+0.002
Aud+0.002
 grin+0.002
zing+0.002
opl+0.002
Neg logit contributions
arp-0.002
 cubes-0.002
Tim-0.002
 cube-0.002
 island-0.002
Token couldn
Token ID3521
Feature activation+7.29e-03

Pos logit contributions
 island+0.025
 ship+0.023
 ships+0.021
 boats+0.019
arp+0.019
Neg logit contributions
 Deal-0.064
Aud-0.059
opl-0.059
-0.057
oled-0.056
Token't
Token ID470
Feature activation+3.10e-02

Pos logit contributions
arp+0.008
guard+0.007
place+0.007
 cube+0.007
Tim+0.007
Neg logit contributions
 amaz-0.015
 Majesty-0.013
 Deal-0.013
 grin-0.013
 fascination-0.012
Token believe
Token ID1975
Feature activation+1.46e-01

Pos logit contributions
arp+0.053
 island+0.050
 cubes+0.047
place+0.045
 bulbs+0.044
Neg logit contributions
 amaz-0.038
 Deal-0.037
 grin-0.037
opl-0.036
severe-0.036
Token his
Token ID465
Feature activation+4.96e-02

Pos logit contributions
arp+0.224
 island+0.214
 cubes+0.212
 bulbs+0.192
 crystals+0.187
Neg logit contributions
 Deal-0.206
severe-0.197
opl-0.197
Aud-0.196
 grin-0.192
Token eyes
Token ID2951
Feature activation-1.54e-02

Pos logit contributions
 island+0.070
arp+0.069
 cubes+0.067
 ship+0.062
 anchor+0.061
Neg logit contributions
Aud-0.085
oled-0.083
 Ashley-0.076
 Immediately-0.074
 Heidi-0.073
Token.
Token ID13
Feature activation+3.10e-02

Pos logit contributions
 Deal+0.036
Aud+0.031
 Majesty+0.029
 Elizabeth+0.029
Sean+0.029
Neg logit contributions
 island-0.015
arp-0.012
 cubes-0.011
 underground-0.011
place-0.011
Token He
Token ID679
Feature activation+6.16e-03

Pos logit contributions
arp+0.038
 cubes+0.036
 island+0.032
 bulbs+0.032
Tim+0.031
Neg logit contributions
severe-0.047
 grin-0.047
 amaz-0.046
Aud-0.046
icks-0.045
Token had
Token ID550
Feature activation+5.52e-02

Pos logit contributions
 island+0.006
 ship+0.004
arp+0.004
 ships+0.004
 boats+0.003
Neg logit contributions
 Deal-0.014
opl-0.013
Aud-0.013
severe-0.012
icks-0.012
Token so
Token ID523
Feature activation+9.13e-02

Pos logit contributions
 island+0.069
 underground+0.065
 cubes+0.063
 creatures+0.057
 bulbs+0.057
Neg logit contributions
adays-0.131
oled-0.130
severe-0.125
opl-0.124
Aud-0.123
Token cool
Token ID3608
Feature activation+6.40e-02

Pos logit contributions
 cubes+0.072
 organized+0.070
 cube+0.065
 pans+0.061
 creatures+0.061
Neg logit contributions
severe-0.197
hered-0.195
oled-0.188
Aud-0.187
opl-0.186
Token and
Token ID290
Feature activation+5.11e-02

Pos logit contributions
 island+0.082
arp+0.077
 cubes+0.072
 bulbs+0.064
 creatures+0.064
Neg logit contributions
 Deal-0.127
severe-0.109
 amaz-0.108
opl-0.107
icks-0.106
Token couldn
Token ID3521
Feature activation+4.56e-03

Pos logit contributions
 island+0.047
 cubes+0.047
 creatures+0.045
 shells+0.044
 treasures+0.042
Neg logit contributions
 Deal-0.108
severe-0.103
oled-0.103
opl-0.102
hered-0.099
Token't
Token ID470
Feature activation+3.11e-02

Pos logit contributions
arp+0.005
place+0.004
guard+0.004
 island+0.004
 bulb+0.004
Neg logit contributions
 amaz-0.009
 Deal-0.008
 Majesty-0.008
 grin-0.008
 reflex-0.007
Token believe
Token ID1975
Feature activation+1.46e-01

Pos logit contributions
arp+0.044
 island+0.044
place+0.039
 cubes+0.037
 bulbs+0.036
Neg logit contributions
 Deal-0.047
 amaz-0.046
Aud-0.046
opl-0.046
oled-0.046
Token what
Token ID644
Feature activation+6.05e-02

Pos logit contributions
arp+0.227
 island+0.216
 cubes+0.212
 bulbs+0.197
 crystals+0.189
Neg logit contributions
 Deal-0.200
severe-0.195
opl-0.194
 grin-0.189
Aud-0.188
Token he
Token ID339
Feature activation+1.57e-02

Pos logit contributions
 cubes+0.072
 island+0.071
 bulbs+0.066
place+0.066
 crystals+0.065
Neg logit contributions
 Deal-0.109
severe-0.107
opl-0.106
oled-0.101
istent-0.101
Token had
Token ID550
Feature activation+5.93e-02

Pos logit contributions
 island+0.012
arp+0.010
place+0.010
 cubes+0.008
 ship+0.007
Neg logit contributions
 Deal-0.036
opl-0.035
severe-0.035
adays-0.034
icks-0.033
Token found
Token ID1043
Feature activation+6.59e-02

Pos logit contributions
 island+0.068
arp+0.065
 cubes+0.063
place+0.057
 collections+0.053
Neg logit contributions
 Deal-0.111
severe-0.104
 grin-0.102
opl-0.101
Aud-0.100
Token.
Token ID13
Feature activation+3.47e-02

Pos logit contributions
 island+0.067
arp+0.067
 cubes+0.063
place+0.059
 crystals+0.054
Neg logit contributions
 Deal-0.141
severe-0.130
Aud-0.129
 grin-0.126
istent-0.122
Token believe
Token ID1975
Feature activation+1.78e-01

Pos logit contributions
 island+0.100
arp+0.098
place+0.090
 cubes+0.084
 bulbs+0.082
Neg logit contributions
 Deal-0.098
 amaz-0.097
oled-0.095
Aud-0.095
adays-0.091
Token it
Token ID340
Feature activation+6.84e-02

Pos logit contributions
arp+0.256
 island+0.253
 cubes+0.248
 bulbs+0.229
 crystals+0.222
Neg logit contributions
 Deal-0.254
severe-0.249
opl-0.246
 amaz-0.242
oled-0.239
Token!
Token ID0
Feature activation-1.35e-03

Pos logit contributions
 island+0.054
place+0.045
 creatures+0.040
arp+0.039
 bulbs+0.037
Neg logit contributions
 Deal-0.157
icks-0.148
Aud-0.147
opl-0.145
severe-0.144
Token
Token ID198
Feature activation+3.75e-02

Pos logit contributions
opl+0.002
severe+0.002
 amaz+0.002
 grin+0.002
zing+0.002
Neg logit contributions
arp-0.002
 bulbs-0.002
 cubes-0.002
 island-0.001
Tim-0.001
Token
Token ID198
Feature activation+2.89e-02

Pos logit contributions
arp+0.054
 island+0.046
place+0.045
 cubes+0.045
B+0.041
Neg logit contributions
severe-0.056
 amaz-0.055
 grin-0.055
adays-0.053
 Deal-0.053
TokenP
Token ID47
Feature activation+1.45e-01

Pos logit contributions
arp+0.035
 island+0.030
place+0.029
 cubes+0.028
B+0.026
Neg logit contributions
 grin-0.049
 amaz-0.049
 thank-0.048
severe-0.048
icks-0.048
Tokenapa
Token ID32678
Feature activation-8.17e-03

Pos logit contributions
arp+0.211
place+0.197
 cubes+0.196
 island+0.192
 collections+0.181
Neg logit contributions
 amaz-0.200
severe-0.196
oled-0.195
opl-0.193
 grin-0.192
Token explained
Token ID4893
Feature activation+2.53e-02

Pos logit contributions
 Deal+0.017
opl+0.016
 amaz+0.016
severe+0.016
Aud+0.015
Neg logit contributions
 island-0.008
arp-0.006
 ship-0.006
 cubes-0.006
 boy-0.006
Token that
Token ID326
Feature activation+9.34e-03

Pos logit contributions
 cubes+0.024
arp+0.023
 island+0.022
 pipes+0.020
 bulbs+0.020
Neg logit contributions
opl-0.056
 Deal-0.056
Aud-0.049
-0.049
 la-0.048
Token the
Token ID262
Feature activation+9.07e-03

Pos logit contributions
 cubes+0.011
 island+0.011
 bulbs+0.010
 crystals+0.010
 creatures+0.010
Neg logit contributions
 Deal-0.018
Aud-0.017
opl-0.017
 grin-0.017
severe-0.017
Token coal
Token ID5655
Feature activation+4.73e-02

Pos logit contributions
 island+0.010
arp+0.010
 cubes+0.010
 bulbs+0.009
place+0.009
Neg logit contributions
oled-0.016
 Deal-0.016
opl-0.016
Aud-0.016
istent-0.016
Token Weight
Token ID14331
Feature activation+4.79e-02

Pos logit contributions
arp+0.023
 bulbs+0.021
 cubes+0.020
 pipes+0.019
place+0.019
Neg logit contributions
 grin-0.020
 amaz-0.018
Aud-0.018
oled-0.018
zing-0.018
Token:
Token ID25
Feature activation+1.02e-01

Pos logit contributions
 bulbs+0.060
 cubes+0.057
arp+0.057
works+0.056
 pipes+0.055
Neg logit contributions
 grin-0.087
 amaz-0.085
 Deal-0.083
Aud-0.081
oled-0.077
Token 15
Token ID1315
Feature activation+4.55e-03

Pos logit contributions
 bulbs+0.134
 pipes+0.133
 cubes+0.129
arp+0.125
 cells+0.121
Neg logit contributions
 grin-0.170
hered-0.167
oled-0.162
ishly-0.156
Aud-0.153
Token kilograms
Token ID37075
Feature activation+4.56e-03

Pos logit contributions
 cubes+0.006
 bulbs+0.005
place+0.005
 island+0.005
arp+0.005
Neg logit contributions
severe-0.008
ishly-0.008
Aud-0.007
 Deal-0.007
 grin-0.007
Token.
Token ID13
Feature activation+5.50e-03

Pos logit contributions
 cubes+0.006
arp+0.006
place+0.005
 island+0.005
 pipes+0.005
Neg logit contributions
 amaz-0.008
 grin-0.008
ishly-0.008
Aud-0.008
 Deal-0.008
Token Average
Token ID13475
Feature activation+1.45e-01

Pos logit contributions
arp+0.009
 bulbs+0.008
 cubes+0.008
 pipes+0.007
place+0.007
Neg logit contributions
 grin-0.008
 amaz-0.007
zing-0.007
oled-0.007
Aud-0.007
Token for
Token ID329
Feature activation-4.52e-02

Pos logit contributions
 cubes+0.197
 island+0.187
arp+0.185
 bulbs+0.175
 crystals+0.173
Neg logit contributions
Aud-0.232
opl-0.226
 grin-0.226
oled-0.224
hered-0.219
Token age
Token ID2479
Feature activation-8.94e-02

Pos logit contributions
oled+0.078
ishly+0.076
severe+0.076
adays+0.075
 grin+0.075
Neg logit contributions
 cubes-0.057
 island-0.054
place-0.053
 pipes-0.051
 bulbs-0.051
Token:
Token ID25
Feature activation+1.01e-01

Pos logit contributions
 amaz+0.149
Aud+0.149
oled+0.146
 grin+0.146
adays+0.145
Neg logit contributions
 cubes-0.111
place-0.102
 island-0.098
 creatures-0.096
arp-0.093
Token 3
Token ID513
Feature activation+5.66e-02

Pos logit contributions
 cubes+0.120
 island+0.109
place+0.106
 pipes+0.103
 anchors+0.102
Neg logit contributions
oled-0.191
ishly-0.177
 grin-0.175
adays-0.171
hered-0.169
Token years
Token ID812
Feature activation+5.96e-02

Pos logit contributions
 cubes+0.053
arp+0.048
place+0.046
 island+0.044
 bulbs+0.042
Neg logit contributions
severe-0.117
Aud-0.115
 Deal-0.114
oled-0.113
adays-0.112
Token full
Token ID1336
Feature activation-4.20e-02

Pos logit contributions
arp+0.030
 island+0.029
 cubes+0.028
 bulbs+0.025
place+0.024
Neg logit contributions
 Deal-0.048
severe-0.047
 grin-0.046
Aud-0.045
 amaz-0.044
Token of
Token ID286
Feature activation-3.30e-03

Pos logit contributions
 Deal+0.056
 grin+0.056
severe+0.056
 amaz+0.056
opl+0.055
Neg logit contributions
arp-0.066
 island-0.061
 cubes-0.060
 bulbs-0.057
place-0.056
Token colourful
Token ID44799
Feature activation-2.60e-02

Pos logit contributions
 amaz+0.006
 grin+0.006
 Deal+0.006
 thank+0.006
severe+0.006
Neg logit contributions
arp-0.004
 island-0.003
 cubes-0.003
 bulbs-0.003
place-0.003
Token things
Token ID1243
Feature activation+3.83e-02

Pos logit contributions
 amaz+0.045
 grin+0.043
 thank+0.042
 delight+0.041
adays+0.041
Neg logit contributions
arp-0.030
 island-0.025
place-0.023
 cubes-0.023
leaning-0.022
Token.
Token ID13
Feature activation+1.99e-02

Pos logit contributions
arp+0.056
 island+0.051
 cubes+0.049
 bulbs+0.046
place+0.046
Neg logit contributions
 amaz-0.055
 grin-0.055
 Deal-0.054
severe-0.053
opl-0.053
Token Among
Token ID9754
Feature activation+1.44e-01

Pos logit contributions
arp+0.036
 island+0.033
 cubes+0.032
 bulbs+0.031
place+0.030
Neg logit contributions
 grin-0.022
 amaz-0.022
opl-0.022
severe-0.022
 Deal-0.022
Token them
Token ID606
Feature activation+2.86e-02

Pos logit contributions
arp+0.240
 island+0.219
 cubes+0.210
place+0.206
 bulbs+0.200
Neg logit contributions
 amaz-0.173
opl-0.160
severe-0.158
Aud-0.157
adays-0.154
Token,
Token ID11
Feature activation+1.49e-03

Pos logit contributions
 island+0.046
arp+0.045
 cubes+0.043
 bulbs+0.042
place+0.041
Neg logit contributions
 Deal-0.041
opl-0.038
severe-0.038
Aud-0.038
 grin-0.036
Token there
Token ID612
Feature activation+1.77e-02

Pos logit contributions
 island+0.002
 cubes+0.002
 bulbs+0.002
arp+0.001
 boats+0.001
Neg logit contributions
opl-0.003
 Deal-0.003
severe-0.003
 grin-0.003
istent-0.003
Token was
Token ID373
Feature activation-9.84e-03

Pos logit contributions
 island+0.017
arp+0.015
 cubes+0.014
 bulbs+0.013
place+0.013
Neg logit contributions
 Deal-0.039
severe-0.037
opl-0.036
Aud-0.035
 grin-0.034
Token a
Token ID257
Feature activation-1.12e-02

Pos logit contributions
opl+0.016
istent+0.016
severe+0.015
 Deal+0.015
 grin+0.015
Neg logit contributions
 island-0.014
 bulbs-0.013
 cubes-0.013
place-0.013
 pipes-0.013
Token happy
Token ID3772
Feature activation+4.19e-02

Pos logit contributions
 island+0.047
 day+0.045
 cubes+0.039
 shells+0.039
 planned+0.039
Neg logit contributions
Aud-0.125
severe-0.123
hered-0.121
opl-0.120
 Deal-0.118
Token!
Token ID0
Feature activation-6.13e-03

Pos logit contributions
 island+0.050
 cubes+0.045
arp+0.042
 creatures+0.040
 crystals+0.039
Neg logit contributions
 Deal-0.085
severe-0.080
istent-0.076
oled-0.075
Aud-0.075
Token She
Token ID1375
Feature activation-2.18e-03

Pos logit contributions
severe+0.009
 amaz+0.009
 grin+0.009
zing+0.009
Aud+0.009
Neg logit contributions
arp-0.008
 cubes-0.007
 island-0.007
 bulbs-0.007
 cube-0.006
Token couldn
Token ID3521
Feature activation+4.43e-03

Pos logit contributions
 Deal+0.005
Aud+0.005
severe+0.004
opl+0.004
oled+0.004
Neg logit contributions
 island-0.002
 ship-0.001
 ships-0.001
 boats-0.001
 decided-0.001
Token't
Token ID470
Feature activation+2.96e-02

Pos logit contributions
guard+0.004
arp+0.004
place+0.004
I+0.003
Tim+0.003
Neg logit contributions
 amaz-0.009
 Majesty-0.008
 Deal-0.008
 fascination-0.008
 reflex-0.008
Token believe
Token ID1975
Feature activation+1.44e-01

Pos logit contributions
arp+0.043
 island+0.041
 cubes+0.038
place+0.037
 bulbs+0.036
Neg logit contributions
 amaz-0.042
 Deal-0.042
opl-0.041
severe-0.041
Aud-0.040
Token she
Token ID673
Feature activation+1.27e-02

Pos logit contributions
arp+0.233
 island+0.222
 cubes+0.218
 bulbs+0.206
 crystals+0.199
Neg logit contributions
 Deal-0.186
opl-0.180
severe-0.179
 grin-0.176
 amaz-0.173
Token was
Token ID373
Feature activation+1.98e-02

Pos logit contributions
 island+0.012
place+0.010
 creatures+0.009
 treasures+0.009
arp+0.008
Neg logit contributions
 Deal-0.027
icks-0.027
opl-0.026
severe-0.026
Aud-0.025
Token getting
Token ID1972
Feature activation+1.22e-02

Pos logit contributions
 island+0.020
 underground+0.019
 creatures+0.017
 bulbs+0.017
 organized+0.016
Neg logit contributions
 Deal-0.039
severe-0.037
oled-0.035
istent-0.034
adays-0.034
Token candy
Token ID18550
Feature activation+5.10e-03

Pos logit contributions
 cubes+0.015
 bulbs+0.014
 crystals+0.013
 shells+0.013
 island+0.013
Neg logit contributions
opl-0.022
 Deal-0.021
istent-0.021
adays-0.020
urance-0.020
Token in
Token ID287
Feature activation+8.57e-02

Pos logit contributions
 island+0.007
 cubes+0.006
place+0.006
arp+0.006
 crystals+0.005
Neg logit contributions
 Deal-0.010
 amaz-0.009
icks-0.009
opl-0.009
severe-0.009
Token invitation
Token ID17023
Feature activation+2.08e-02

Pos logit contributions
 island+0.005
 cubes+0.004
arp+0.004
 bulbs+0.004
 tunnel+0.004
Neg logit contributions
oled-0.008
istent-0.008
Aud-0.008
severe-0.008
icks-0.008
Token,
Token ID11
Feature activation+4.32e-02

Pos logit contributions
 island+0.025
arp+0.021
place+0.020
 cubes+0.019
 ship+0.018
Neg logit contributions
 Deal-0.042
 amaz-0.039
opl-0.037
severe-0.037
used-0.036
Token she
Token ID673
Feature activation+1.30e-02

Pos logit contributions
 island+0.043
 bulbs+0.035
 cubes+0.034
 ship+0.033
 ships+0.033
Neg logit contributions
 Deal-0.090
opl-0.090
severe-0.084
icks-0.082
upid-0.080
Token couldn
Token ID3521
Feature activation+1.96e-03

Pos logit contributions
 island+0.009
 ship+0.007
place+0.006
 decided+0.006
 bulbs+0.006
Neg logit contributions
opl-0.030
 Deal-0.029
severe-0.028
Aud-0.027
 amaz-0.027
Token't
Token ID470
Feature activation+2.68e-02

Pos logit contributions
arp+0.002
place+0.002
guard+0.002
 island+0.002
 bulbs+0.002
Neg logit contributions
 amaz-0.004
 Majesty-0.003
 Deal-0.003
 grin-0.003
 reflex-0.003
Token believe
Token ID1975
Feature activation+1.44e-01

Pos logit contributions
arp+0.040
 island+0.038
place+0.035
 cubes+0.034
 bulbs+0.032
Neg logit contributions
 amaz-0.039
 Deal-0.039
opl-0.038
severe-0.038
Aud-0.037
Token how
Token ID703
Feature activation+6.54e-02

Pos logit contributions
arp+0.211
 island+0.203
 cubes+0.200
 bulbs+0.190
 crystals+0.186
Neg logit contributions
 Deal-0.206
severe-0.203
opl-0.201
Aud-0.196
 grin-0.194
Token excited
Token ID6568
Feature activation+3.66e-02

Pos logit contributions
arp+0.083
 island+0.077
place+0.075
 cubes+0.073
 bulbs+0.071
Neg logit contributions
 Deal-0.111
opl-0.108
severe-0.107
 amaz-0.104
 grin-0.104
Token Tommy
Token ID19919
Feature activation-1.71e-03

Pos logit contributions
 island+0.043
 bulbs+0.039
arp+0.038
 crystals+0.038
 creatures+0.038
Neg logit contributions
 Deal-0.074
severe-0.067
oled-0.066
istent-0.065
icks-0.064
Token was
Token ID373
Feature activation+6.45e-03

Pos logit contributions
 Deal+0.004
 amaz+0.004
icks+0.004
opl+0.004
severe+0.004
Neg logit contributions
 island-0.001
arp-0.001
 cubes-0.001
place-0.001
ie-0.001
Token.
Token ID13
Feature activation+2.68e-02

Pos logit contributions
 island+0.008
 underground+0.006
 creatures+0.006
 bulbs+0.005
 ship+0.005
Neg logit contributions
 Deal-0.014
severe-0.013
Aud-0.012
oled-0.012
opl-0.011
Token was
Token ID373
Feature activation+4.62e-02

Pos logit contributions
arp+0.053
 island+0.052
 cubes+0.051
 bulbs+0.045
 boats+0.043
Neg logit contributions
 Deal-0.077
 amaz-0.074
Aud-0.072
 grin-0.069
 Jeffrey-0.068
Token!
Token ID0
Feature activation+6.90e-03

Pos logit contributions
 island+0.054
 cubes+0.052
arp+0.050
 bulbs+0.048
place+0.043
Neg logit contributions
 Deal-0.085
severe-0.083
Aud-0.083
adays-0.082
opl-0.080
Token She
Token ID1375
Feature activation+7.11e-03

Pos logit contributions
arp+0.009
 cubes+0.008
 bulbs+0.008
Tim+0.008
 island+0.008
Neg logit contributions
opl-0.010
 amaz-0.010
 grin-0.010
severe-0.010
Aud-0.009
Token couldn
Token ID3521
Feature activation+7.91e-03

Pos logit contributions
 island+0.007
arp+0.006
 cubes+0.006
 bulbs+0.005
 boats+0.005
Neg logit contributions
 Deal-0.015
opl-0.015
severe-0.014
adays-0.014
Aud-0.014
Token't
Token ID470
Feature activation+3.43e-02

Pos logit contributions
arp+0.011
place+0.009
 bulb+0.009
 bulbs+0.009
 cube+0.009
Neg logit contributions
 amaz-0.014
 Majesty-0.013
 Deal-0.012
 grin-0.012
 reflex-0.011
Token believe
Token ID1975
Feature activation+1.44e-01

Pos logit contributions
arp+0.062
 cubes+0.056
 island+0.056
 bulbs+0.053
place+0.052
Neg logit contributions
 grin-0.039
 thank-0.038
 amaz-0.038
 Deal-0.036
severe-0.035
Token how
Token ID703
Feature activation+6.71e-02

Pos logit contributions
arp+0.249
 island+0.233
 cubes+0.229
 bulbs+0.219
 crystals+0.207
Neg logit contributions
 Deal-0.170
severe-0.166
 grin-0.165
opl-0.164
 amaz-0.164
Token different
Token ID1180
Feature activation+7.90e-02

Pos logit contributions
arp+0.101
 cubes+0.090
 island+0.089
 bulbs+0.087
place+0.085
Neg logit contributions
 Deal-0.099
severe-0.097
opl-0.097
 grin-0.096
 amaz-0.096
Token it
Token ID340
Feature activation+4.20e-02

Pos logit contributions
arp+0.106
 bulbs+0.104
 island+0.100
 cubes+0.098
 crystals+0.094
Neg logit contributions
 Deal-0.148
 grin-0.135
severe-0.132
oled-0.130
Aud-0.129
Token was
Token ID373
Feature activation+6.97e-03

Pos logit contributions
arp+0.046
 island+0.042
 bulbs+0.040
 cubes+0.039
place+0.037
Neg logit contributions
 Deal-0.083
severe-0.078
 grin-0.077
opl-0.077
 amaz-0.077
Token from
Token ID422
Feature activation+8.45e-03

Pos logit contributions
 island+0.008
arp+0.008
 bulbs+0.008
 cubes+0.007
place+0.007
Neg logit contributions
 Deal-0.013
severe-0.012
Aud-0.012
 amaz-0.012
 grin-0.012
Token!
Token ID0
Feature activation+6.32e-03

Pos logit contributions
 Deal+0.014
severe+0.013
istent+0.013
 amaz+0.012
oled+0.012
Neg logit contributions
 island-0.007
 cubes-0.006
 bulbs-0.006
 boats-0.006
 underground-0.006
Token The
Token ID383
Feature activation+4.56e-02

Pos logit contributions
arp+0.007
 cubes+0.007
Tim+0.007
 bulbs+0.007
B+0.006
Neg logit contributions
 amaz-0.010
opl-0.009
severe-0.009
Aud-0.009
 grin-0.009
Token mouse
Token ID10211
Feature activation+4.88e-02

Pos logit contributions
 island+0.054
arp+0.050
 cubes+0.048
 bulbs+0.045
place+0.043
Neg logit contributions
oled-0.082
icks-0.082
istent-0.082
Aud-0.081
opl-0.081
Token couldn
Token ID3521
Feature activation-7.35e-04

Pos logit contributions
 island+0.045
arp+0.037
 bulbs+0.037
 creatures+0.037
 tunnel+0.034
Neg logit contributions
 Deal-0.105
severe-0.098
opl-0.096
Aud-0.096
 amaz-0.090
Token't
Token ID470
Feature activation+2.48e-02

Pos logit contributions
 amaz+0.001
 Majesty+0.001
 grin+0.001
 Deal+0.001
 fascination+0.001
Neg logit contributions
arp-0.001
place-0.001
Tim-0.001
guard-0.001
B-0.001
Token believe
Token ID1975
Feature activation+1.43e-01

Pos logit contributions
arp+0.042
 island+0.039
 cubes+0.037
place+0.036
 bulbs+0.035
Neg logit contributions
 amaz-0.030
 Deal-0.030
 grin-0.030
severe-0.029
opl-0.029
Token it
Token ID340
Feature activation+4.44e-02

Pos logit contributions
arp+0.224
 island+0.215
 cubes+0.209
 bulbs+0.195
 crystals+0.187
Neg logit contributions
 Deal-0.192
opl-0.187
severe-0.187
 amaz-0.182
 grin-0.181
Token!
Token ID0
Feature activation-1.86e-02

Pos logit contributions
 island+0.040
arp+0.035
place+0.032
 underground+0.030
 creatures+0.030
Neg logit contributions
 Deal-0.092
Aud-0.090
opl-0.089
severe-0.088
icks-0.087
Token The
Token ID383
Feature activation+2.63e-02

Pos logit contributions
opl+0.025
severe+0.025
 amaz+0.025
 grin+0.024
icks+0.024
Neg logit contributions
arp-0.026
 cubes-0.023
 bulbs-0.022
 island-0.022
Tim-0.021
Token young
Token ID1862
Feature activation-1.56e-02

Pos logit contributions
arp+0.029
 island+0.028
 cubes+0.026
 bulbs+0.025
place+0.023
Neg logit contributions
opl-0.047
adays-0.046
Aud-0.046
severe-0.046
 amaz-0.046
Token boy
Token ID2933
Feature activation+2.95e-02

Pos logit contributions
 Deal+0.031
opl+0.030
severe+0.030
adays+0.030
 grin+0.030
Neg logit contributions
arp-0.015
 island-0.015
 cubes-0.013
 bulbs-0.013
place-0.011
Token said
Token ID531
Feature activation+2.95e-02

Pos logit contributions
 island+0.075
 boats+0.062
arp+0.062
 cubes+0.061
 ship+0.060
Neg logit contributions
opl-0.121
 Deal-0.120
oled-0.115
 amaz-0.114
istent-0.112
Token goodbye
Token ID24829
Feature activation-2.93e-02

Pos logit contributions
 cubes+0.026
 boats+0.025
 island+0.025
 shells+0.023
 ships+0.023
Neg logit contributions
opl-0.067
 Deal-0.063
severe-0.056
istent-0.056
Aud-0.054
Token and
Token ID290
Feature activation+4.26e-02

Pos logit contributions
 Deal+0.065
 amaz+0.063
opl+0.063
severe+0.060
oled+0.058
Neg logit contributions
 island-0.026
arp-0.022
 jackets-0.021
 ship-0.020
 cubes-0.019
Token promised
Token ID8072
Feature activation+9.17e-03

Pos logit contributions
 island+0.043
 ship+0.034
 jackets+0.032
 boy+0.031
 shells+0.029
Neg logit contributions
opl-0.094
istent-0.093
 Deal-0.091
oled-0.090
upid-0.084
Token to
Token ID284
Feature activation+4.36e-02

Pos logit contributions
arp+0.008
 island+0.008
 jackets+0.007
place+0.007
 workers+0.006
Neg logit contributions
 Deal-0.020
 amaz-0.019
opl-0.019
 grin-0.018
 la-0.018
Token believe
Token ID1975
Feature activation+1.43e-01

Pos logit contributions
 island+0.053
 ship+0.040
 jackets+0.037
place+0.036
arp+0.034
Neg logit contributions
oled-0.092
istent-0.086
inged-0.085
 Immediately-0.084
 amaz-0.084
Token in
Token ID287
Feature activation+9.21e-02

Pos logit contributions
arp+0.200
 island+0.185
 cubes+0.179
 bulbs+0.167
place+0.162
Neg logit contributions
 Deal-0.217
 amaz-0.217
opl-0.214
 grin-0.214
severe-0.210
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
 island+0.115
place+0.102
arp+0.101
 cubes+0.092
 treasures+0.091
Neg logit contributions
oled-0.166
istent-0.163
severe-0.161
 grin-0.153
 Immediately-0.152
Token magic
Token ID5536
Feature activation+6.81e-03

Pos logit contributions
 island+0.027
arp+0.027
 cubes+0.023
place+0.023
 bulbs+0.022
Neg logit contributions
oled-0.037
istent-0.036
 Immediately-0.036
 Deal-0.035
icks-0.035
Token of
Token ID286
Feature activation+8.66e-03

Pos logit contributions
 island+0.008
arp+0.008
 bulbs+0.007
place+0.007
 cubes+0.007
Neg logit contributions
 Deal-0.013
Aud-0.012
oled-0.012
severe-0.012
opl-0.012
Token the
Token ID262
Feature activation+8.31e-03

Pos logit contributions
 island+0.013
 cubes+0.010
 bulbs+0.010
 shells+0.010
arp+0.010
Neg logit contributions
oled-0.015
istent-0.015
severe-0.015
 Deal-0.014
 Immediately-0.014
Tokens
Token ID82
Feature activation-2.13e-02

Pos logit contributions
 amaz+0.085
 Majesty+0.080
severe+0.077
 delight+0.076
 Deal+0.075
Neg logit contributions
arp-0.036
 cubes-0.033
 cube-0.025
guard-0.024
washer-0.023
Token pretend
Token ID16614
Feature activation+1.47e-02

Pos logit contributions
oled+0.045
Aud+0.043
opl+0.040
 Deal+0.039
joy+0.038
Neg logit contributions
 island-0.025
 ship-0.023
 anchor-0.021
 cube-0.020
 bulb-0.020
Token to
Token ID284
Feature activation-1.36e-02

Pos logit contributions
 island+0.019
 cubes+0.018
arp+0.016
place+0.016
 boats+0.016
Neg logit contributions
 Deal-0.028
severe-0.026
istent-0.025
oled-0.025
opl-0.024
Token be
Token ID307
Feature activation+1.50e-02

Pos logit contributions
oled+0.028
 Deal+0.026
opl+0.026
Aud+0.025
istent+0.024
Neg logit contributions
 island-0.017
place-0.014
 ship-0.013
arp-0.013
 tunnel-0.013
Token aer
Token ID9551
Feature activation-5.13e-03

Pos logit contributions
 island+0.019
 creatures+0.018
 pirates+0.017
 bulbs+0.017
 ships+0.017
Neg logit contributions
 Deal-0.028
istent-0.027
oled-0.026
chief-0.026
adays-0.025
Tokenopl
Token ID20106
Feature activation-2.37e-01

Pos logit contributions
 amaz+0.003
 grin+0.002
 Deal+0.002
 thank+0.002
severe+0.002
Neg logit contributions
arp-0.012
 cubes-0.011
place-0.011
 island-0.011
leaning-0.011
Tokenanes
Token ID7305
Feature activation-3.95e-02

Pos logit contributions
 amaz+0.495
 delight+0.458
 grin+0.452
 goodbye+0.423
 thank+0.421
Neg logit contributions
arp-0.260
 cubes-0.248
we-0.216
place-0.206
 bulbs-0.182
Token,
Token ID11
Feature activation-1.98e-02

Pos logit contributions
 Deal+0.082
 amaz+0.077
 grin+0.073
oled+0.072
 delight+0.071
Neg logit contributions
 island-0.048
 cubes-0.041
arp-0.039
 ship-0.039
 boats-0.037
Tokenâ
Token ID22940
Feature activation+1.79e-02

Pos logit contributions
opl+0.034
icks+0.033
 Deal+0.033
 grin+0.032
oled+0.032
Neg logit contributions
arp-0.023
 island-0.023
 cubes-0.023
 boats-0.022
 ships-0.021
Token
Token ID26391
Feature activation+8.39e-03

Pos logit contributions
arp+0.029
 island+0.026
 cubes+0.025
place+0.024
 bulbs+0.024
Neg logit contributions
 amaz-0.024
 grin-0.023
 Deal-0.023
severe-0.022
adays-0.022
Token Jack
Token ID3619
Feature activation-2.03e-02

Pos logit contributions
arp+0.013
 cubes+0.011
 island+0.011
ney+0.010
 jackets+0.010
Neg logit contributions
 Deal-0.012
 amaz-0.012
severe-0.012
 delight-0.011
 grin-0.011
Tokenmy
Token ID1820
Feature activation-8.31e-02

Pos logit contributions
 cubes+0.006
 island+0.005
arp+0.005
 bulbs+0.005
 crystals+0.005
Neg logit contributions
 Deal-0.009
Aud-0.008
severe-0.008
opl-0.008
 AW-0.008
Token all
Token ID477
Feature activation-1.34e-03

Pos logit contributions
 Deal+0.173
opl+0.157
Aud+0.156
severe+0.149
 amaz+0.146
Neg logit contributions
 cubes-0.097
 island-0.091
 crystals-0.084
 bulbs-0.082
 ships-0.081
Token about
Token ID546
Feature activation-1.82e-02

Pos logit contributions
 Deal+0.001
 amaz+0.001
 grin+0.001
severe+0.001
opl+0.001
Neg logit contributions
arp-0.003
 island-0.003
 cubes-0.003
 bulbs-0.003
place-0.002
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
 Deal+0.031
severe+0.030
oled+0.028
 grin+0.028
istent+0.028
Neg logit contributions
 island-0.026
 cubes-0.025
arp-0.023
 bulbs-0.023
 pipes-0.022
Token aer
Token ID9551
Feature activation-1.47e-02

Pos logit contributions
 amaz+0.029
opl+0.028
 thank+0.028
 grin+0.028
severe+0.027
Neg logit contributions
arp-0.018
 cubes-0.016
 island-0.015
 bulbs-0.014
place-0.014
Tokenopl
Token ID20106
Feature activation-2.36e-01

Pos logit contributions
opl+0.000
 grin+0.000
 amaz+0.000
 Deal-0.000
severe-0.001
Neg logit contributions
arp-0.042
 island-0.040
 cubes-0.040
 bulbs-0.039
place-0.039
Tokenane
Token ID1531
Feature activation-6.43e-02

Pos logit contributions
opl+0.265
 grin+0.263
 amaz+0.263
 Deal+0.257
severe+0.255
Neg logit contributions
arp-0.411
 island-0.386
 cubes-0.371
 bulbs-0.356
place-0.354
Token he
Token ID339
Feature activation-2.18e-02

Pos logit contributions
 Deal+0.134
severe+0.112
icks+0.109
Aud+0.108
 Majesty+0.105
Neg logit contributions
 island-0.086
arp-0.075
place-0.070
 ship-0.069
 cubes-0.069
Token saw
Token ID2497
Feature activation-2.06e-03

Pos logit contributions
 Deal+0.047
adays+0.046
severe+0.045
 grin+0.045
 amaz+0.045
Neg logit contributions
 island-0.017
arp-0.017
place-0.016
 cubes-0.014
 ship-0.012
Token and
Token ID290
Feature activation-1.19e-02

Pos logit contributions
 Deal+0.005
Aud+0.004
 grin+0.004
istent+0.004
severe+0.004
Neg logit contributions
 island-0.002
arp-0.002
 cubes-0.002
place-0.002
 bulbs-0.002
Token how
Token ID703
Feature activation+1.05e-02

Pos logit contributions
 Deal+0.027
opl+0.025
Aud+0.024
istent+0.024
severe+0.024
Neg logit contributions
 cubes-0.011
 island-0.011
 bulbs-0.010
 pipes-0.009
 ships-0.009
Token the
Token ID262
Feature activation-1.39e-02

Pos logit contributions
arp+0.073
 island+0.069
 cubes+0.066
 bulbs+0.061
place+0.060
Neg logit contributions
 Deal-0.059
 grin-0.058
severe-0.058
oled-0.058
istent-0.056
Token sky
Token ID6766
Feature activation-5.23e-02

Pos logit contributions
 amaz+0.016
 grin+0.016
 Deal+0.016
severe+0.015
opl+0.015
Neg logit contributions
arp-0.024
 island-0.022
 cubes-0.022
 bulbs-0.021
place-0.021
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
 Deal+0.133
severe+0.129
oled+0.126
adays+0.123
istent+0.122
Neg logit contributions
 island-0.030
arp-0.025
 cubes-0.023
 bulbs-0.019
 creatures-0.015
Token The
Token ID383
Feature activation-6.44e-03

Pos logit contributions
opl+0.019
 grin+0.018
istent+0.017
severe+0.017
 amaz+0.016
Neg logit contributions
arp-0.012
 island-0.012
 cubes-0.011
 boats-0.011
 pipes-0.011
Token aer
Token ID9551
Feature activation-1.40e-02

Pos logit contributions
 amaz+0.011
 thank+0.011
opl+0.011
 grin+0.011
 bye+0.010
Neg logit contributions
arp-0.008
 cubes-0.007
 island-0.006
 bulbs-0.006
place-0.006
Tokenopl
Token ID20106
Feature activation-2.34e-01

Pos logit contributions
opl+0.000
 grin-0.000
 amaz-0.000
 Deal-0.000
severe-0.001
Neg logit contributions
arp-0.041
 island-0.039
 cubes-0.038
 bulbs-0.037
place-0.037
Tokenane
Token ID1531
Feature activation-6.53e-02

Pos logit contributions
opl+0.244
 amaz+0.224
severe+0.221
 grin+0.220
oled+0.218
Neg logit contributions
arp-0.434
 island-0.415
 cubes-0.398
place-0.389
 bulbs-0.382
Token makes
Token ID1838
Feature activation-3.28e-02

Pos logit contributions
 Deal+0.091
 grin+0.085
 amaz+0.085
oled+0.085
istent+0.083
Neg logit contributions
 island-0.101
arp-0.100
 cubes-0.091
 bulbs-0.090
place-0.087
Token a
Token ID257
Feature activation-2.57e-02

Pos logit contributions
 Deal+0.071
used+0.067
+0.067
istent+0.063
ishly+0.062
Neg logit contributions
 tunnels-0.036
 animals-0.035
 boats-0.035
 island-0.033
arp-0.032
Token loud
Token ID7812
Feature activation-9.27e-02

Pos logit contributions
 Deal+0.026
opl+0.026
severe+0.026
 amaz+0.026
 grin+0.026
Neg logit contributions
arp-0.048
 island-0.045
 cubes-0.043
 bulbs-0.041
place-0.041
Token noise
Token ID7838
Feature activation-2.09e-02

Pos logit contributions
 Deal+0.177
used+0.165
Aud+0.165
 amaz+0.165
severe+0.163
Neg logit contributions
arp-0.102
 island-0.097
 tunnel-0.080
 cubes-0.080
 bulbs-0.077
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
opl+0.000
 grin+0.000
 amaz-0.000
 Deal-0.000
 thank-0.000
Neg logit contributions
arp-0.024
 island-0.023
 cubes-0.023
 bulbs-0.022
place-0.022
Tokenane
Token ID1531
Feature activation-6.14e-02

Pos logit contributions
 grin+0.265
 amaz+0.263
opl+0.260
 Deal+0.258
severe+0.255
Neg logit contributions
arp-0.406
 island-0.377
 cubes-0.366
 bulbs-0.350
place-0.348
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
opl+0.072
 thank+0.069
 grin+0.069
 amaz+0.067
 Immediately+0.065
Neg logit contributions
arp-0.105
 cubes-0.094
 island-0.092
 bulbs-0.090
place-0.087
Token The
Token ID383
Feature activation-1.25e-02

Pos logit contributions
 Deal+0.016
 grin+0.016
 amaz+0.015
severe+0.015
Aud+0.015
Neg logit contributions
arp-0.027
 island-0.026
 cubes-0.026
 bulbs-0.025
place-0.023
Token aer
Token ID9551
Feature activation-1.22e-02

Pos logit contributions
 thank+0.020
 amaz+0.019
opl+0.019
 bye+0.019
 grin+0.019
Neg logit contributions
arp-0.016
 cubes-0.014
 bulbs-0.014
place-0.013
leaning-0.013
Tokenopl
Token ID20106
Feature activation-2.34e-01

Pos logit contributions
opl+0.000
 grin-0.002
 amaz-0.002
 thank-0.002
 Deal-0.003
Neg logit contributions
arp-0.037
 island-0.035
 cubes-0.035
 bulbs-0.034
place-0.034
Tokenane
Token ID1531
Feature activation-6.38e-02

Pos logit contributions
opl+0.242
 amaz+0.221
 grin+0.220
oled+0.217
severe+0.216
Neg logit contributions
arp-0.437
 island-0.415
 cubes-0.398
place-0.390
 bulbs-0.386
Token was
Token ID373
Feature activation-3.36e-02

Pos logit contributions
 thank+0.062
opl+0.061
 grin+0.055
 bye+0.055
 goodbye+0.054
Neg logit contributions
arp-0.125
 cubes-0.108
leaning-0.105
place-0.103
 bulbs-0.103
Token very
Token ID845
Feature activation+5.73e-02

Pos logit contributions
 Deal+0.054
 amaz+0.053
 grin+0.052
adays+0.051
oled+0.051
Neg logit contributions
arp-0.044
 island-0.044
 cubes-0.041
 bulbs-0.038
place-0.036
Token generous
Token ID14431
Feature activation-1.55e-02

Pos logit contributions
arp+0.094
 island+0.086
 cubes+0.084
 bulbs+0.079
place+0.079
Neg logit contributions
 amaz-0.073
 grin-0.073
 Deal-0.072
severe-0.070
opl-0.070
Token.
Token ID13
Feature activation-1.32e-02

Pos logit contributions
 grin+0.018
 amaz+0.018
 thank+0.017
opl+0.017
 Deal+0.017
Neg logit contributions
arp-0.027
 island-0.024
 cubes-0.024
 bulbs-0.023
place-0.023
Token like
Token ID588
Feature activation-3.32e-02

Pos logit contributions
Aud+0.067
opl+0.065
 Deal+0.064
oled+0.063
Sean+0.062
Neg logit contributions
 island-0.037
place-0.034
arp-0.033
 underground-0.032
 bulbs-0.032
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
 grin+0.061
 amaz+0.060
 Deal+0.059
oled+0.058
Aud+0.057
Neg logit contributions
 island-0.040
place-0.039
arp-0.037
 bulbs-0.035
 cubes-0.034
Token Although
Token ID4900
Feature activation-2.14e-02

Pos logit contributions
 grin+0.018
 amaz+0.016
Aud+0.015
oled+0.015
zing+0.015
Neg logit contributions
arp-0.021
leaning-0.018
 bulbs-0.017
place-0.017
 cubes-0.016
Token the
Token ID262
Feature activation-1.52e-02

Pos logit contributions
 Deal+0.044
oled+0.043
 grin+0.043
opl+0.041
istent+0.040
Neg logit contributions
 island-0.024
place-0.023
arp-0.020
 bulbs-0.019
 shells-0.019
Token aer
Token ID9551
Feature activation-9.67e-03

Pos logit contributions
oled+0.030
istent+0.029
opl+0.029
severe+0.029
Aud+0.029
Neg logit contributions
 island-0.015
arp-0.014
 bulbs-0.013
place-0.013
 cubes-0.012
Tokenopl
Token ID20106
Feature activation-2.34e-01

Pos logit contributions
 amaz+0.006
 grin+0.005
 Deal+0.005
severe+0.005
adays+0.005
Neg logit contributions
arp-0.024
 island-0.021
 cubes-0.021
place-0.021
 bulbs-0.021
Tokenane
Token ID1531
Feature activation-6.16e-02

Pos logit contributions
 amaz+0.407
 grin+0.406
 delight+0.394
 Deal+0.389
 thank+0.374
Neg logit contributions
arp-0.318
 cubes-0.266
 island-0.248
 bulbs-0.240
place-0.234
Token was
Token ID373
Feature activation-3.19e-02

Pos logit contributions
 Deal+0.124
Aud+0.118
oled+0.118
 amaz+0.114
 grin+0.110
Neg logit contributions
 island-0.065
place-0.063
 creatures-0.056
 bulbs-0.056
arp-0.056
Token a
Token ID257
Feature activation-3.21e-02

Pos logit contributions
oled+0.065
 Deal+0.064
 grin+0.063
adays+0.063
 amaz+0.062
Neg logit contributions
 island-0.031
 underground-0.029
 bulbs-0.028
place-0.026
 creatures-0.025
Token pretty
Token ID2495
Feature activation-1.33e-02

Pos logit contributions
icks+0.055
 Deal+0.054
opl+0.054
Aud+0.053
oled+0.053
Neg logit contributions
arp-0.039
 island-0.039
place-0.035
 cubes-0.034
 tunnel-0.032
Token sight
Token ID6504
Feature activation-6.09e-02

Pos logit contributions
 Deal+0.027
Aud+0.025
oled+0.025
icks+0.024
opl+0.024
Neg logit contributions
 island-0.017
arp-0.015
 bulbs-0.013
 cubes-0.013
 tunnel-0.013
TokenL
Token ID43
Feature activation-5.02e-03

Pos logit contributions
 Deal+0.024
 amaz+0.023
 grin+0.023
severe+0.023
Aud+0.022
Neg logit contributions
arp-0.016
 island-0.015
 cubes-0.014
 bulbs-0.013
place-0.013
Tokenily
Token ID813
Feature activation+8.66e-02

Pos logit contributions
 Deal+0.009
 grin+0.009
 amaz+0.009
opl+0.009
severe+0.009
Neg logit contributions
arp-0.006
 island-0.005
 cubes-0.005
 bulbs-0.004
place-0.004
Token watched
Token ID7342
Feature activation-2.69e-02

Pos logit contributions
 island+0.079
arp+0.079
 cubes+0.071
 cube+0.063
 jackets+0.063
Neg logit contributions
 Deal-0.177
opl-0.168
severe-0.164
adays-0.156
 amaz-0.155
Token the
Token ID262
Feature activation-1.33e-02

Pos logit contributions
 Deal+0.048
opl+0.048
Aud+0.048
 amaz+0.044
ives+0.044
Neg logit contributions
 boats-0.028
 island-0.028
 cubes-0.028
 bulbs-0.027
arp-0.027
Token aer
Token ID9551
Feature activation-1.05e-02

Pos logit contributions
 Deal+0.028
 grin+0.028
 amaz+0.027
severe+0.027
adays+0.027
Neg logit contributions
arp-0.011
 island-0.010
 cubes-0.009
 bulbs-0.008
place-0.008
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
 amaz+0.002
 grin+0.002
 Deal+0.001
severe+0.001
adays+0.001
Neg logit contributions
arp-0.029
 island-0.027
 cubes-0.027
place-0.026
 bulbs-0.026
Tokenane
Token ID1531
Feature activation-6.12e-02

Pos logit contributions
 amaz+0.300
 grin+0.298
 Deal+0.293
severe+0.284
 thank+0.281
Neg logit contributions
arp-0.385
 island-0.348
 cubes-0.343
 bulbs-0.322
place-0.319
Token until
Token ID1566
Feature activation-2.24e-02

Pos logit contributions
 Deal+0.102
oled+0.094
Aud+0.092
Sean+0.087
 amaz+0.087
Neg logit contributions
 island-0.090
arp-0.083
 bulbs-0.075
place-0.073
 cubes-0.073
Token it
Token ID340
Feature activation+9.67e-03

Pos logit contributions
 Deal+0.053
opl+0.053
istent+0.050
ives+0.047
icks+0.047
Neg logit contributions
 island-0.017
 shells-0.015
 cubes-0.014
 boats-0.013
 seas-0.013
Token disappeared
Token ID12120
Feature activation-4.36e-02

Pos logit contributions
 island+0.010
arp+0.010
 tunnel+0.008
 bulbs+0.008
place+0.008
Neg logit contributions
 Deal-0.020
opl-0.018
 grin-0.018
istent-0.018
ishly-0.018
Token.
Token ID13
Feature activation-5.29e-03

Pos logit contributions
 Deal+0.086
opl+0.086
Aud+0.083
oled+0.081
 grin+0.079
Neg logit contributions
arp-0.047
 island-0.046
 bulbs-0.041
 cubes-0.040
 crystals-0.037
Tokenily
Token ID813
Feature activation+8.50e-02

Pos logit contributions
opl+0.010
 Deal+0.010
 grin+0.010
 thank+0.010
 amaz+0.010
Neg logit contributions
arp-0.008
 island-0.007
 cubes-0.007
 bulbs-0.007
place-0.006
Token saw
Token ID2497
Feature activation+4.32e-03

Pos logit contributions
arp+0.121
 island+0.111
 cubes+0.107
 bulbs+0.100
place+0.098
Neg logit contributions
 Deal-0.127
 amaz-0.127
opl-0.127
 grin-0.123
severe-0.122
Token her
Token ID607
Feature activation-1.06e-02

Pos logit contributions
 cubes+0.007
arp+0.007
 pipes+0.006
 island+0.006
 bulbs+0.006
Neg logit contributions
istent-0.006
 Deal-0.006
 grin-0.006
severe-0.006
used-0.005
Token broken
Token ID5445
Feature activation-4.07e-02

Pos logit contributions
 Deal+0.014
 amaz+0.014
severe+0.014
 grin+0.014
adays+0.014
Neg logit contributions
arp-0.017
 island-0.015
 cubes-0.015
 bulbs-0.014
place-0.014
Token aer
Token ID9551
Feature activation-1.25e-02

Pos logit contributions
 amaz+0.078
 grin+0.078
 Deal+0.078
severe+0.076
opl+0.076
Neg logit contributions
arp-0.040
 island-0.035
 cubes-0.033
 bulbs-0.030
place-0.029
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
 amaz+0.001
 grin+0.001
 Deal+0.000
opl+0.000
severe-0.000
Neg logit contributions
arp-0.036
 island-0.034
 cubes-0.033
 bulbs-0.033
place-0.032
Tokenane
Token ID1531
Feature activation-6.15e-02

Pos logit contributions
opl+0.249
 grin+0.235
 amaz+0.233
severe+0.232
oled+0.231
Neg logit contributions
arp-0.421
 island-0.407
 cubes-0.382
 bulbs-0.375
place-0.373
Token and
Token ID290
Feature activation-1.44e-02

Pos logit contributions
 Deal+0.102
Aud+0.093
 amaz+0.093
severe+0.091
oled+0.091
Neg logit contributions
 island-0.082
arp-0.082
 cubes-0.076
 bulbs-0.072
place-0.072
Token cried
Token ID16896
Feature activation+3.14e-04

Pos logit contributions
 Deal+0.026
opl+0.025
severe+0.024
istent+0.024
Aud+0.024
Neg logit contributions
 cubes-0.017
 island-0.017
arp-0.017
 bulbs-0.016
 pipes-0.015
Token.
Token ID13
Feature activation-6.34e-03

Pos logit contributions
arp+0.000
 cubes+0.000
 bulbs+0.000
 island+0.000
 pipes+0.000
Neg logit contributions
 amaz-0.001
opl-0.001
Aud-0.001
 Deal-0.001
 grin-0.001
Token She
Token ID1375
Feature activation-5.20e-02

Pos logit contributions
severe+0.009
 amaz+0.009
 grin+0.008
opl+0.008
 Deal+0.008
Neg logit contributions
arp-0.009
 pipes-0.008
 bulbs-0.008
 cubes-0.008
leaning-0.008
Token The
Token ID383
Feature activation-8.70e-03

Pos logit contributions
 amaz+0.009
 grin+0.009
 Deal+0.009
 thank+0.009
opl+0.009
Neg logit contributions
arp-0.023
 island-0.021
 cubes-0.021
place-0.020
 bulbs-0.020
Token children
Token ID1751
Feature activation-3.07e-02

Pos logit contributions
 thank+0.014
 amaz+0.014
opl+0.014
 bye+0.013
 grin+0.013
Neg logit contributions
arp-0.012
 cubes-0.010
 bulbs-0.010
 island-0.009
place-0.009
Token loved
Token ID6151
Feature activation-4.23e-03

Pos logit contributions
 grin+0.044
 thank+0.044
 amaz+0.044
severe+0.043
adays+0.042
Neg logit contributions
arp-0.045
 island-0.039
 cubes-0.038
place-0.036
 bulbs-0.036
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
 amaz+0.005
 grin+0.005
 Deal+0.005
 thank+0.005
opl+0.005
Neg logit contributions
arp-0.007
 island-0.006
 cubes-0.006
 bulbs-0.006
place-0.006
Token aer
Token ID9551
Feature activation-1.19e-02

Pos logit contributions
opl+0.026
 thank+0.026
 amaz+0.026
 grin+0.025
 bye+0.024
Neg logit contributions
arp-0.020
 cubes-0.017
 bulbs-0.016
 island-0.016
place-0.015
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
opl+0.000
 grin-0.001
 amaz-0.001
 Deal-0.001
 thank-0.001
Neg logit contributions
arp-0.035
 island-0.033
 cubes-0.033
 bulbs-0.032
place-0.032
Tokenane
Token ID1531
Feature activation-6.31e-02

Pos logit contributions
opl+0.252
 grin+0.243
 amaz+0.242
severe+0.237
oled+0.236
Neg logit contributions
arp-0.419
 island-0.396
 cubes-0.378
 bulbs-0.365
place-0.364
Token very
Token ID845
Feature activation+6.01e-02

Pos logit contributions
 Deal+0.094
 amaz+0.089
 grin+0.087
severe+0.087
oled+0.086
Neg logit contributions
arp-0.095
 island-0.092
 cubes-0.086
 bulbs-0.082
place-0.082
Token much
Token ID881
Feature activation-2.99e-02

Pos logit contributions
arp+0.142
 island+0.132
 cubes+0.127
 bulbs+0.125
leaning+0.122
Neg logit contributions
 thank-0.034
 grin-0.032
opl-0.029
adays-0.029
 goodbye-0.028
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
 amaz+0.038
 grin+0.038
 thank+0.037
 Deal+0.037
opl+0.036
Neg logit contributions
arp-0.049
 island-0.044
 cubes-0.043
 bulbs-0.041
place-0.040
Token
Token ID198
Feature activation-1.91e-02

Pos logit contributions
 amaz+0.009
 thank+0.009
 Deal+0.008
opl+0.008
 Immediately+0.008
Neg logit contributions
arp-0.025
 island-0.024
 cubes-0.023
place-0.023
 bulbs-0.022
Token.
Token ID13
Feature activation-6.34e-03

Pos logit contributions
arp+0.000
 cubes+0.000
 bulbs+0.000
 island+0.000
 pipes+0.000
Neg logit contributions
 amaz-0.001
opl-0.001
Aud-0.001
 Deal-0.001
 grin-0.001
Token She
Token ID1375
Feature activation-5.20e-02

Pos logit contributions
severe+0.009
 amaz+0.009
 grin+0.008
opl+0.008
 Deal+0.008
Neg logit contributions
arp-0.009
 pipes-0.008
 bulbs-0.008
 cubes-0.008
leaning-0.008
Token loved
Token ID6151
Feature activation-2.28e-03

Pos logit contributions
 thank+0.061
 grin+0.059
 amaz+0.057
 Deal+0.056
oled+0.056
Neg logit contributions
arp-0.094
 island-0.086
 cubes-0.084
 bulbs-0.079
place-0.079
Token her
Token ID607
Feature activation-1.01e-02

Pos logit contributions
 Deal+0.003
severe+0.003
 grin+0.003
istent+0.003
adays+0.003
Neg logit contributions
 cubes-0.004
arp-0.003
 island-0.003
 bulbs-0.003
 pipes-0.003
Token aer
Token ID9551
Feature activation-1.32e-02

Pos logit contributions
 amaz+0.017
 thank+0.017
opl+0.016
 grin+0.016
 goodbye+0.016
Neg logit contributions
arp-0.013
 cubes-0.011
 island-0.011
place-0.011
 bulbs-0.010
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
 amaz+0.001
 grin+0.001
 Deal+0.000
severe+0.000
opl+0.000
Neg logit contributions
arp-0.038
 island-0.036
 cubes-0.035
 bulbs-0.034
place-0.034
Tokenane
Token ID1531
Feature activation-6.18e-02

Pos logit contributions
opl+0.255
 grin+0.241
 amaz+0.238
severe+0.237
oled+0.236
Neg logit contributions
arp-0.415
 island-0.401
 cubes-0.378
 bulbs-0.367
place-0.367
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
 Deal+0.114
used+0.108
oled+0.106
 amaz+0.105
Aud+0.104
Neg logit contributions
 island-0.071
arp-0.069
 cubes-0.066
place-0.063
 bulbs-0.062
Token now
Token ID783
Feature activation-4.44e-02

Pos logit contributions
 Deal+0.027
severe+0.025
istent+0.025
opl+0.025
Aud+0.025
Neg logit contributions
 cubes-0.015
 island-0.015
arp-0.015
 bulbs-0.014
 pipes-0.013
Token it
Token ID340
Feature activation+1.01e-02

Pos logit contributions
 Deal+0.089
 amaz+0.078
istent+0.077
severe+0.077
Aud+0.076
Neg logit contributions
 cubes-0.042
 island-0.040
 crystals-0.036
 bulbs-0.036
arp-0.035
Token was
Token ID373
Feature activation-2.97e-02

Pos logit contributions
arp+0.014
 island+0.012
 cubes+0.012
 bulbs+0.011
place+0.011
Neg logit contributions
 Deal-0.016
 amaz-0.016
 grin-0.016
severe-0.015
opl-0.015
Token there
Token ID612
Feature activation-3.68e-05

Pos logit contributions
 amaz+0.054
 grin+0.054
 Deal+0.054
 thank+0.052
severe+0.052
Neg logit contributions
arp-0.041
 island-0.036
 cubes-0.034
place-0.032
 bulbs-0.032
Token was
Token ID373
Feature activation-3.15e-02

Pos logit contributions
 Deal+0.000
severe+0.000
 grin+0.000
Aud+0.000
 amaz+0.000
Neg logit contributions
arp-0.000
 island-0.000
 cubes-0.000
place-0.000
 bulbs-0.000
Token a
Token ID257
Feature activation-2.95e-02

Pos logit contributions
 amaz+0.024
 grin+0.024
 Deal+0.023
severe+0.022
opl+0.022
Neg logit contributions
arp-0.068
 island-0.063
 cubes-0.062
 bulbs-0.059
place-0.059
Token big
Token ID1263
Feature activation-4.89e-02

Pos logit contributions
 thank+0.029
 grin+0.029
 amaz+0.027
 bye+0.027
 Deal+0.025
Neg logit contributions
arp-0.058
 cubes-0.051
 island-0.051
 bulbs-0.050
place-0.050
Token aer
Token ID9551
Feature activation-8.41e-03

Pos logit contributions
 Deal+0.074
 amaz+0.073
severe+0.073
 grin+0.072
adays+0.071
Neg logit contributions
arp-0.069
 island-0.066
 cubes-0.062
 bulbs-0.057
place-0.056
Tokenopl
Token ID20106
Feature activation-2.33e-01

Pos logit contributions
opl+0.000
 grin+0.000
 amaz-0.000
 Deal-0.000
 thank-0.000
Neg logit contributions
arp-0.024
 island-0.023
 cubes-0.023
 bulbs-0.022
place-0.022
Tokenane
Token ID1531
Feature activation-6.14e-02

Pos logit contributions
 grin+0.265
 amaz+0.263
opl+0.260
 Deal+0.258
severe+0.255
Neg logit contributions
arp-0.406
 island-0.377
 cubes-0.366
 bulbs-0.350
place-0.348
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
opl+0.072
 thank+0.069
 grin+0.069
 amaz+0.067
 Immediately+0.065
Neg logit contributions
arp-0.105
 cubes-0.094
 island-0.092
 bulbs-0.090
place-0.087
Token The
Token ID383
Feature activation-1.25e-02

Pos logit contributions
 Deal+0.016
 grin+0.016
 amaz+0.015
severe+0.015
Aud+0.015
Neg logit contributions
arp-0.027
 island-0.026
 cubes-0.026
 bulbs-0.025
place-0.023
Token aer
Token ID9551
Feature activation-1.22e-02

Pos logit contributions
 thank+0.020
 amaz+0.019
opl+0.019
 bye+0.019
 grin+0.019
Neg logit contributions
arp-0.016
 cubes-0.014
 bulbs-0.014
place-0.013
leaning-0.013
Tokenopl
Token ID20106
Feature activation-2.34e-01

Pos logit contributions
opl+0.000
 grin-0.002
 amaz-0.002
 thank-0.002
 Deal-0.003
Neg logit contributions
arp-0.037
 island-0.035
 cubes-0.035
 bulbs-0.034
place-0.034
Token,
Token ID11
Feature activation-2.65e-02

Pos logit contributions
opl+0.007
 Deal+0.007
severe+0.007
 amaz+0.007
istent+0.007
Neg logit contributions
 island-0.012
arp-0.012
 cubes-0.012
place-0.011
 bulbs-0.011
Token that
Token ID326
Feature activation-3.21e-02

Pos logit contributions
opl+0.041
istent+0.039
severe+0.039
 Immediately+0.038
 grin+0.038
Neg logit contributions
 island-0.038
arp-0.037
 cubes-0.036
place-0.032
 bulbs-0.032
Token is
Token ID318
Feature activation-6.32e-02

Pos logit contributions
 Deal+0.051
 grin+0.048
 amaz+0.047
oled+0.047
severe+0.046
Neg logit contributions
arp-0.048
 island-0.045
 cubes-0.041
 tunnel-0.039
place-0.039
Token our
Token ID674
Feature activation-1.76e-02

Pos logit contributions
 grin+0.065
 amaz+0.064
 Deal+0.061
severe+0.061
opl+0.060
Neg logit contributions
arp-0.119
 island-0.112
 cubes-0.111
 bulbs-0.104
place-0.104
Token aer
Token ID9551
Feature activation-1.18e-02

Pos logit contributions
 Deal+0.038
 grin+0.038
oled+0.037
severe+0.037
 amaz+0.037
Neg logit contributions
arp-0.015
 island-0.014
 cubes-0.012
 bulbs-0.010
place-0.010
Tokenopl
Token ID20106
Feature activation-2.32e-01

Pos logit contributions
 amaz+0.004
 grin+0.003
 Deal+0.003
severe+0.003
adays+0.003
Neg logit contributions
arp-0.031
 island-0.029
 cubes-0.029
place-0.028
 bulbs-0.028
Tokenane
Token ID1531
Feature activation-6.36e-02

Pos logit contributions
 amaz+0.310
 grin+0.306
 Deal+0.299
severe+0.291
adays+0.288
Neg logit contributions
arp-0.378
 island-0.338
 cubes-0.337
 bulbs-0.314
place-0.311
Token,
Token ID11
Feature activation-2.90e-02

Pos logit contributions
 Deal+0.115
 amaz+0.107
oled+0.107
Aud+0.102
 Immediately+0.099
Neg logit contributions
 island-0.089
 cubes-0.077
 ship-0.077
arp-0.076
 cube-0.076
Token give
Token ID1577
Feature activation-2.38e-02

Pos logit contributions
severe+0.050
istent+0.048
umped+0.048
 mastered+0.047
used+0.046
Neg logit contributions
 island-0.041
 ship-0.034
 cubes-0.034
 pirates-0.032
arp-0.032
Token it
Token ID340
Feature activation+8.51e-03

Pos logit contributions
 grin+0.048
 amaz+0.047
istent+0.047
 Deal+0.046
oled+0.045
Neg logit contributions
arp-0.027
 island-0.024
 cubes-0.022
place-0.020
 creatures-0.020
Token back
Token ID736
Feature activation-2.62e-02

Pos logit contributions
arp+0.010
 island+0.010
 cubes+0.009
place+0.008
 bulbs+0.008
Neg logit contributions
oled-0.016
istent-0.016
 amaz-0.016
 Deal-0.016
 grin-0.015
Token,
Token ID11
Feature activation-7.46e-03

Pos logit contributions
 Deal+0.083
severe+0.068
icks+0.067
Aud+0.066
opl+0.065
Neg logit contributions
 island-0.063
place-0.051
 tunnel-0.049
arp-0.049
 underground-0.049
Token Lily
Token ID20037
Feature activation+2.54e-03

Pos logit contributions
opl+0.016
 Deal+0.014
 grin+0.014
istent+0.014
severe+0.014
Neg logit contributions
arp-0.007
 cubes-0.007
 bulbs-0.007
 island-0.007
 pipes-0.006
Token saw
Token ID2497
Feature activation+2.00e-03

Pos logit contributions
 island+0.002
arp+0.002
 cubes+0.002
 ship+0.002
 ships+0.002
Neg logit contributions
 Deal-0.006
opl-0.005
 grin-0.005
icks-0.005
 amaz-0.005
Token many
Token ID867
Feature activation-1.38e-02

Pos logit contributions
 island+0.003
 cubes+0.002
 bulbs+0.002
arp+0.002
 boats+0.002
Neg logit contributions
 Deal-0.004
istent-0.004
 grin-0.004
severe-0.004
used-0.003
Token aer
Token ID9551
Feature activation-1.07e-02

Pos logit contributions
 amaz+0.022
 thank+0.020
 delight+0.020
opl+0.020
 grin+0.019
Neg logit contributions
arp-0.019
 cubes-0.015
 island-0.015
leaning-0.015
 bulbs-0.014
Tokenopl
Token ID20106
Feature activation-2.32e-01

Pos logit contributions
opl+0.000
 grin-0.001
 amaz-0.001
 Deal-0.001
severe-0.001
Neg logit contributions
arp-0.031
 island-0.030
 cubes-0.030
 bulbs-0.029
place-0.029
Tokenanes
Token ID7305
Feature activation-4.31e-02

Pos logit contributions
opl+0.255
 grin+0.248
 amaz+0.247
 Deal+0.245
severe+0.243
Neg logit contributions
arp-0.414
 island-0.392
 cubes-0.371
 bulbs-0.358
place-0.357
Token parked
Token ID19584
Feature activation-1.74e-02

Pos logit contributions
 Deal+0.074
 grin+0.065
 amaz+0.065
severe+0.064
Aud+0.063
Neg logit contributions
 island-0.062
arp-0.061
 cubes-0.056
 bulbs-0.053
place-0.052
Token outside
Token ID2354
Feature activation+1.05e-02

Pos logit contributions
 Deal+0.031
 grin+0.030
 amaz+0.030
severe+0.029
adays+0.029
Neg logit contributions
arp-0.021
 island-0.020
 cubes-0.019
 bulbs-0.018
place-0.016
Token.
Token ID13
Feature activation-4.81e-03

Pos logit contributions
 island+0.010
arp+0.010
 cubes+0.009
 bulbs+0.008
 boats+0.007
Neg logit contributions
 Deal-0.022
severe-0.022
Aud-0.021
 grin-0.021
oled-0.020
Token Her
Token ID2332
Feature activation+3.53e-02

Pos logit contributions
opl+0.006
 grin+0.006
 amaz+0.006
 Deal+0.006
severe+0.006
Neg logit contributions
arp-0.008
 bulbs-0.007
 cubes-0.007
 pipes-0.007
 island-0.007
Token
Token ID198
Feature activation-1.83e-02

Pos logit contributions
 Deal+0.012
 thank+0.012
 amaz+0.012
 Once+0.011
 grin+0.011
Neg logit contributions
arp-0.046
 island-0.044
 cubes-0.043
 bulbs-0.042
place-0.040
TokenThey
Token ID2990
Feature activation+3.63e-03

Pos logit contributions
Aud+0.020
 Deal+0.019
+0.018
adays+0.017
 thank+0.017
Neg logit contributions
arp-0.035
 cubes-0.033
 island-0.032
 crystals-0.032
 bulbs-0.032
Token take
Token ID1011
Feature activation-4.56e-02

Pos logit contributions
 island+0.005
arp+0.005
 cubes+0.005
 bulbs+0.004
 boats+0.004
Neg logit contributions
opl-0.005
 Deal-0.005
 amaz-0.005
 Immediately-0.005
oled-0.005
Token the
Token ID262
Feature activation-1.16e-02

Pos logit contributions
 Deal+0.066
opl+0.065
istent+0.064
 grin+0.064
oled+0.060
Neg logit contributions
arp-0.071
 island-0.067
 cubes-0.065
 boats-0.064
 bulbs-0.062
Token aer
Token ID9551
Feature activation-1.03e-02

Pos logit contributions
 amaz+0.018
 thank+0.018
 goodbye+0.017
opl+0.017
 bye+0.017
Neg logit contributions
arp-0.016
 cubes-0.014
 island-0.013
place-0.013
leaning-0.013
Tokenopl
Token ID20106
Feature activation-2.32e-01

Pos logit contributions
opl+0.000
 grin-0.001
 Deal-0.002
 amaz-0.002
 thank-0.002
Neg logit contributions
arp-0.031
 island-0.030
 cubes-0.029
 bulbs-0.028
place-0.028
Tokenane
Token ID1531
Feature activation-6.23e-02

Pos logit contributions
opl+0.218
used+0.195
oled+0.193
severe+0.189
icks+0.188
Neg logit contributions
arp-0.447
 island-0.444
 cubes-0.416
place-0.409
 bulbs-0.404
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
 amaz+0.080
 grin+0.080
 Deal+0.079
severe+0.076
opl+0.076
Neg logit contributions
arp-0.102
 island-0.094
 cubes-0.091
 bulbs-0.086
place-0.085
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
oled+0.028
istent+0.026
opl+0.026
used+0.025
oped+0.025
Neg logit contributions
 island-0.015
 boats-0.012
 place-0.011
 navy-0.011
 pipes-0.011
Token park
Token ID3952
Feature activation-3.75e-02

Pos logit contributions
 grin+0.027
 Deal+0.026
oled+0.026
 amaz+0.026
istent+0.026
Neg logit contributions
arp-0.018
 island-0.017
 cubes-0.015
 bulbs-0.014
place-0.014
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
 Deal+0.072
severe+0.068
oled+0.065
 grin+0.065
opl+0.065
Neg logit contributions
 island-0.045
arp-0.042
 cubes-0.040
 bulbs-0.035
place-0.035
Token laugh
Token ID6487
Feature activation-3.31e-02

Pos logit contributions
opl+0.024
oled+0.024
 Deal+0.023
 amaz+0.023
istent+0.023
Neg logit contributions
 island-0.019
 cubes-0.019
 jackets-0.018
arp-0.018
 boats-0.018
Token and
Token ID290
Feature activation-1.36e-02

Pos logit contributions
opl+0.065
 Deal+0.064
 amaz+0.061
used+0.061
 grin+0.060
Neg logit contributions
 island-0.032
arp-0.031
 cubes-0.029
 bulbs-0.027
 boats-0.027
Token throw
Token ID3714
Feature activation+4.56e-03

Pos logit contributions
ayed+0.024
inged+0.023
aman+0.022
oled+0.022
opl+0.021
Neg logit contributions
 jackets-0.015
 island-0.014
 boats-0.014
 cubes-0.014
 pans-0.014
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
arp+0.007
 island+0.006
 cubes+0.006
 bulbs+0.006
 pipes+0.006
Neg logit contributions
 Deal-0.007
 grin-0.007
istent-0.006
opl-0.006
 amaz-0.006
Token aer
Token ID9551
Feature activation-1.19e-02

Pos logit contributions
 amaz+0.017
 thank+0.017
opl+0.017
 grin+0.016
severe+0.016
Neg logit contributions
arp-0.014
 island-0.012
 cubes-0.012
place-0.012
leaning-0.011
Tokenopl
Token ID20106
Feature activation-2.32e-01

Pos logit contributions
opl+0.000
 grin-0.001
 amaz-0.001
 Deal-0.001
severe-0.001
Neg logit contributions
arp-0.035
 island-0.034
 cubes-0.033
 bulbs-0.032
place-0.032
Tokenane
Token ID1531
Feature activation-6.33e-02

Pos logit contributions
opl+0.246
severe+0.227
 grin+0.226
 amaz+0.225
oled+0.224
Neg logit contributions
arp-0.421
 island-0.407
 cubes-0.387
place-0.374
 bulbs-0.373
Token in
Token ID287
Feature activation+4.47e-02

Pos logit contributions
 Deal+0.096
 amaz+0.095
 grin+0.095
severe+0.091
opl+0.091
Neg logit contributions
arp-0.090
 island-0.083
 cubes-0.080
 bulbs-0.075
place-0.073
Token the
Token ID262
Feature activation-1.39e-02

Pos logit contributions
arp+0.073
 island+0.069
 cubes+0.066
 bulbs+0.061
place+0.060
Neg logit contributions
 Deal-0.059
 grin-0.058
severe-0.058
oled-0.058
istent-0.056
Token sky
Token ID6766
Feature activation-5.23e-02

Pos logit contributions
 amaz+0.016
 grin+0.016
 Deal+0.016
severe+0.015
opl+0.015
Neg logit contributions
arp-0.024
 island-0.022
 cubes-0.022
 bulbs-0.021
place-0.021
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
 Deal+0.133
severe+0.129
oled+0.126
adays+0.123
istent+0.122
Neg logit contributions
 island-0.030
arp-0.025
 cubes-0.023
 bulbs-0.019
 creatures-0.015
TokenOne
Token ID3198
Feature activation+3.68e-02

Pos logit contributions
 Not+0.016
 practice+0.015
Aud+0.014
+0.014
 la+0.014
Neg logit contributions
arp-0.033
 crystals-0.031
 cubes-0.031
isher-0.030
 treasures-0.030
Token day
Token ID1110
Feature activation-2.35e-02

Pos logit contributions
arp+0.052
 cubes+0.045
 bulbs+0.044
 island+0.042
 pipes+0.041
Neg logit contributions
 bye-0.057
 thank-0.056
 grin-0.052
 amaz-0.052
 goodbye-0.052
Token,
Token ID11
Feature activation-2.27e-02

Pos logit contributions
 amaz+0.015
 grin+0.015
 Deal+0.014
 thank+0.014
severe+0.014
Neg logit contributions
arp-0.053
 island-0.050
 cubes-0.049
 bulbs-0.047
place-0.047
Token the
Token ID262
Feature activation-1.51e-02

Pos logit contributions
 amaz+0.020
 grin+0.019
 Deal+0.019
 thank+0.018
severe+0.018
Neg logit contributions
arp-0.047
 island-0.043
 cubes-0.042
place-0.040
 bulbs-0.040
Token aer
Token ID9551
Feature activation-1.17e-02

Pos logit contributions
 thank+0.024
 bye+0.023
opl+0.023
 amaz+0.023
 grin+0.022
Neg logit contributions
arp-0.021
 cubes-0.017
 bulbs-0.017
 island-0.016
place-0.016
Tokenopl
Token ID20106
Feature activation-2.32e-01

Pos logit contributions
opl+0.000
 grin-0.002
 amaz-0.002
 thank-0.002
oled-0.002
Neg logit contributions
arp-0.035
 island-0.034
 cubes-0.033
 bulbs-0.033
place-0.032
Tokenane
Token ID1531
Feature activation-6.28e-02

Pos logit contributions
opl+0.236
 amaz+0.215
oled+0.213
severe+0.212
used+0.212
Neg logit contributions
arp-0.436
 island-0.414
 cubes-0.398
place-0.389
 bulbs-0.387
Token saw
Token ID2497
Feature activation-8.93e-04

Pos logit contributions
 amaz+0.094
 grin+0.093
 Deal+0.093
severe+0.090
opl+0.090
Neg logit contributions
arp-0.089
 island-0.081
 cubes-0.078
 bulbs-0.073
place-0.072
Token a
Token ID257
Feature activation-2.66e-02

Pos logit contributions
 Deal+0.001
 grin+0.001
istent+0.001
severe+0.001
opl+0.001
Neg logit contributions
 island-0.002
arp-0.002
 cubes-0.002
 bulbs-0.001
 pipes-0.001
Token little
Token ID1310
Feature activation-4.14e-02

Pos logit contributions
 amaz+0.032
 grin+0.032
 thank+0.031
 Deal+0.030
severe+0.030
Neg logit contributions
arp-0.046
 island-0.041
 cubes-0.041
 bulbs-0.039
place-0.038
Token girl
Token ID2576
Feature activation-2.23e-02

Pos logit contributions
 amaz+0.070
 grin+0.069
 thank+0.067
 bye+0.065
severe+0.065
Neg logit contributions
arp-0.048
 cubes-0.041
 island-0.039
leaning-0.038
place-0.037
Token help
Token ID1037
Feature activation+4.76e-02

Pos logit contributions
 amaz+0.049
 grin+0.048
 Deal+0.048
opl+0.048
severe+0.048
Neg logit contributions
arp-0.054
 island-0.049
 cubes-0.049
 bulbs-0.046
place-0.045
Token you
Token ID345
Feature activation-2.82e-02

Pos logit contributions
arp+0.063
 cubes+0.060
 island+0.056
place+0.053
 bulbs+0.052
Neg logit contributions
 amaz-0.081
 grin-0.079
Aud-0.078
opl-0.077
oled-0.077
Token paint
Token ID7521
Feature activation+5.94e-03

Pos logit contributions
 Deal+0.046
 grin+0.046
oled+0.046
 amaz+0.046
Aud+0.046
Neg logit contributions
arp-0.036
 island-0.033
 cubes-0.032
 bulbs-0.031
place-0.030
Token the
Token ID262
Feature activation-1.38e-02

Pos logit contributions
 cubes+0.008
arp+0.008
 island+0.007
 bulbs+0.007
place+0.007
Neg logit contributions
oled-0.011
 grin-0.010
 Deal-0.010
istent-0.010
urance-0.010
Token aer
Token ID9551
Feature activation-1.05e-02

Pos logit contributions
 amaz+0.026
 grin+0.025
opl+0.025
 thank+0.025
 Deal+0.025
Neg logit contributions
arp-0.014
 island-0.012
 cubes-0.012
place-0.011
 bulbs-0.011
Tokenopl
Token ID20106
Feature activation-2.31e-01

Pos logit contributions
 amaz+0.000
opl+0.000
 grin-0.000
 Deal-0.000
severe-0.001
Neg logit contributions
arp-0.030
 island-0.029
 cubes-0.028
 bulbs-0.028
place-0.028
Tokenane
Token ID1531
Feature activation-6.01e-02

Pos logit contributions
 amaz+0.283
 grin+0.281
 Deal+0.277
severe+0.270
opl+0.269
Neg logit contributions
arp-0.391
 island-0.358
 cubes-0.350
 bulbs-0.331
place-0.329
Token?"
Token ID1701
Feature activation-1.44e-02

Pos logit contributions
oled+0.139
 Deal+0.135
Aud+0.129
 amaz+0.128
 Jeffrey+0.125
Neg logit contributions
 island-0.053
 cubes-0.044
arp-0.042
 cube-0.041
place-0.039
Token Tim
Token ID5045
Feature activation+8.21e-03

Pos logit contributions
severe+0.020
 amaz+0.019
opl+0.019
 Deal+0.019
Aud+0.018
Neg logit contributions
arp-0.022
 cubes-0.021
 island-0.020
 bulbs-0.019
place-0.018
Token said
Token ID531
Feature activation-2.85e-02

Pos logit contributions
arp+0.008
 cubes+0.008
 cube+0.007
 island+0.007
 boy+0.006
Neg logit contributions
opl-0.015
adays-0.015
 amaz-0.015
severe-0.015
 Deal-0.015
Token,
Token ID11
Feature activation-2.37e-02

Pos logit contributions
opl+0.045
Aud+0.039
 amaz+0.039
 Deal+0.039
severe+0.037
Neg logit contributions
 cubes-0.041
arp-0.039
 cube-0.039
 bulbs-0.036
 island-0.036
Token began
Token ID2540
Feature activation-7.42e-03

Pos logit contributions
 Deal+0.023
oled+0.022
istent+0.020
opl+0.020
inged+0.020
Neg logit contributions
 shells-0.012
 boats-0.012
 bulbs-0.011
 ships-0.011
 island-0.011
Token flying
Token ID7348
Feature activation-6.87e-02

Pos logit contributions
 Deal+0.018
adays+0.015
istent+0.015
oled+0.015
Aud+0.015
Neg logit contributions
 cubes-0.006
 creatures-0.005
 island-0.005
 bulbs-0.005
 boats-0.005
Token around
Token ID1088
Feature activation-9.13e-03

Pos logit contributions
 Deal+0.148
 grin+0.133
oled+0.131
istent+0.130
 amaz+0.128
Neg logit contributions
arp-0.076
 island-0.071
 bulbs-0.066
 cubes-0.064
 creatures-0.061
Token making
Token ID1642
Feature activation-1.88e-02

Pos logit contributions
 Deal+0.019
severe+0.018
 grin+0.017
icks+0.017
istent+0.017
Neg logit contributions
 island-0.010
arp-0.010
 cubes-0.010
 bulbs-0.009
 creatures-0.009
Token aer
Token ID9551
Feature activation-4.42e-03

Pos logit contributions
 Deal+0.042
oled+0.037
used+0.037
+0.037
istent+0.036
Neg logit contributions
 boats-0.021
 island-0.021
 creatures-0.019
 bulbs-0.019
 shells-0.018
Tokenopl
Token ID20106
Feature activation-2.31e-01

Pos logit contributions
 amaz+0.002
 grin+0.002
 Deal+0.002
 thank+0.002
adays+0.002
Neg logit contributions
arp-0.011
 cubes-0.010
 island-0.010
place-0.010
 bulbs-0.009
Tokenane
Token ID1531
Feature activation-5.33e-02

Pos logit contributions
 amaz+0.493
 delight+0.466
 grin+0.466
 goodbye+0.443
 thank+0.441
Neg logit contributions
arp-0.242
 cubes-0.215
we-0.187
 bulbs-0.161
place-0.160
Token noises
Token ID26782
Feature activation-3.14e-02

Pos logit contributions
 Deal+0.110
oled+0.097
 Heidi+0.093
Aud+0.093
used+0.092
Neg logit contributions
arp-0.064
 island-0.062
 bulbs-0.053
 creatures-0.053
 cubes-0.053
Token.
Token ID13
Feature activation-6.26e-03

Pos logit contributions
 Deal+0.079
 amaz+0.068
 Majesty+0.068
adays+0.066
severe+0.066
Neg logit contributions
 island-0.022
arp-0.022
 cubes-0.019
 boats-0.017
 creatures-0.016
Token Jack
Token ID3619
Feature activation-1.37e-02

Pos logit contributions
 amaz+0.010
 grin+0.010
severe+0.010
icks+0.010
opl+0.010
Neg logit contributions
arp-0.007
 cubes-0.006
B-0.006
Tim-0.006
Kids-0.005
Token soon
Token ID2582
Feature activation-3.17e-02

Pos logit contributions
 Deal+0.032
opl+0.027
adays+0.027
icks+0.026
 amaz+0.026
Neg logit contributions
 island-0.012
arp-0.011
 ship-0.010
 cubes-0.010
 boats-0.010
Token there
Token ID612
Feature activation+1.50e-03

Pos logit contributions
 amaz+0.050
 grin+0.049
 Deal+0.049
 thank+0.048
severe+0.048
Neg logit contributions
arp-0.040
 island-0.035
 cubes-0.033
place-0.031
 bulbs-0.031
Token was
Token ID373
Feature activation-2.80e-02

Pos logit contributions
arp+0.002
 island+0.002
 cubes+0.001
place+0.001
 bulbs+0.001
Neg logit contributions
 Deal-0.003
severe-0.003
 grin-0.003
Aud-0.003
opl-0.003
Token a
Token ID257
Feature activation-2.94e-02

Pos logit contributions
 amaz+0.022
 grin+0.022
 Deal+0.021
severe+0.021
opl+0.020
Neg logit contributions
arp-0.060
 island-0.056
 cubes-0.055
 bulbs-0.052
place-0.052
Token humble
Token ID19695
Feature activation-1.00e-02

Pos logit contributions
 thank+0.029
 grin+0.029
 bye+0.027
 amaz+0.027
 sorry+0.025
Neg logit contributions
arp-0.058
 cubes-0.051
 island-0.051
place-0.050
 bulbs-0.050
Token aer
Token ID9551
Feature activation-5.69e-03

Pos logit contributions
 Deal+0.017
 amaz+0.017
severe+0.016
opl+0.016
adays+0.016
Neg logit contributions
arp-0.013
 island-0.012
 cubes-0.011
 bulbs-0.011
place-0.010
Tokenopl
Token ID20106
Feature activation-2.31e-01

Pos logit contributions
opl+0.000
 grin-0.000
 amaz-0.000
 thank-0.000
 Deal-0.000
Neg logit contributions
arp-0.016
 island-0.016
 cubes-0.016
 bulbs-0.015
place-0.015
Tokenane
Token ID1531
Feature activation-5.85e-02

Pos logit contributions
 grin+0.252
opl+0.252
 amaz+0.249
 Deal+0.245
severe+0.243
Neg logit contributions
arp-0.411
 island-0.385
 cubes-0.372
 bulbs-0.356
place-0.355
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
opl+0.068
 thank+0.066
 grin+0.065
 amaz+0.063
 bye+0.062
Neg logit contributions
arp-0.100
 cubes-0.090
 island-0.088
 bulbs-0.085
place-0.083
Token He
Token ID679
Feature activation-2.59e-02

Pos logit contributions
 Deal+0.014
 grin+0.013
oled+0.013
 amaz+0.013
severe+0.013
Neg logit contributions
arp-0.026
 island-0.025
 cubes-0.024
 bulbs-0.024
place-0.022
Token lived
Token ID5615
Feature activation-3.48e-04

Pos logit contributions
 thank+0.033
opl+0.032
 grin+0.031
severe+0.031
 bye+0.030
Neg logit contributions
arp-0.043
 cubes-0.037
 island-0.037
 bulbs-0.036
place-0.034
Token on
Token ID319
Feature activation-9.76e-03

Pos logit contributions
 grin+0.001
 amaz+0.001
 Deal+0.001
severe+0.000
 thank+0.000
Neg logit contributions
arp-0.001
 island-0.000
 cubes-0.000
place-0.000
 bulbs-0.000
Token,
Token ID11
Feature activation-2.22e-02

Pos logit contributions
 Deal+0.086
severe+0.083
Aud+0.078
 amaz+0.075
oled+0.073
Neg logit contributions
 cubes-0.051
 island-0.050
arp-0.043
 ship-0.042
 cube-0.042
Token look
Token ID804
Feature activation+1.04e-02

Pos logit contributions
opl+0.038
 grin+0.035
istent+0.035
 Deal+0.035
oled+0.035
Neg logit contributions
arp-0.030
 island-0.030
 cubes-0.027
 bulbs-0.025
 tunnel-0.024
Token!
Token ID0
Feature activation-6.09e-02

Pos logit contributions
arp+0.014
 island+0.013
 cubes+0.013
 bulbs+0.012
 crystals+0.011
Neg logit contributions
opl-0.017
 Deal-0.017
severe-0.016
-0.016
adays-0.016
Token An
Token ID1052
Feature activation+5.99e-02

Pos logit contributions
 grin+0.092
opl+0.089
 amaz+0.082
zing+0.081
Aud+0.079
Neg logit contributions
arp-0.089
 island-0.073
 cubes-0.072
 bulbs-0.070
 cube-0.067
Token aer
Token ID9551
Feature activation-7.30e-03

Pos logit contributions
arp+0.067
 cubes+0.063
 bulbs+0.057
 collections+0.057
 island+0.056
Neg logit contributions
opl-0.104
 amaz-0.099
 thank-0.097
istent-0.094
 grin-0.094
Tokenopl
Token ID20106
Feature activation-2.31e-01

Pos logit contributions
 amaz+0.003
 Deal+0.002
 grin+0.002
severe+0.002
adays+0.002
Neg logit contributions
arp-0.019
 island-0.018
 cubes-0.018
place-0.017
 bulbs-0.017
Tokenane
Token ID1531
Feature activation-5.79e-02

Pos logit contributions
 amaz+0.323
 grin+0.320
 Deal+0.313
severe+0.302
adays+0.300
Neg logit contributions
arp-0.367
 island-0.322
 cubes-0.320
 bulbs-0.298
place-0.292
Token!"
Token ID2474
Feature activation-6.23e-02

Pos logit contributions
 Deal+0.112
 amaz+0.096
oled+0.096
severe+0.094
 grin+0.094
Neg logit contributions
 island-0.078
arp-0.068
 tunnel-0.065
 ship-0.063
 cube-0.060
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
opl+0.114
severe+0.102
upid+0.097
 amaz+0.097
rou+0.096
Neg logit contributions
arp-0.058
 boy-0.052
 pans-0.051
 jackets-0.051
Stars-0.050
Token
Token ID198
Feature activation-1.10e-02

Pos logit contributions
 amaz+0.017
opl+0.016
 grin+0.016
severe+0.016
istent+0.016
Neg logit contributions
arp-0.013
place-0.010
 island-0.010
B-0.010
P-0.009
TokenHer
Token ID9360
Feature activation+4.78e-02

Pos logit contributions
opl+0.018
 grin+0.018
 amaz+0.017
severe+0.017
istent+0.016
Neg logit contributions
arp-0.014
 island-0.012
place-0.012
leaning-0.011
 bulbs-0.010
Token saw
Token ID2497
Feature activation+4.54e-03

Pos logit contributions
arp+0.058
 island+0.054
 cubes+0.051
place+0.047
 tunnel+0.046
Neg logit contributions
 Deal-0.107
 amaz-0.102
opl-0.099
 grin-0.098
adays-0.096
Token Lily
Token ID20037
Feature activation+2.13e-03

Pos logit contributions
 cubes+0.007
arp+0.007
 island+0.006
 bulbs+0.006
 pipes+0.006
Neg logit contributions
 Deal-0.007
istent-0.007
 grin-0.007
severe-0.007
adays-0.006
Token with
Token ID351
Feature activation-2.74e-02

Pos logit contributions
 island+0.003
 cubes+0.003
arp+0.003
 bulbs+0.003
place+0.003
Neg logit contributions
 Deal-0.003
severe-0.003
Aud-0.003
opl-0.003
adays-0.003
Token his
Token ID465
Feature activation+1.29e-02

Pos logit contributions
adays+0.049
istent+0.049
oled+0.048
 Majesty+0.048
 Deal+0.047
Neg logit contributions
 cubes-0.033
 bulbs-0.029
 shells-0.029
 pipes-0.028
 crystals-0.028
Token aer
Token ID9551
Feature activation-1.00e-02

Pos logit contributions
arp+0.015
 cubes+0.015
 island+0.015
 bulbs+0.013
place+0.013
Neg logit contributions
adays-0.022
oled-0.022
severe-0.022
 Deal-0.022
Aud-0.021
Tokenopl
Token ID20106
Feature activation-2.31e-01

Pos logit contributions
 amaz+0.003
 grin+0.002
 Deal+0.002
severe+0.002
adays+0.002
Neg logit contributions
arp-0.027
 cubes-0.025
 island-0.025
place-0.024
 bulbs-0.024
Tokenane
Token ID1531
Feature activation-5.93e-02

Pos logit contributions
 grin+0.263
 amaz+0.263
opl+0.260
 Deal+0.259
severe+0.255
Neg logit contributions
arp-0.402
 island-0.376
 cubes-0.361
 bulbs-0.346
place-0.344
Token.
Token ID13
Feature activation-5.11e-03

Pos logit contributions
 Deal+0.111
oled+0.100
 amaz+0.100
Aud+0.098
severe+0.098
Neg logit contributions
 island-0.070
arp-0.068
 cubes-0.063
place-0.060
 bulbs-0.060
Token He
Token ID679
Feature activation-2.32e-02

Pos logit contributions
 amaz+0.007
 Deal+0.007
opl+0.007
severe+0.007
used+0.007
Neg logit contributions
arp-0.008
 cubes-0.008
 bulbs-0.007
 island-0.007
 pipes-0.007
Token was
Token ID373
Feature activation-2.44e-02

Pos logit contributions
 amaz+0.037
 Deal+0.037
 grin+0.037
opl+0.036
severe+0.036
Neg logit contributions
arp-0.030
 island-0.027
 cubes-0.027
 bulbs-0.025
place-0.025
Token not
Token ID407
Feature activation-1.41e-02

Pos logit contributions
adays+0.049
severe+0.047
 Deal+0.046
istent+0.045
 amaz+0.044
Neg logit contributions
 underground-0.023
 cubes-0.022
 island-0.022
 bulbs-0.021
 cube-0.019
Token are
Token ID389
Feature activation-3.17e-02

Pos logit contributions
opl+0.010
 amaz+0.010
Aud+0.010
 Deal+0.010
 grin+0.010
Neg logit contributions
arp-0.013
 island-0.013
 cubes-0.013
place-0.012
 bulbs-0.011
Token twins
Token ID20345
Feature activation+8.18e-03

Pos logit contributions
 amaz+0.044
severe+0.043
 grin+0.043
 Deal+0.043
opl+0.042
Neg logit contributions
arp-0.046
 island-0.045
 cubes-0.044
 bulbs-0.042
place-0.040
Token?
Token ID30
Feature activation-2.12e-02

Pos logit contributions
arp+0.010
 island+0.009
 cubes+0.009
place+0.009
 bulbs+0.008
Neg logit contributions
 amaz-0.014
 Deal-0.014
opl-0.014
severe-0.014
adays-0.013
Token You
Token ID921
Feature activation-4.72e-02

Pos logit contributions
 grin+0.030
 amaz+0.030
opl+0.028
severe+0.027
istent+0.027
Neg logit contributions
arp-0.031
 cubes-0.030
 bulbs-0.029
 island-0.027
 pipes-0.026
Token look
Token ID804
Feature activation+3.30e-02

Pos logit contributions
 amaz+0.056
 grin+0.054
 Deal+0.054
opl+0.054
severe+0.051
Neg logit contributions
arp-0.081
 island-0.078
 cubes-0.075
place-0.072
 bulbs-0.072
Token very
Token ID845
Feature activation+8.45e-02

Pos logit contributions
 cubes+0.034
 island+0.032
arp+0.031
place+0.030
 ships+0.029
Neg logit contributions
opl-0.062
chief-0.058
Aud-0.057
adays-0.057
 Deal-0.057
Token unique
Token ID3748
Feature activation+1.36e-02

Pos logit contributions
 cubes+0.098
arp+0.093
 island+0.093
 bulbs+0.088
place+0.085
Neg logit contributions
 amaz-0.146
severe-0.145
 Deal-0.141
opl-0.141
 grin-0.140
Token.
Token ID13
Feature activation+9.25e-03

Pos logit contributions
arp+0.014
 cubes+0.014
 island+0.013
 bulbs+0.012
 crystals+0.012
Neg logit contributions
 Deal-0.026
 amaz-0.026
Aud-0.026
opl-0.026
 grin-0.025
Token Do
Token ID2141
Feature activation-1.56e-03

Pos logit contributions
arp+0.016
 cubes+0.015
 island+0.014
 bulbs+0.014
place+0.014
Neg logit contributions
 grin-0.011
 amaz-0.011
severe-0.010
opl-0.010
oled-0.010
Token you
Token ID345
Feature activation-2.99e-03

Pos logit contributions
 amaz+0.002
 grin+0.002
severe+0.002
 Deal+0.002
opl+0.002
Neg logit contributions
arp-0.002
 island-0.002
 cubes-0.002
place-0.002
 bulbs-0.002
Token want
Token ID765
Feature activation-3.65e-02

Pos logit contributions
 amaz+0.004
opl+0.004
adays+0.004
Aud+0.004
ishly+0.003
Neg logit contributions
arp-0.005
 island-0.005
 cubes-0.004
place-0.004
 bulbs-0.004
Token have
Token ID423
Feature activation+3.26e-03

Pos logit contributions
 Deal+0.005
 amaz+0.005
severe+0.005
oled+0.005
 Immediately+0.005
Neg logit contributions
arp-0.007
 island-0.007
 cubes-0.007
 bulbs-0.007
place-0.006
Token fun
Token ID1257
Feature activation+2.22e-02

Pos logit contributions
arp+0.005
 island+0.005
 cubes+0.004
 bulbs+0.004
place+0.004
Neg logit contributions
 amaz-0.004
 grin-0.004
 Deal-0.004
 thank-0.004
severe-0.004
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
arp+0.034
 island+0.031
 cubes+0.030
 bulbs+0.028
place+0.028
Neg logit contributions
 amaz-0.031
 grin-0.031
 Deal-0.030
severe-0.030
opl-0.030
Token<|endoftext|>
Token ID50256
Feature activation+3.03e-02

Pos logit contributions
 Deal+0.011
 thank+0.011
 amaz+0.011
 grin+0.010
adays+0.010
Neg logit contributions
arp-0.028
 island-0.027
 cubes-0.025
place-0.024
 bulbs-0.024
TokenL
Token ID43
Feature activation-4.06e-03

Pos logit contributions
arp+0.049
 island+0.045
 cubes+0.044
 bulbs+0.042
place+0.041
Neg logit contributions
 amaz-0.038
 grin-0.038
 Deal-0.038
opl-0.037
severe-0.037
Tokenily
Token ID813
Feature activation+8.53e-02

Pos logit contributions
icks+0.005
 Deal+0.005
adays+0.005
 Josh+0.005
 Tom+0.005
Neg logit contributions
arp-0.006
 island-0.006
 bulbs-0.006
place-0.006
 cubes-0.005
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
arp+0.122
 island+0.120
 cubes+0.112
 bulbs+0.104
place+0.102
Neg logit contributions
 Deal-0.128
 amaz-0.122
severe-0.121
 grin-0.120
istent-0.117
Token Sam
Token ID3409
Feature activation-2.92e-02

Pos logit contributions
opl+0.024
 amaz+0.022
oled+0.022
severe+0.022
istent+0.022
Neg logit contributions
 island-0.028
arp-0.028
 cubes-0.027
 bulbs-0.025
place-0.024
Token were
Token ID547
Feature activation-1.82e-02

Pos logit contributions
 Deal+0.035
 amaz+0.034
 grin+0.033
severe+0.033
opl+0.032
Neg logit contributions
arp-0.049
 island-0.048
 cubes-0.046
place-0.043
 bulbs-0.042
Token twins
Token ID20345
Feature activation-1.32e-02

Pos logit contributions
 amaz+0.028
severe+0.028
 grin+0.027
adays+0.027
 Immediately+0.027
Neg logit contributions
 cubes-0.024
arp-0.024
 island-0.023
 bulbs-0.021
place-0.020
Token who
Token ID508
Feature activation+6.50e-02

Pos logit contributions
 grin+0.017
 thank+0.017
 amaz+0.017
 Deal+0.016
opl+0.016
Neg logit contributions
arp-0.022
 island-0.019
 cubes-0.019
 bulbs-0.018
place-0.018
Token bumped
Token ID38034
Feature activation+4.11e-02

Pos logit contributions
 amaz+0.017
 grin+0.017
 thank+0.017
severe+0.016
 Deal+0.016
Neg logit contributions
arp-0.023
 island-0.020
 cubes-0.020
 bulbs-0.019
place-0.019
Token into
Token ID656
Feature activation+1.73e-02

Pos logit contributions
arp+0.066
 island+0.060
 cubes+0.059
 bulbs+0.055
place+0.054
Neg logit contributions
 amaz-0.055
 grin-0.054
 Deal-0.054
opl-0.052
severe-0.052
Token a
Token ID257
Feature activation-1.03e-02

Pos logit contributions
 cubes+0.027
arp+0.025
 pipes+0.024
 island+0.023
 bulbs+0.022
Neg logit contributions
severe-0.027
 Deal-0.027
istent-0.027
opl-0.027
 grin-0.027
Token table
Token ID3084
Feature activation-3.05e-02

Pos logit contributions
 Deal+0.019
severe+0.019
istent+0.019
used+0.018
adays+0.018
Neg logit contributions
arp-0.012
 island-0.011
 cubes-0.011
 tunnel-0.010
 bulbs-0.009
Token and
Token ID290
Feature activation+1.70e-03

Pos logit contributions
 Deal+0.059
severe+0.057
Aud+0.056
istent+0.053
adays+0.053
Neg logit contributions
 island-0.034
 cubes-0.034
arp-0.033
 pipes-0.029
 tunnel-0.027
Token knocked
Token ID13642
Feature activation+7.73e-02

Pos logit contributions
arp+0.002
 cubes+0.002
 island+0.002
 pipes+0.002
 bulbs+0.002
Neg logit contributions
 Deal-0.003
opl-0.003
 grin-0.003
 amaz-0.003
istent-0.003
Token over
Token ID625
Feature activation-4.17e-02

Pos logit contributions
arp+0.139
 island+0.128
 cubes+0.125
 bulbs+0.119
place+0.118
Neg logit contributions
 amaz-0.087
 grin-0.086
 Deal-0.085
severe-0.083
opl-0.083
Token a
Token ID257
Feature activation-9.68e-03

Pos logit contributions
 Deal+0.054
opl+0.054
 grin+0.054
severe+0.053
istent+0.053
Neg logit contributions
arp-0.070
 cubes-0.069
 island-0.066
 bulbs-0.061
place-0.060
Token v
Token ID410
Feature activation-3.59e-02

Pos logit contributions
 Deal+0.017
severe+0.017
opl+0.017
istent+0.017
used+0.017
Neg logit contributions
arp-0.012
 island-0.011
 cubes-0.011
 bulbs-0.009
place-0.009
Tokenase
Token ID589
Feature activation+1.08e-02

Pos logit contributions
opl+0.056
 grin+0.055
 Deal+0.053
 amaz+0.053
oled+0.053
Neg logit contributions
arp-0.045
 island-0.044
 bulbs-0.041
 cubes-0.040
place-0.039
Token.
Token ID13
Feature activation+8.90e-03

Pos logit contributions
arp+0.012
 island+0.010
 cubes+0.010
 bulbs+0.009
 pipes+0.009
Neg logit contributions
 Deal-0.021
 amaz-0.020
severe-0.020
 grin-0.020
 Majesty-0.020
Token the
Token ID262
Feature activation+1.82e-02

Pos logit contributions
 island+0.043
 shells+0.040
 bulbs+0.040
 boats+0.038
 creatures+0.036
Neg logit contributions
opl-0.086
istent-0.082
oled-0.082
 Deal-0.080
urance-0.075
Token butterfly
Token ID35113
Feature activation-3.28e-03

Pos logit contributions
 island+0.020
arp+0.019
 cubes+0.018
 bulbs+0.018
 crystals+0.016
Neg logit contributions
oled-0.034
istent-0.034
adays-0.034
opl-0.034
severe-0.034
Token.
Token ID13
Feature activation+2.92e-02

Pos logit contributions
 Deal+0.007
 amaz+0.007
opl+0.007
Sean+0.006
severe+0.006
Neg logit contributions
 island-0.003
 bulbs-0.003
fish-0.002
 creatures-0.002
 boats-0.002
Token They
Token ID1119
Feature activation+2.86e-02

Pos logit contributions
arp+0.036
 cubes+0.033
 bulbs+0.033
 island+0.032
Tim+0.030
Neg logit contributions
 grin-0.044
 amaz-0.044
zing-0.043
severe-0.043
opl-0.042
Token felt
Token ID2936
Feature activation+2.72e-02

Pos logit contributions
 island+0.031
 boats+0.027
 bulbs+0.026
 shells+0.025
arp+0.023
Neg logit contributions
 Deal-0.056
opl-0.055
ER-0.051
inged-0.050
oled-0.050
Token very
Token ID845
Feature activation+9.26e-02

Pos logit contributions
 island+0.024
 creatures+0.023
place+0.023
 bulbs+0.023
 underground+0.022
Neg logit contributions
ER-0.054
 Deal-0.053
opl-0.053
Aud-0.053
istent-0.053
Token bad
Token ID2089
Feature activation+2.17e-02

Pos logit contributions
 island+0.094
place+0.087
 creatures+0.084
 bulbs+0.083
arp+0.083
Neg logit contributions
 Deal-0.176
Aud-0.170
opl-0.169
 sixty-0.168
 amaz-0.167
Token for
Token ID329
Feature activation-3.88e-02

Pos logit contributions
arp+0.024
 island+0.023
 cubes+0.022
 bulbs+0.020
 pipes+0.020
Neg logit contributions
 Deal-0.041
 amaz-0.039
severe-0.038
 grin-0.038
Aud-0.038
Token what
Token ID644
Feature activation+3.39e-02

Pos logit contributions
severe+0.066
opl+0.065
 grin+0.062
Aud+0.062
 Deal+0.061
Neg logit contributions
 island-0.051
 bulbs-0.048
 cubes-0.048
 pipes-0.045
 boats-0.044
Token they
Token ID484
Feature activation+1.69e-02

Pos logit contributions
arp+0.040
 island+0.038
 cubes+0.037
 bulbs+0.035
place+0.033
Neg logit contributions
 Deal-0.059
severe-0.058
opl-0.058
 amaz-0.058
 grin-0.057
Token did
Token ID750
Feature activation-4.41e-03

Pos logit contributions
 island+0.017
arp+0.017
 cubes+0.015
place+0.015
 bulbs+0.014
Neg logit contributions
 amaz-0.032
 Deal-0.032
opl-0.031
severe-0.031
 grin-0.031
Token of
Token ID286
Feature activation+7.09e-03

Pos logit contributions
 Deal+0.046
 amaz+0.044
 grin+0.043
used+0.043
severe+0.042
Neg logit contributions
arp-0.035
 cubes-0.030
place-0.030
 island-0.030
 bulbs-0.027
Token hugs
Token ID40657
Feature activation-4.67e-02

Pos logit contributions
arp+0.010
 cubes+0.010
 island+0.009
place+0.009
 bulbs+0.009
Neg logit contributions
 amaz-0.010
 grin-0.010
 Deal-0.010
Aud-0.010
adays-0.010
Token.
Token ID13
Feature activation+2.96e-02

Pos logit contributions
 Deal+0.113
 amaz+0.107
 Majesty+0.106
used+0.104
severe+0.103
Neg logit contributions
arp-0.034
 cubes-0.027
 jackets-0.027
place-0.026
 island-0.026
Token Everyone
Token ID11075
Feature activation+2.33e-02

Pos logit contributions
 cubes+0.036
arp+0.036
 island+0.034
 cube+0.031
 bulbs+0.031
Neg logit contributions
severe-0.048
Aud-0.045
hered-0.044
oled-0.043
 la-0.042
Token was
Token ID373
Feature activation+9.47e-03

Pos logit contributions
arp+0.038
 island+0.034
 cubes+0.034
 bulbs+0.032
place+0.031
Neg logit contributions
 grin-0.030
 amaz-0.030
 thank-0.029
adays-0.028
 Immediately-0.028
Token very
Token ID845
Feature activation+1.00e-01

Pos logit contributions
 island+0.007
 cubes+0.006
 underground+0.006
 organized+0.005
arp+0.005
Neg logit contributions
 Deal-0.021
severe-0.020
adays-0.019
opl-0.019
 reflex-0.019
Token happy
Token ID3772
Feature activation+2.63e-02

Pos logit contributions
arp+0.100
 island+0.100
 cubes+0.098
place+0.095
 cube+0.089
Neg logit contributions
opl-0.188
severe-0.181
 Deal-0.180
Aud-0.174
chief-0.172
Token to
Token ID284
Feature activation+2.35e-02

Pos logit contributions
arp+0.036
 island+0.035
 cubes+0.034
 bulbs+0.031
place+0.030
Neg logit contributions
 Deal-0.043
severe-0.041
opl-0.040
 amaz-0.039
 grin-0.039
Token see
Token ID766
Feature activation+7.12e-02

Pos logit contributions
 island+0.032
arp+0.031
place+0.027
 occasion+0.025
 cubes+0.024
Neg logit contributions
 amaz-0.035
oled-0.035
severe-0.034
Aud-0.034
opl-0.033
Token how
Token ID703
Feature activation+4.87e-02

Pos logit contributions
 island+0.089
arp+0.086
place+0.082
 cubes+0.080
 creatures+0.074
Neg logit contributions
 Deal-0.129
severe-0.128
istent-0.127
 grin-0.127
oled-0.124
Token brave
Token ID14802
Feature activation+4.63e-02

Pos logit contributions
arp+0.069
 cubes+0.068
place+0.060
 island+0.059
 creatures+0.057
Neg logit contributions
 Deal-0.078
opl-0.076
 amaz-0.075
 grin-0.071
severe-0.070
Token re
Token ID302
Feature activation+1.06e-02

Pos logit contributions
arp+0.051
 cubes+0.046
 island+0.044
 bulbs+0.043
place+0.042
Neg logit contributions
 amaz-0.043
 thank-0.042
 grin-0.042
 Deal-0.042
opl-0.041
Tokenind
Token ID521
Feature activation-3.98e-02

Pos logit contributions
arp+0.012
 cubes+0.011
 island+0.011
 bulbs+0.010
place+0.010
Neg logit contributions
opl-0.018
 amaz-0.018
 grin-0.017
 Deal-0.017
used-0.017
Tokeneer
Token ID28153
Feature activation+8.42e-03

Pos logit contributions
 amaz+0.079
 grin+0.079
 Deal+0.078
opl+0.077
severe+0.077
Neg logit contributions
arp-0.037
 island-0.031
 cubes-0.030
 bulbs-0.026
place-0.026
Token laughs
Token ID22051
Feature activation-4.25e-02

Pos logit contributions
 island+0.011
 cubes+0.010
 ship+0.009
 tunnel+0.009
arp+0.009
Neg logit contributions
istent-0.014
oled-0.013
Aud-0.013
 Deal-0.013
severe-0.012
Token and
Token ID290
Feature activation+9.82e-03

Pos logit contributions
opl+0.085
 amaz+0.083
adays+0.082
used+0.081
 Deal+0.081
Neg logit contributions
arp-0.036
 island-0.032
 cubes-0.032
 bulbs-0.028
 underground-0.026
Token n
Token ID299
Feature activation+2.22e-02

Pos logit contributions
 jackets+0.012
 boats+0.012
 shells+0.011
 island+0.011
 rocks+0.010
Neg logit contributions
istent-0.015
oled-0.014
urance-0.014
opl-0.014
 Deal-0.014
Tokenuzz
Token ID4715
Feature activation+1.68e-02

Pos logit contributions
arp+0.027
 island+0.023
 cubes+0.023
 bulbs+0.021
place+0.020
Neg logit contributions
 grin-0.039
 thank-0.039
 amaz-0.039
severe-0.038
 Deal-0.038
Tokenles
Token ID829
Feature activation-2.28e-02

Pos logit contributions
arp+0.019
 cubes+0.016
 island+0.016
 bulbs+0.015
 boats+0.014
Neg logit contributions
 amaz-0.032
 Deal-0.031
 grin-0.030
 Once-0.030
istent-0.029
Token them
Token ID606
Feature activation+3.46e-02

Pos logit contributions
 Deal+0.053
istent+0.051
 amaz+0.050
aman+0.050
mmm+0.049
Neg logit contributions
 boats-0.016
 cubes-0.013
 creatures-0.012
 island-0.012
 shells-0.012
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
 island+0.032
 cubes+0.032
 boats+0.032
 jackets+0.030
 tunnels+0.028
Neg logit contributions
 Deal-0.065
aman-0.063
istent-0.063
 amaz-0.061
oled-0.060
Token He
Token ID679
Feature activation-8.14e-04

Pos logit contributions
arp+0.015
 cubes+0.014
 pipes+0.013
 bulbs+0.013
 island+0.013
Neg logit contributions
used-0.021
zing-0.020
severe-0.020
opl-0.020
istent-0.020
Token had
Token ID550
Feature activation+2.14e-02

Pos logit contributions
arp+0.019
 island+0.017
 cubes+0.016
 bulbs+0.016
place+0.016
Neg logit contributions
 Deal-0.030
 grin-0.029
 amaz-0.029
severe-0.028
opl-0.028
Token lots
Token ID6041
Feature activation-5.43e-02

Pos logit contributions
 island+0.028
arp+0.027
 cubes+0.026
 bulbs+0.026
 pipes+0.024
Neg logit contributions
 Deal-0.039
 grin-0.037
istent-0.036
used-0.036
ishly-0.035
Token of
Token ID286
Feature activation-1.96e-02

Pos logit contributions
 Deal+0.114
severe+0.105
ishly+0.102
 Jeffrey+0.100
used+0.099
Neg logit contributions
arp-0.058
 cubes-0.057
place-0.054
 bulbs-0.051
 island-0.050
Token shiny
Token ID22441
Feature activation-5.07e-03

Pos logit contributions
severe+0.037
 Deal+0.036
 grin+0.036
adays+0.036
ishly+0.035
Neg logit contributions
arp-0.021
 cubes-0.020
 island-0.018
 bulbs-0.018
 pipes-0.017
Token tables
Token ID8893
Feature activation-2.75e-02

Pos logit contributions
 amaz+0.009
 grin+0.009
 Deal+0.009
severe+0.009
opl+0.009
Neg logit contributions
arp-0.006
 island-0.005
 cubes-0.005
 bulbs-0.005
place-0.005
Token and
Token ID290
Feature activation-8.95e-03

Pos logit contributions
 Deal+0.062
severe+0.054
 Majesty+0.054
 grin+0.052
 amaz+0.051
Neg logit contributions
 island-0.029
arp-0.027
 cubes-0.027
 underground-0.023
 bulbs-0.023
Token knew
Token ID2993
Feature activation+7.66e-03

Pos logit contributions
 Deal+0.020
severe+0.019
 grin+0.019
istent+0.019
opl+0.019
Neg logit contributions
 cubes-0.008
arp-0.007
 island-0.007
 bulbs-0.007
 pipes-0.006
Token gadgets
Token ID35281
Feature activation-5.00e-03

Pos logit contributions
 bulbs+0.009
 island+0.008
 shells+0.008
 crystals+0.008
arp+0.008
Neg logit contributions
opl-0.015
 Deal-0.015
severe-0.015
 grin-0.014
istent-0.014
Token everywhere
Token ID8347
Feature activation-3.61e-02

Pos logit contributions
 Deal+0.011
Aud+0.010
 amaz+0.009
 grin+0.009
severe+0.009
Neg logit contributions
 island-0.005
arp-0.005
 cubes-0.005
 bulbs-0.005
place-0.004
Token.
Token ID13
Feature activation-9.07e-03

Pos logit contributions
 Deal+0.074
severe+0.074
 grin+0.072
 amaz+0.071
opl+0.071
Neg logit contributions
arp-0.037
 bulbs-0.033
 cubes-0.032
 island-0.032
 crystals-0.028
Token She
Token ID1375
Feature activation-5.25e-02

Pos logit contributions
severe+0.010
opl+0.010
 grin+0.009
istent+0.009
 Deal+0.009
Neg logit contributions
arp-0.016
 island-0.015
 cubes-0.015
 bulbs-0.014
 collections-0.013
Token'd
Token ID1549
Feature activation-5.74e-03

Pos logit contributions
 Deal+0.047
icks+0.046
severe+0.045
opl+0.044
adays+0.043
Neg logit contributions
 island-0.016
place-0.014
arp-0.013
 ship-0.010
 tunnel-0.010
Token moved
Token ID3888
Feature activation+4.29e-03

Pos logit contributions
 Deal+0.010
severe+0.010
ishly+0.010
oled+0.009
 Immediately+0.009
Neg logit contributions
 island-0.007
place-0.006
arp-0.006
 tunnel-0.005
 treasures-0.005
Token far
Token ID1290
Feature activation-8.11e-02

Pos logit contributions
arp+0.005
 island+0.005
 cubes+0.004
place+0.004
 bulbs+0.004
Neg logit contributions
 Deal-0.008
opl-0.008
oled-0.008
istent-0.007
adays-0.007
Token away
Token ID1497
Feature activation-1.04e-02

Pos logit contributions
 Deal+0.156
opl+0.147
Aud+0.147
oled+0.147
icks+0.146
Neg logit contributions
arp-0.091
 island-0.090
place-0.074
 cubes-0.070
 bulbs-0.064
Token from
Token ID422
Feature activation-2.85e-02

Pos logit contributions
 Deal+0.024
Aud+0.022
opl+0.021
oled+0.021
icks+0.020
Neg logit contributions
 island-0.011
 creatures-0.009
 underground-0.009
arp-0.009
 treasures-0.008
Token his
Token ID465
Feature activation+1.12e-02

Pos logit contributions
oled+0.051
istent+0.050
 Deal+0.050
Aud+0.050
ives+0.048
Neg logit contributions
 island-0.038
 cubes-0.033
arp-0.031
 underground-0.031
 boats-0.030
Token old
Token ID1468
Feature activation-2.40e-02

Pos logit contributions
arp+0.013
 island+0.013
 cubes+0.012
place+0.011
 ship+0.010
Neg logit contributions
 Deal-0.020
oled-0.020
icks-0.020
adays-0.020
severe-0.020
Token house
Token ID2156
Feature activation-1.61e-02

Pos logit contributions
 Deal+0.048
adays+0.045
 amaz+0.045
severe+0.045
icks+0.045
Neg logit contributions
arp-0.025
 island-0.023
 cubes-0.022
 bulbs-0.020
 pipes-0.019
Token.
Token ID13
Feature activation-6.24e-03

Pos logit contributions
 Deal+0.036
icks+0.032
severe+0.032
Aud+0.031
opl+0.031
Neg logit contributions
 island-0.017
arp-0.014
 cubes-0.014
 ship-0.014
 underground-0.012
Token With
Token ID2080
Feature activation-5.02e-02

Pos logit contributions
 grin+0.009
Aud+0.009
icks+0.009
 la+0.009
 amaz+0.009
Neg logit contributions
arp-0.008
 cubes-0.007
leaning-0.006
 island-0.006
ney-0.006
Token his
Token ID465
Feature activation+1.44e-02

Pos logit contributions
oled+0.093
istent+0.088
AZ+0.086
 Deal+0.086
 Majesty+0.085
Neg logit contributions
 island-0.056
 cubes-0.051
 anchor-0.048
 minerals-0.048
 jackets-0.048
Token When
Token ID1649
Feature activation-2.46e-02

Pos logit contributions
arp+0.020
 cubes+0.019
 pipes+0.017
 island+0.017
Tim+0.017
Neg logit contributions
 grin-0.026
opl-0.026
Aud-0.025
icks-0.025
adays-0.025
Token he
Token ID339
Feature activation-2.57e-03

Pos logit contributions
 Deal+0.058
istent+0.056
opl+0.054
oled+0.054
icks+0.054
Neg logit contributions
 island-0.022
 cubes-0.017
 ship-0.016
 ships-0.016
 boats-0.015
Token reached
Token ID4251
Feature activation+4.16e-02

Pos logit contributions
 Deal+0.005
opl+0.005
icks+0.005
severe+0.005
istent+0.004
Neg logit contributions
 island-0.003
arp-0.003
place-0.002
 ship-0.002
 cubes-0.002
Token a
Token ID257
Feature activation-7.89e-03

Pos logit contributions
 island+0.052
 shells+0.043
 underground+0.042
 tunnels+0.039
 tunnel+0.039
Neg logit contributions
istent-0.087
oled-0.085
 Deal-0.083
severe-0.075
 grin-0.075
Token clearing
Token ID17304
Feature activation+7.84e-03

Pos logit contributions
 Deal+0.015
icks+0.014
severe+0.014
opl+0.014
istent+0.014
Neg logit contributions
 island-0.010
arp-0.009
 tunnel-0.008
place-0.008
 cubes-0.008
Token in
Token ID287
Feature activation+6.37e-02

Pos logit contributions
 island+0.012
arp+0.011
 cubes+0.011
place+0.010
 bulbs+0.010
Neg logit contributions
 Deal-0.013
severe-0.012
Aud-0.012
opl-0.012
oled-0.011
Token the
Token ID262
Feature activation+1.33e-03

Pos logit contributions
arp+0.102
 island+0.102
 cubes+0.092
place+0.088
 bulbs+0.088
Neg logit contributions
 Deal-0.085
severe-0.084
istent-0.083
oled-0.083
opl-0.081
Token forest
Token ID8222
Feature activation+1.56e-02

Pos logit contributions
arp+0.002
 island+0.001
 cubes+0.001
place+0.001
 bulbs+0.001
Neg logit contributions
 grin-0.002
 amaz-0.002
 Deal-0.002
severe-0.002
opl-0.002
Token,
Token ID11
Feature activation+1.08e-03

Pos logit contributions
 island+0.025
 tunnel+0.021
arp+0.021
 creatures+0.020
place+0.020
Neg logit contributions
 Deal-0.029
Aud-0.026
severe-0.025
opl-0.024
icks-0.023
Token he
Token ID339
Feature activation-1.28e-02

Pos logit contributions
 island+0.001
 cubes+0.001
 pipes+0.001
arp+0.001
 crystals+0.001
Neg logit contributions
opl-0.002
 Deal-0.002
istent-0.002
icks-0.002
severe-0.002
Token saw
Token ID2497
Feature activation+1.09e-02

Pos logit contributions
opl+0.031
 Deal+0.030
severe+0.028
icks+0.028
adays+0.028
Neg logit contributions
 island-0.010
arp-0.007
 ship-0.007
 cubes-0.006
 ships-0.006
Token he
Token ID339
Feature activation-1.87e-02

Pos logit contributions
 Deal+0.023
severe+0.022
 amaz+0.022
opl+0.022
istent+0.022
Neg logit contributions
 cubes-0.013
 island-0.012
 boats-0.011
arp-0.011
 bulbs-0.011
Token snapped
Token ID20821
Feature activation-4.92e-03

Pos logit contributions
 Deal+0.038
 amaz+0.035
 grin+0.035
adays+0.034
severe+0.033
Neg logit contributions
arp-0.020
 island-0.019
 cubes-0.017
place-0.017
 bulbs-0.016
Token and
Token ID290
Feature activation-7.47e-03

Pos logit contributions
opl+0.010
 Deal+0.010
istent+0.009
Aud+0.009
+0.009
Neg logit contributions
 cubes-0.006
 crystals-0.005
 shells-0.005
 bulbs-0.005
 pipes-0.005
Token bark
Token ID21405
Feature activation-3.48e-02

Pos logit contributions
 Deal+0.016
istent+0.015
oled+0.014
Aud+0.014
opl+0.014
Neg logit contributions
 cubes-0.008
 pipes-0.007
 tunnel-0.007
 crystals-0.007
 shells-0.007
Tokened
Token ID276
Feature activation-8.12e-02

Pos logit contributions
 Deal+0.061
 amaz+0.054
opl+0.051
 grin+0.050
 Jeffrey+0.047
Neg logit contributions
arp-0.053
 cubes-0.046
place-0.045
B-0.044
 bulbs-0.044
Token.
Token ID13
Feature activation-7.27e-03

Pos logit contributions
 Deal+0.183
opl+0.167
Aud+0.165
Sean+0.162
+0.161
Neg logit contributions
 cubes-0.071
arp-0.069
 bulbs-0.068
 island-0.068
 creatures-0.066
Token One
Token ID1881
Feature activation+1.60e-02

Pos logit contributions
 amaz+0.010
 grin+0.010
Aud+0.010
severe+0.009
adays+0.009
Neg logit contributions
arp-0.011
 cubes-0.011
 island-0.010
 bulbs-0.010
 pipes-0.009
Token day
Token ID1110
Feature activation-1.91e-02

Pos logit contributions
arp+0.016
 island+0.013
 cubes+0.013
 bulbs+0.012
place+0.011
Neg logit contributions
 amaz-0.031
 grin-0.031
opl-0.030
 Deal-0.030
 thank-0.030
Token his
Token ID465
Feature activation+1.31e-02

Pos logit contributions
 Deal+0.026
opl+0.025
 amaz+0.025
Aud+0.024
 grin+0.023
Neg logit contributions
 cubes-0.031
arp-0.030
 island-0.029
 pipes-0.027
 bulbs-0.027
Token dad
Token ID9955
Feature activation+2.98e-03

Pos logit contributions
 island+0.011
arp+0.011
place+0.011
 cubes+0.009
 tunnel+0.009
Neg logit contributions
opl-0.027
oled-0.027
istent-0.027
 Immediately-0.027
 amaz-0.026
Token gave
Token ID2921
Feature activation-4.01e-02

Pos logit contributions
 island+0.003
arp+0.003
 cubes+0.003
 bulbs+0.002
 ship+0.002
Neg logit contributions
 Deal-0.006
opl-0.006
 amaz-0.006
 grin-0.006
severe-0.006
Token,
Token ID11
Feature activation-1.18e-02

Pos logit contributions
arp+0.007
 cubes+0.007
 island+0.007
 bulbs+0.007
place+0.006
Neg logit contributions
 amaz-0.003
opl-0.003
 grin-0.003
 Deal-0.003
severe-0.003
Token a
Token ID257
Feature activation+1.36e-03

Pos logit contributions
 amaz+0.008
 grin+0.007
 thank+0.007
 Deal+0.007
 Immediately+0.007
Neg logit contributions
arp-0.027
 island-0.025
 cubes-0.024
place-0.024
 bulbs-0.024
Token lonely
Token ID21757
Feature activation+6.11e-03

Pos logit contributions
arp+0.003
 island+0.002
 bulbs+0.002
 cubes+0.002
place+0.002
Neg logit contributions
 thank-0.001
 bye-0.001
 grin-0.001
 amaz-0.001
 Deal-0.001
Token bird
Token ID6512
Feature activation+2.90e-02

Pos logit contributions
arp+0.009
 island+0.008
 cubes+0.007
 bulbs+0.007
place+0.007
Neg logit contributions
 Deal-0.010
 amaz-0.009
severe-0.009
 grin-0.009
opl-0.009
Token was
Token ID373
Feature activation-3.92e-03

Pos logit contributions
arp+0.050
 cubes+0.046
 island+0.043
 bulbs+0.042
place+0.042
Neg logit contributions
opl-0.034
 thank-0.033
 grin-0.032
 bye-0.032
 amaz-0.031
Token flying
Token ID7348
Feature activation-3.91e-02

Pos logit contributions
 amaz+0.006
 Deal+0.005
 grin+0.005
severe+0.005
adays+0.005
Neg logit contributions
arp-0.006
 island-0.006
 cubes-0.006
 bulbs-0.005
place-0.005
Token in
Token ID287
Feature activation+7.56e-02

Pos logit contributions
 grin+0.057
 amaz+0.056
severe+0.055
opl+0.055
 thank+0.055
Neg logit contributions
arp-0.057
 island-0.050
 cubes-0.049
 bulbs-0.046
place-0.046
Token the
Token ID262
Feature activation+1.29e-02

Pos logit contributions
 island+0.126
arp+0.123
 cubes+0.117
 bulbs+0.113
 tunnel+0.107
Neg logit contributions
 Deal-0.098
oled-0.097
 grin-0.097
severe-0.096
istent-0.096
Token sky
Token ID6766
Feature activation-1.56e-02

Pos logit contributions
arp+0.017
 island+0.015
 cubes+0.015
 bulbs+0.014
place+0.013
Neg logit contributions
 amaz-0.021
 grin-0.021
 Deal-0.020
severe-0.020
opl-0.020
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
 Deal+0.027
 amaz+0.025
severe+0.025
 grin+0.025
adays+0.025
Neg logit contributions
arp-0.020
 island-0.019
 cubes-0.018
place-0.016
 bulbs-0.016
Token The
Token ID383
Feature activation+2.04e-02

Pos logit contributions
arp+0.023
 island+0.022
 cubes+0.021
 bulbs+0.020
place+0.020
Neg logit contributions
 amaz-0.009
 Deal-0.009
severe-0.009
 grin-0.008
opl-0.008
TokenMom
Token ID29252
Feature activation+2.92e-02

Pos logit contributions
arp+0.082
 cubes+0.075
place+0.063
 island+0.063
 pipes+0.059
Neg logit contributions
adays-0.127
severe-0.127
ishly-0.126
 amaz-0.126
 Deal-0.126
Token,
Token ID11
Feature activation-2.64e-02

Pos logit contributions
 cube+0.033
arp+0.030
 cubes+0.030
 ship+0.029
ie+0.029
Neg logit contributions
 amaz-0.054
Aud-0.053
 Deal-0.052
severe-0.049
opl-0.048
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
opl+0.045
severe+0.043
Aud+0.042
 Immediately+0.041
 Deal+0.040
Neg logit contributions
 cubes-0.034
 island-0.032
arp-0.032
 cube-0.031
 anchor-0.029
Token bird
Token ID6512
Feature activation-3.29e-03

Pos logit contributions
oled+0.022
severe+0.022
adays+0.022
 Deal+0.022
istent+0.021
Neg logit contributions
 island-0.009
arp-0.009
 cubes-0.008
 bulbs-0.007
place-0.007
Token ate
Token ID15063
Feature activation-1.76e-02

Pos logit contributions
 Deal+0.007
 amaz+0.007
Aud+0.006
severe+0.006
 grin+0.006
Neg logit contributions
arp-0.003
 island-0.003
 cube-0.003
ie-0.003
 bulb-0.003
Token my
Token ID616
Feature activation-7.13e-02

Pos logit contributions
oled+0.036
 grin+0.035
Aud+0.035
severe+0.034
istent+0.034
Neg logit contributions
 cubes-0.021
arp-0.017
 island-0.017
 crystals-0.016
 shells-0.016
Token fry
Token ID32959
Feature activation-8.33e-03

Pos logit contributions
adays+0.127
severe+0.127
oled+0.127
Aud+0.123
 amaz+0.119
Neg logit contributions
 cubes-0.085
arp-0.083
 island-0.082
place-0.073
 cube-0.072
Token!
Token ID0
Feature activation-6.72e-02

Pos logit contributions
 amaz+0.017
 Deal+0.016
Aud+0.016
severe+0.015
 Majesty+0.015
Neg logit contributions
 cubes-0.010
arp-0.009
 cube-0.008
 island-0.008
place-0.008
Tokenâ
Token ID22940
Feature activation+3.14e-02

Pos logit contributions
Aud+0.103
severe+0.099
zing+0.097
 grin+0.096
hered+0.095
Neg logit contributions
arp-0.083
 cubes-0.077
Tim-0.070
 cube-0.067
 bulbs-0.066
Token
Token ID26391
Feature activation+1.54e-02

Pos logit contributions
arp+0.054
 island+0.050
 cubes+0.049
 bulbs+0.047
place+0.046
Neg logit contributions
 grin-0.037
 amaz-0.037
 Deal-0.036
opl-0.036
severe-0.036
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
arp+0.022
 cubes+0.021
ney+0.020
 island+0.019
 collections+0.018
Neg logit contributions
 Deal-0.022
severe-0.021
 amaz-0.020
 reflex-0.020
 grin-0.019
Token They
Token ID1119
Feature activation+1.00e-02

Pos logit contributions
arp+0.008
 island+0.008
 cubes+0.008
 bulbs+0.007
place+0.007
Neg logit contributions
 grin-0.006
 Deal-0.006
severe-0.006
 amaz-0.006
Aud-0.006
Token chose
Token ID7690
Feature activation+1.09e-02

Pos logit contributions
 island+0.010
arp+0.009
 bulbs+0.009
 cubes+0.008
 boats+0.008
Neg logit contributions
 Deal-0.021
opl-0.021
severe-0.019
Aud-0.018
 grin-0.018
Token to
Token ID284
Feature activation-1.53e-03

Pos logit contributions
 island+0.015
 bulbs+0.014
 cubes+0.013
 shells+0.013
arp+0.013
Neg logit contributions
 Deal-0.022
istent-0.020
opl-0.019
oled-0.019
severe-0.019
Token explore
Token ID7301
Feature activation+4.32e-02

Pos logit contributions
oled+0.003
 Deal+0.003
severe+0.003
opl+0.003
istent+0.003
Neg logit contributions
 island-0.002
 shells-0.002
place-0.002
 bulbs-0.001
 boats-0.001
Token the
Token ID262
Feature activation-1.24e-04

Pos logit contributions
 island+0.068
arp+0.066
 cubes+0.061
 bulbs+0.061
place+0.060
Neg logit contributions
 Deal-0.065
severe-0.061
oled-0.060
 grin-0.059
opl-0.058
Token land
Token ID1956
Feature activation-3.32e-02

Pos logit contributions
 amaz+0.000
 grin+0.000
 thank+0.000
opl+0.000
severe+0.000
Neg logit contributions
arp-0.000
 cubes-0.000
 island-0.000
 bulbs-0.000
place-0.000
Token together
Token ID1978
Feature activation+1.94e-02

Pos logit contributions
 Deal+0.065
severe+0.059
Aud+0.057
 grin+0.055
oled+0.055
Neg logit contributions
 island-0.046
arp-0.041
 cubes-0.040
place-0.037
 ship-0.037
Token.
Token ID13
Feature activation+6.22e-03

Pos logit contributions
 island+0.021
arp+0.017
 cubes+0.016
place+0.016
 creatures+0.015
Neg logit contributions
 Deal-0.042
severe-0.040
Aud-0.039
opl-0.038
oled-0.037
Token They
Token ID1119
Feature activation+1.19e-02

Pos logit contributions
arp+0.011
 island+0.010
 cubes+0.010
 bulbs+0.009
place+0.009
Neg logit contributions
 grin-0.007
severe-0.007
Aud-0.007
 amaz-0.007
 Deal-0.007
Token wanted
Token ID2227
Feature activation-3.35e-03

Pos logit contributions
 island+0.013
arp+0.012
 bulbs+0.011
 cubes+0.011
 collections+0.010
Neg logit contributions
 Deal-0.023
opl-0.023
severe-0.022
 grin-0.021
oled-0.021
Token to
Token ID284
Feature activation-4.38e-05

Pos logit contributions
 Deal+0.005
opl+0.005
 grin+0.005
severe+0.005
oled+0.005
Neg logit contributions
arp-0.004
 island-0.004
 cubes-0.004
place-0.004
 bulbs-0.004
Token pretty
Token ID2495
Feature activation+1.48e-03

Pos logit contributions
arp+0.031
 cubes+0.029
 bulbs+0.027
place+0.027
 island+0.026
Neg logit contributions
 Deal-0.029
 amaz-0.028
opl-0.028
 grin-0.028
severe-0.027
Token her
Token ID607
Feature activation-1.46e-04

Pos logit contributions
 bulbs+0.002
 cubes+0.002
arp+0.002
 crystals+0.002
 jackets+0.002
Neg logit contributions
 Deal-0.003
istent-0.002
severe-0.002
used-0.002
 Goodbye-0.002
Token hair
Token ID4190
Feature activation-3.13e-02

Pos logit contributions
severe+0.000
istent+0.000
oled+0.000
 Jeffrey+0.000
adays+0.000
Neg logit contributions
 cubes-0.000
 bulbs-0.000
arp-0.000
place-0.000
 jackets-0.000
Token looked
Token ID3114
Feature activation+3.83e-02

Pos logit contributions
 Deal+0.076
 amaz+0.067
 Jeffrey+0.067
severe+0.066
used+0.065
Neg logit contributions
arp-0.025
 cubes-0.023
 bulbs-0.021
 cube-0.019
place-0.019
Token.
Token ID13
Feature activation-1.53e-04

Pos logit contributions
 cubes+0.033
arp+0.032
 island+0.032
 bulbs+0.030
place+0.029
Neg logit contributions
 Deal-0.081
 Jeffrey-0.079
Aud-0.078
opl-0.078
 Josh-0.077
Token She
Token ID1375
Feature activation-4.06e-02

Pos logit contributions
opl+0.000
used+0.000
 amaz+0.000
 grin+0.000
severe+0.000
Neg logit contributions
arp-0.000
 bulbs-0.000
 cubes-0.000
 island-0.000
leaning-0.000
Token felt
Token ID2936
Feature activation+1.38e-02

Pos logit contributions
 Deal+0.081
severe+0.077
opl+0.077
istent+0.073
adays+0.073
Neg logit contributions
arp-0.037
 cubes-0.037
 island-0.037
 bulbs-0.033
 cube-0.031
Token happy
Token ID3772
Feature activation-3.98e-04

Pos logit contributions
place+0.015
arp+0.014
 cubes+0.013
 island+0.013
 bulbs+0.013
Neg logit contributions
opl-0.023
 Deal-0.023
istent-0.022
used-0.022
 Majesty-0.022
Token and
Token ID290
Feature activation+4.53e-04

Pos logit contributions
 Deal+0.001
opl+0.001
severe+0.001
Aud+0.001
icks+0.001
Neg logit contributions
 island-0.000
arp-0.000
 cubes-0.000
 bulbs-0.000
 crystals-0.000
Token proud
Token ID6613
Feature activation-5.14e-04

Pos logit contributions
arp+0.000
 island+0.000
 cubes+0.000
 organized+0.000
 creatures+0.000
Neg logit contributions
 Deal-0.001
opl-0.001
severe-0.001
icks-0.001
 amaz-0.001
Token that
Token ID326
Feature activation-1.54e-02

Pos logit contributions
 Deal+0.001
opl+0.001
severe+0.001
 grin+0.001
 amaz+0.001
Neg logit contributions
arp-0.001
 cubes-0.001
 island-0.001
 bulbs-0.001
place-0.001
Token store
Token ID3650
Feature activation-2.76e-02

Pos logit contributions
 grin+0.005
istent+0.005
severe+0.005
oled+0.005
 Deal+0.005
Neg logit contributions
 island-0.003
arp-0.003
 cubes-0.003
place-0.003
 bulbs-0.003
Token and
Token ID290
Feature activation-7.86e-03

Pos logit contributions
 grin+0.046
 Deal+0.046
 amaz+0.046
severe+0.045
oled+0.045
Neg logit contributions
arp-0.035
 island-0.034
 cubes-0.033
place-0.031
 bulbs-0.029
Token buy
Token ID2822
Feature activation-1.73e-03

Pos logit contributions
opl+0.015
istent+0.014
oled+0.014
 grin+0.013
 Deal+0.013
Neg logit contributions
 island-0.010
 cubes-0.009
place-0.009
 bulbs-0.009
arp-0.008
Token some
Token ID617
Feature activation+1.58e-03

Pos logit contributions
 grin+0.003
oled+0.002
istent+0.002
severe+0.002
 Deal+0.002
Neg logit contributions
arp-0.003
 cubes-0.003
 island-0.003
 bulbs-0.002
place-0.002
Token jam
Token ID16853
Feature activation-1.77e-02

Pos logit contributions
arp+0.002
 island+0.002
 cubes+0.002
 bulbs+0.002
place+0.002
Neg logit contributions
 grin-0.002
 amaz-0.002
severe-0.002
 Deal-0.002
oled-0.002
Token?
Token ID30
Feature activation-3.48e-02

Pos logit contributions
 amaz+0.032
severe+0.031
 grin+0.030
 Deal+0.030
oled+0.029
Neg logit contributions
arp-0.021
 cubes-0.021
 island-0.021
 bulbs-0.019
place-0.019
Token It
Token ID632
Feature activation+1.99e-02

Pos logit contributions
 grin+0.051
opl+0.050
 amaz+0.047
zing+0.045
adays+0.044
Neg logit contributions
arp-0.053
 bulbs-0.047
 cubes-0.045
 island-0.044
leaning-0.043
Token is
Token ID318
Feature activation-5.56e-02

Pos logit contributions
arp+0.024
 island+0.024
 bulbs+0.023
 cubes+0.022
place+0.021
Neg logit contributions
 grin-0.034
oled-0.034
 amaz-0.034
severe-0.033
opl-0.033
Token not
Token ID407
Feature activation-1.36e-02

Pos logit contributions
severe+0.094
oled+0.093
used+0.092
 grin+0.091
istent+0.089
Neg logit contributions
 island-0.071
 cubes-0.070
 bulbs-0.069
arp-0.065
 crystals-0.062
Token far
Token ID1290
Feature activation-7.73e-02

Pos logit contributions
 amaz+0.022
 grin+0.021
oled+0.021
opl+0.021
 Deal+0.021
Neg logit contributions
 island-0.019
 cubes-0.018
arp-0.018
 bulbs-0.018
 crystals-0.016
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
 amaz+0.139
opl+0.134
 Deal+0.134
Aud+0.132
 grin+0.129
Neg logit contributions
 island-0.092
arp-0.089
 cubes-0.081
place-0.078
 bulbs-0.076
Token Wh
Token ID854
Feature activation-3.55e-02

Pos logit contributions
arp+0.042
 island+0.039
 cubes+0.039
 bulbs+0.039
place+0.036
Neg logit contributions
 amaz-0.027
 grin-0.026
severe-0.025
opl-0.024
 Deal-0.023
Tokenisk
Token ID1984
Feature activation-1.79e-01

Pos logit contributions
opl+0.017
 Deal+0.016
 grin+0.016
 amaz+0.015
oled+0.015
Neg logit contributions
arp-0.085
 island-0.081
 cubes-0.080
 bulbs-0.077
place-0.076
Tokeners
Token ID364
Feature activation-2.09e-02

Pos logit contributions
opl+0.280
Aud+0.274
 grin+0.274
adays+0.272
severe+0.272
Neg logit contributions
arp-0.229
 island-0.204
 cubes-0.198
place-0.182
 bulbs-0.181
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
 thank+0.023
opl+0.023
 grin+0.022
oled+0.022
 amaz+0.021
Neg logit contributions
arp-0.037
 island-0.034
 cubes-0.033
 bulbs-0.032
place-0.032
Token Wh
Token ID854
Feature activation-3.58e-02

Pos logit contributions
 amaz+0.014
 grin+0.014
 Deal+0.014
severe+0.013
opl+0.013
Neg logit contributions
arp-0.027
 island-0.025
 cubes-0.025
 bulbs-0.024
place-0.023
Tokenisk
Token ID1984
Feature activation-1.79e-01

Pos logit contributions
opl+0.015
 Deal+0.013
oled+0.012
 grin+0.012
severe+0.011
Neg logit contributions
arp-0.089
 island-0.085
 cubes-0.083
 bulbs-0.080
place-0.079
Tokeners
Token ID364
Feature activation-2.00e-02

Pos logit contributions
opl+0.254
Aud+0.247
icks+0.241
adays+0.241
severe+0.239
Neg logit contributions
arp-0.250
 island-0.226
 cubes-0.219
place-0.203
 bulbs-0.200
Token liked
Token ID8288
Feature activation-7.09e-03

Pos logit contributions
 thank+0.019
 grin+0.017
 Not+0.016
opl+0.015
 bye+0.015
Neg logit contributions
arp-0.043
isher-0.036
 cubes-0.035
 island-0.035
 bulbs-0.035
Token to
Token ID284
Feature activation-1.70e-02

Pos logit contributions
 amaz+0.009
 grin+0.009
 Deal+0.009
severe+0.009
opl+0.009
Neg logit contributions
arp-0.011
 island-0.010
 cubes-0.010
 bulbs-0.010
place-0.010
Token imagine
Token ID5967
Feature activation-3.89e-03

Pos logit contributions
 amaz+0.029
oled+0.028
used+0.028
 Deal+0.028
severe+0.028
Neg logit contributions
 island-0.021
arp-0.021
 cubes-0.019
 bulbs-0.019
place-0.019
Token that
Token ID326
Feature activation-3.70e-02

Pos logit contributions
 Deal+0.006
severe+0.006
 grin+0.006
 amaz+0.006
oled+0.006
Neg logit contributions
arp-0.005
 island-0.005
 cubes-0.005
 bulbs-0.005
place-0.005
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
 Deal+0.131
severe+0.122
icks+0.120
upid+0.115
Aud+0.114
Neg logit contributions
 island-0.044
arp-0.035
 cubes-0.032
 occasion-0.029
place-0.029
Token still
Token ID991
Feature activation-1.68e-02

Pos logit contributions
icks+0.035
 Deal+0.034
opl+0.033
aud+0.032
severe+0.032
Neg logit contributions
 island-0.016
 cubes-0.013
 ship-0.013
 ships-0.012
 boy-0.012
Token in
Token ID287
Feature activation+4.98e-02

Pos logit contributions
 Deal+0.032
Aud+0.030
severe+0.029
oled+0.029
icks+0.028
Neg logit contributions
 island-0.019
 creatures-0.016
place-0.016
 underground-0.015
 cubes-0.015
Token his
Token ID465
Feature activation+1.13e-02

Pos logit contributions
 island+0.060
 cubes+0.055
place+0.053
 place+0.052
 tunnel+0.052
Neg logit contributions
elcome-0.085
Aud-0.084
oled-0.084
severe-0.083
istent-0.082
Token p
Token ID279
Feature activation+1.03e-02

Pos logit contributions
 island+0.013
place+0.011
 cubes+0.010
 collections+0.010
arp+0.009
Neg logit contributions
oled-0.025
istent-0.023
severe-0.023
adays-0.021
Aud-0.021
Tokenaj
Token ID1228
Feature activation-1.42e-01

Pos logit contributions
arp+0.013
 cubes+0.011
 island+0.009
place+0.009
 bulbs+0.009
Neg logit contributions
severe-0.019
 thank-0.019
 Deal-0.019
adays-0.019
 Jeffrey-0.019
Tokenamas
Token ID17485
Feature activation-8.68e-02

Pos logit contributions
 thank+0.218
 catches+0.215
severe+0.214
icks+0.212
 Deal+0.207
Neg logit contributions
arp-0.213
 cubes-0.193
 island-0.185
 bulbs-0.167
 pans-0.162
Token.
Token ID13
Feature activation-9.37e-03

Pos logit contributions
 Deal+0.215
 Majesty+0.189
icks+0.188
 amaz+0.187
Aud+0.186
Neg logit contributions
 island-0.064
arp-0.062
washer-0.053
 ship-0.050
 cubes-0.050
Token Everyone
Token ID11075
Feature activation-1.10e-02

Pos logit contributions
Aud+0.016
icks+0.016
severe+0.015
hered+0.015
 grin+0.014
Neg logit contributions
arp-0.010
 cubes-0.009
ney-0.008
 garage-0.008
 island-0.008
Token in
Token ID287
Feature activation+4.37e-02

Pos logit contributions
 Deal+0.018
opl+0.018
severe+0.018
 amaz+0.018
 grin+0.017
Neg logit contributions
arp-0.014
 island-0.013
 cubes-0.012
place-0.012
 bulbs-0.011
Token town
Token ID3240
Feature activation+3.15e-02

Pos logit contributions
 island+0.049
 cubes+0.042
 boats+0.040
 ships+0.039
 ship+0.038
Neg logit contributions
severe-0.079
 Deal-0.078
istent-0.078
opl-0.077
elcome-0.077
Token small
Token ID1402
Feature activation-2.19e-02

Pos logit contributions
 grin+0.071
 amaz+0.071
 Deal+0.070
severe+0.069
opl+0.067
Neg logit contributions
arp-0.099
 island-0.094
 cubes-0.090
 bulbs-0.086
place-0.084
Token,
Token ID11
Feature activation-9.61e-03

Pos logit contributions
 Deal+0.039
Aud+0.038
 amaz+0.036
 grin+0.036
oled+0.035
Neg logit contributions
 island-0.030
arp-0.027
place-0.027
 cubes-0.027
 bulbs-0.026
Token has
Token ID468
Feature activation-3.52e-02

Pos logit contributions
severe+0.016
oled+0.016
Aud+0.016
opl+0.016
used+0.015
Neg logit contributions
arp-0.013
 island-0.013
 cubes-0.012
 bulbs-0.012
 cube-0.011
Token a
Token ID257
Feature activation-2.68e-02

Pos logit contributions
 grin+0.058
 Deal+0.055
oled+0.054
istent+0.053
Aud+0.050
Neg logit contributions
 island-0.056
 cubes-0.053
arp-0.051
 bulbs-0.050
 pipes-0.049
Token bus
Token ID1323
Feature activation-7.30e-02

Pos logit contributions
adays+0.050
severe+0.050
alled+0.050
Aud+0.049
oled+0.049
Neg logit contributions
 island-0.032
 pipe-0.029
arp-0.028
 tunnel-0.028
 cell-0.028
Tokenhy
Token ID12114
Feature activation-1.45e-01

Pos logit contributions
 Deal+0.142
 amaz+0.138
 delight+0.134
 fascination+0.132
 ease+0.132
Neg logit contributions
 island-0.078
 ship-0.071
arp-0.068
place-0.067
 cubes-0.066
Token tail
Token ID7894
Feature activation-8.11e-02

Pos logit contributions
 Deal+0.262
+0.254
 amaz+0.252
 Afterwards+0.252
adays+0.250
Neg logit contributions
 island-0.188
 ship-0.172
 cubes-0.155
arp-0.153
an-0.153
Token,
Token ID11
Feature activation-1.42e-02

Pos logit contributions
 Deal+0.178
 amaz+0.177
Aud+0.169
 grin+0.163
adays+0.162
Neg logit contributions
 island-0.079
arp-0.069
 cubes-0.062
 ship-0.059
 cube-0.055
Token and
Token ID290
Feature activation-7.17e-03

Pos logit contributions
 Deal+0.026
severe+0.026
hered+0.025
oled+0.025
Aud+0.025
Neg logit contributions
 island-0.017
 pipes-0.016
 cubes-0.016
 bulbs-0.016
 coal-0.015
Token likes
Token ID7832
Feature activation-6.39e-02

Pos logit contributions
oled+0.014
 grin+0.013
 Deal+0.013
istent+0.013
Aud+0.013
Neg logit contributions
 island-0.009
 bulbs-0.009
 crystals-0.009
 pipes-0.009
 cubes-0.008
Token to
Token ID284
Feature activation-9.43e-03

Pos logit contributions
 grin+0.125
 Deal+0.123
 amaz+0.117
oled+0.116
istent+0.113
Neg logit contributions
 island-0.077
arp-0.073
 cubes-0.069
 bulbs-0.068
place-0.066
Token a
Token ID257
Feature activation-2.91e-02

Pos logit contributions
 amaz+0.021
 grin+0.020
 Deal+0.020
 thank+0.019
opl+0.018
Neg logit contributions
arp-0.068
 island-0.063
 cubes-0.062
place-0.060
 bulbs-0.059
Token friendly
Token ID8030
Feature activation-2.88e-02

Pos logit contributions
 thank+0.028
 grin+0.027
 bye+0.026
 amaz+0.025
 sorry+0.024
Neg logit contributions
arp-0.059
 cubes-0.051
 island-0.051
place-0.050
 bulbs-0.050
Token cat
Token ID3797
Feature activation-2.13e-02

Pos logit contributions
 Deal+0.049
 amaz+0.047
severe+0.047
opl+0.046
adays+0.046
Neg logit contributions
arp-0.037
 island-0.036
 cubes-0.033
 bulbs-0.031
place-0.029
Token named
Token ID3706
Feature activation+2.30e-02

Pos logit contributions
opl+0.023
 thank+0.022
icks+0.021
oled+0.021
 Mitt+0.020
Neg logit contributions
arp-0.038
 cubes-0.034
 island-0.034
place-0.033
 collections-0.032
Token Wh
Token ID854
Feature activation-3.55e-02

Pos logit contributions
arp+0.042
 island+0.039
 cubes+0.039
 bulbs+0.039
place+0.036
Neg logit contributions
 amaz-0.027
 grin-0.026
severe-0.025
opl-0.024
 Deal-0.023
Tokenisk
Token ID1984
Feature activation-1.79e-01

Pos logit contributions
opl+0.017
 Deal+0.016
 grin+0.016
 amaz+0.015
oled+0.015
Neg logit contributions
arp-0.085
 island-0.081
 cubes-0.080
 bulbs-0.077
place-0.076
Tokeners
Token ID364
Feature activation-2.09e-02

Pos logit contributions
opl+0.280
Aud+0.274
 grin+0.274
adays+0.272
severe+0.272
Neg logit contributions
arp-0.229
 island-0.204
 cubes-0.198
place-0.182
 bulbs-0.181
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
 thank+0.023
opl+0.023
 grin+0.022
oled+0.022
 amaz+0.021
Neg logit contributions
arp-0.037
 island-0.034
 cubes-0.033
 bulbs-0.032
place-0.032
Token Wh
Token ID854
Feature activation-3.58e-02

Pos logit contributions
 amaz+0.014
 grin+0.014
 Deal+0.014
severe+0.013
opl+0.013
Neg logit contributions
arp-0.027
 island-0.025
 cubes-0.025
 bulbs-0.024
place-0.023
Tokenisk
Token ID1984
Feature activation-1.79e-01

Pos logit contributions
opl+0.015
 Deal+0.013
oled+0.012
 grin+0.012
severe+0.011
Neg logit contributions
arp-0.089
 island-0.085
 cubes-0.083
 bulbs-0.080
place-0.079
Tokeners
Token ID364
Feature activation-2.00e-02

Pos logit contributions
opl+0.254
Aud+0.247
icks+0.241
adays+0.241
severe+0.239
Neg logit contributions
arp-0.250
 island-0.226
 cubes-0.219
place-0.203
 bulbs-0.200
Token drawer
Token ID33451
Feature activation+1.35e-02

Pos logit contributions
 amaz+0.004
 grin+0.004
 Deal+0.004
severe+0.004
opl+0.004
Neg logit contributions
arp-0.005
 island-0.004
 cubes-0.004
 bulbs-0.004
place-0.004
Token to
Token ID284
Feature activation-8.06e-03

Pos logit contributions
arp+0.021
 island+0.020
 cubes+0.019
place+0.018
 bulbs+0.018
Neg logit contributions
 Deal-0.019
 amaz-0.019
 grin-0.019
opl-0.018
severe-0.018
Token get
Token ID651
Feature activation-3.96e-02

Pos logit contributions
 amaz+0.010
 grin+0.010
 Deal+0.010
 thank+0.010
severe+0.009
Neg logit contributions
arp-0.014
 island-0.012
 cubes-0.012
 bulbs-0.012
place-0.011
Token her
Token ID607
Feature activation-2.83e-03

Pos logit contributions
 amaz+0.026
 thank+0.026
 grin+0.024
 Deal+0.023
severe+0.023
Neg logit contributions
arp-0.091
 island-0.083
 cubes-0.078
place-0.077
leaning-0.075
Token cr
Token ID1067
Feature activation-1.17e-02

Pos logit contributions
 amaz+0.005
 grin+0.005
 Deal+0.005
severe+0.005
opl+0.005
Neg logit contributions
arp-0.004
 island-0.003
 cubes-0.003
 bulbs-0.003
place-0.003
Tokenay
Token ID323
Feature activation-1.33e-01

Pos logit contributions
 amaz+0.007
 grin+0.007
 Deal+0.007
severe+0.006
 thank+0.006
Neg logit contributions
arp-0.027
 island-0.025
 cubes-0.025
 bulbs-0.024
place-0.024
Tokenons
Token ID684
Feature activation-1.55e-02

Pos logit contributions
 amaz+0.151
 grin+0.150
 Deal+0.147
severe+0.143
opl+0.141
Neg logit contributions
arp-0.238
 island-0.217
 cubes-0.215
 bulbs-0.204
place-0.201
Token,
Token ID11
Feature activation-1.69e-02

Pos logit contributions
 amaz+0.024
 Deal+0.024
 grin+0.024
opl+0.023
severe+0.023
Neg logit contributions
arp-0.021
 island-0.020
 cubes-0.019
 bulbs-0.018
place-0.017
Token but
Token ID475
Feature activation+1.40e-02

Pos logit contributions
 amaz+0.028
 grin+0.028
opl+0.028
 Deal+0.028
severe+0.028
Neg logit contributions
arp-0.021
 island-0.019
 cubes-0.019
 bulbs-0.018
place-0.017
Token she
Token ID673
Feature activation-2.05e-02

Pos logit contributions
arp+0.021
 island+0.021
 cubes+0.020
 bulbs+0.020
 crystals+0.018
Neg logit contributions
opl-0.020
 grin-0.020
 Deal-0.020
istent-0.019
severe-0.019
Token saw
Token ID2497
Feature activation+6.85e-03

Pos logit contributions
 amaz+0.025
 grin+0.025
 Deal+0.024
severe+0.024
opl+0.024
Neg logit contributions
arp-0.035
 island-0.032
 cubes-0.031
 bulbs-0.030
place-0.029