TOP ACTIVATIONS
MAX = 3.554

said , " These sa us ages are for you !"
sign says : " Circ us is here ! Come and
a large selection of ch ocol ates . Ell a picked
was filled with delicious ch ocol ates . He was happy
, cup cakes and ch ocol ates .
was a box of ch ocol ates ! Alice and her
a big box of ch ocol ates to share with the
colorful cand ies and ch ocol ates . She said to
a big box of ch ocol ates ! <|endoftext|> Once upon
sign that says " Circ us ". Lily and Tom are
smiled . " These sa us ages are not bitter at
sign that said " Circ us ". They ran inside the
and her favourite , ch ocol ates ! She asked mummy
a big box of ch ocol ates !
sign that said " Circ us ". Mom bought tickets for
a big box of ch ocol ates . It was so
cakes and cookies and ch ocol ates and ice cream .
" Ch oo cho o , this is the red
and laughed and ate ch ocol ates . They had a
her a box of ch ocol ates . Lily opened the

MIN ACTIVATIONS
MIN = -3.012

learned not to judge by appearances . They learned to help
happy to have won the tournament and learned what mild mornings
worry , Lily . Po pp ies are soft and gentle
you so you can do your best ." Joe
. You did not do your homework and clean . You
. If you do not store your toys , you will
car again and Lily insisted one more time . Her mom
? You did not do your chores . You did not
him . He pulls the trigger . Bang !
. You do not do your work . You do not
, sweet ie . Po pp ies are very delicate .
tiger 's journey didn 't end there - as soon as
was glad it didn 't end too soon . He went
Sam . He pulls the trigger . The gun
Mia . He pulls the trigger . But nothing happens .
fort and you can do your painting too !"
. She did not have one . He looked at the
The two friends didn 't end up playing together anymore and
. The day did not end well for Tim and Sam
named Lily who loved po pp ies . She had a

INTERVAL 1.913 - 3.554
CONTAINS 0.033%

and her favourite , ch ocol ates ! She asked mummy
like lions , gir aff es , and elephants .
and noisy voice , " John , these caul if l
playing together , and showed each other their famous toys .
flour , water , yeast and salt in a big bowl

INTERVAL 0.271 - 1.913
CONTAINS 28.250%

were all wearing matching outfits . Billy ran over
made it look nice and delicious . He eagerly picked it
save herself . The girl lived a happy life . <|endoftext|>
Yes , you can share it . But wash it first
something to happen . Nothing did . The

INTERVAL -1.370 - 0.271
CONTAINS 71.041%

her plan . She decided to bake a cake , buy
worried that she wasn 't good enough .
oranges . L ily said , " I want
help ." The owl smiled and said , " You 're
. The little girl was very sad and cried a lot

INTERVAL -3.012 - -1.370
CONTAINS 0.676%

From that day forward , the cel ery always
boat d ocked at a harbor far away . The cat
forgive you . You 're my brother and I love you
okay ." M ummy and Daddy laughed and hugged
be his wife and Ben 's mom . He asked Ben
Token said
Token ID531
Feature activation+4.22e-01

Pos logit contributions
CA+0.013
 emergencies+0.012
 steam+0.012
 sailors+0.011
 lava+0.011
Neg logit contributions
 salon-0.017
aring-0.015
spe-0.013
Instead-0.013
ho-0.013
Token,
Token ID11
Feature activation-3.53e-01

Pos logit contributions
CA+0.020
 emergencies+0.020
 steam+0.019
 lava+0.019
 sailors+0.019
Neg logit contributions
 salon-0.028
aring-0.024
Instead-0.023
spe-0.022
 pad-0.022
Token "
Token ID366
Feature activation+5.39e-01

Pos logit contributions
 salon+0.022
aring+0.019
spe+0.017
Instead+0.017
ared+0.016
Neg logit contributions
CA-0.019
 emergencies-0.018
 steam-0.018
 sailors-0.018
 lava-0.017
TokenThese
Token ID4711
Feature activation+2.94e-01

Pos logit contributions
CA+0.025
 sailors+0.022
 steam+0.022
rob+0.022
 emergencies+0.021
Neg logit contributions
 salon-0.038
aring-0.034
spe-0.030
Instead-0.029
ho-0.029
Token sa
Token ID473
Feature activation+1.31e+00

Pos logit contributions
CA+0.012
 emergencies+0.012
 steam+0.012
 sailors+0.011
 batteries+0.011
Neg logit contributions
 salon-0.021
aring-0.020
spe-0.018
Instead-0.017
ho-0.017
Tokenus
Token ID385
Feature activation+3.55e+00

Pos logit contributions
CA+0.033
 emergencies+0.027
 steam+0.026
 lava+0.023
 aliens+0.021
Neg logit contributions
 salon-0.122
aring-0.116
spe-0.107
ho-0.106
Instead-0.106
Tokenages
Token ID1095
Feature activation+2.01e+00

Pos logit contributions
CA+0.215
 emergencies+0.204
 steam+0.197
 lava+0.192
 batteries+0.188
Neg logit contributions
 salon-0.199
aring-0.183
spe-0.159
ho-0.154
Instead-0.153
Token are
Token ID389
Feature activation+6.75e-01

Pos logit contributions
CA+0.129
 emergencies+0.128
 steam+0.128
 lava+0.124
 sailors+0.124
Neg logit contributions
 salon-0.100
aring-0.085
spe-0.075
Instead-0.073
ho-0.070
Token for
Token ID329
Feature activation+3.99e-01

Pos logit contributions
CA+0.039
 emergencies+0.037
 steam+0.036
 sailors+0.035
 lava+0.035
Neg logit contributions
 salon-0.039
aring-0.035
spe-0.031
Instead-0.031
ho-0.030
Token you
Token ID345
Feature activation-2.00e-01

Pos logit contributions
CA+0.018
 steam+0.016
 lava+0.015
 emergencies+0.015
rob+0.015
Neg logit contributions
 salon-0.028
aring-0.026
Instead-0.024
spe-0.023
ho-0.023
Token!"
Token ID2474
Feature activation+2.13e-02

Pos logit contributions
 salon+0.016
aring+0.014
spe+0.014
Instead+0.013
ho+0.013
Neg logit contributions
 emergencies-0.007
 sailors-0.007
 steam-0.007
CA-0.006
 batteries-0.006
Token sign
Token ID1051
Feature activation-1.88e-01

Pos logit contributions
CA+0.019
 steam+0.018
 emergencies+0.018
 sailors+0.017
 lava+0.017
Neg logit contributions
 salon-0.022
aring-0.020
spe-0.019
Instead-0.018
ho-0.017
Token says
Token ID1139
Feature activation+7.94e-01

Pos logit contributions
 salon+0.013
aring+0.012
Instead+0.011
spe+0.010
ho+0.010
Neg logit contributions
CA-0.009
 emergencies-0.008
 steam-0.008
 batteries-0.008
 lava-0.008
Token:
Token ID25
Feature activation+5.84e-01

Pos logit contributions
CA+0.048
 emergencies+0.046
agons+0.045
 steam+0.045
 sailors+0.045
Neg logit contributions
 salon-0.043
aring-0.039
spe-0.034
ho-0.033
Instead-0.033
Token "
Token ID366
Feature activation+4.63e-01

Pos logit contributions
CA+0.033
 emergencies+0.032
 steam+0.031
 sailors+0.030
 lava+0.030
Neg logit contributions
 salon-0.035
aring-0.031
spe-0.027
Instead-0.027
ho-0.026
TokenCirc
Token ID31560
Feature activation+1.56e+00

Pos logit contributions
CA+0.024
 emergencies+0.023
 steam+0.022
 sailors+0.022
 lava+0.021
Neg logit contributions
 salon-0.030
aring-0.027
spe-0.024
Instead-0.024
ho-0.023
Tokenus
Token ID385
Feature activation+3.50e+00

Pos logit contributions
CA+0.060
 emergencies+0.050
 steam+0.047
 lava+0.046
 batteries+0.043
Neg logit contributions
 salon-0.127
aring-0.123
spe-0.111
ho-0.108
Instead-0.105
Token is
Token ID318
Feature activation+1.49e+00

Pos logit contributions
CA+0.165
 emergencies+0.156
 steam+0.149
 lava+0.144
 batteries+0.143
Neg logit contributions
 salon-0.242
aring-0.222
spe-0.200
ho-0.195
Instead-0.195
Token here
Token ID994
Feature activation+1.30e+00

Pos logit contributions
CA+0.074
 emergencies+0.066
kins+0.065
 steam+0.063
agons+0.063
Neg logit contributions
 salon-0.098
aring-0.091
spe-0.081
Instead-0.079
ho-0.078
Token!
Token ID0
Feature activation+1.33e+00

Pos logit contributions
CA+0.047
 emergencies+0.045
 steam+0.043
 sailors+0.041
 lava+0.041
Neg logit contributions
 salon-0.103
aring-0.094
spe-0.086
Instead-0.086
ho-0.084
Token Come
Token ID7911
Feature activation+2.82e-01

Pos logit contributions
CA+0.075
 emergencies+0.072
 steam+0.069
 sailors+0.069
 lava+0.068
Neg logit contributions
 salon-0.080
aring-0.070
spe-0.063
Instead-0.063
ho-0.062
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
CA+0.017
 emergencies+0.016
 lava+0.016
 steam+0.016
rob+0.015
Neg logit contributions
 salon-0.016
aring-0.014
ho-0.012
spe-0.012
Instead-0.012
Token a
Token ID257
Feature activation+7.10e-02

Pos logit contributions
 steam+0.034
CA+0.034
 emergencies+0.033
 batteries+0.033
 lava+0.032
Neg logit contributions
 salon-0.057
aring-0.057
ho-0.049
Instead-0.048
itating-0.047
Token large
Token ID1588
Feature activation-2.93e-01

Pos logit contributions
 steam+0.003
 pans+0.003
 batteries+0.003
 emergencies+0.003
 coal+0.003
Neg logit contributions
aring-0.005
ared-0.005
 salon-0.005
Instead-0.005
ouncing-0.004
Token selection
Token ID6356
Feature activation-1.04e-02

Pos logit contributions
aring+0.020
 salon+0.019
Instead+0.018
itating+0.018
spe+0.017
Neg logit contributions
 steam-0.014
 batteries-0.013
 emergencies-0.012
 lava-0.012
 pans-0.012
Token of
Token ID286
Feature activation+1.40e+00

Pos logit contributions
 salon+0.001
aring+0.001
Instead+0.000
spe+0.000
 Sadly+0.000
Neg logit contributions
CA-0.001
 emergencies-0.001
 steam-0.001
kins-0.001
 batteries-0.001
Token ch
Token ID442
Feature activation+1.03e+00

Pos logit contributions
CA+0.058
 emergencies+0.057
 steam+0.056
 batteries+0.055
 sailors+0.053
Neg logit contributions
 salon-0.103
aring-0.096
spe-0.086
ho-0.085
Instead-0.085
Tokenocol
Token ID4668
Feature activation+3.41e+00

Pos logit contributions
CA+0.024
 emergencies+0.021
 steam+0.020
 lava+0.018
 sailors+0.018
Neg logit contributions
 salon-0.095
aring-0.089
spe-0.082
Instead-0.081
ho-0.080
Tokenates
Token ID689
Feature activation+1.88e+00

Pos logit contributions
CA+0.124
 steam+0.121
 emergencies+0.110
 aliens+0.104
 shark+0.098
Neg logit contributions
 salon-0.258
aring-0.247
ared-0.246
 pad-0.241
ho-0.240
Token.
Token ID13
Feature activation-8.25e-03

Pos logit contributions
 steam+0.051
 emergencies+0.051
CA+0.051
kins+0.050
 sailors+0.049
Neg logit contributions
 salon-0.160
aring-0.147
Instead-0.138
spe-0.136
 Sadly-0.133
Token Ell
Token ID7122
Feature activation-5.56e-01

Pos logit contributions
 salon+0.001
aring+0.001
ho+0.000
ared+0.000
spe+0.000
Neg logit contributions
CA-0.000
 emergencies-0.000
 steam-0.000
 batteries-0.000
 Pig-0.000
Tokena
Token ID64
Feature activation-1.53e+00

Pos logit contributions
 salon+0.024
aring+0.023
Instead+0.022
 Even+0.021
 Sadly+0.021
Neg logit contributions
us-0.035
kins-0.034
pa-0.032
we-0.032
izz-0.032
Token picked
Token ID6497
Feature activation+5.77e-01

Pos logit contributions
 salon+0.101
aring+0.098
Instead+0.086
itating+0.085
 perspective+0.085
Neg logit contributions
CA-0.065
 steam-0.063
kins-0.063
 sailors-0.060
 pans-0.059
Token was
Token ID373
Feature activation+4.04e-01

Pos logit contributions
CA+0.019
 emergencies+0.018
 steam+0.017
 sailors+0.016
 lava+0.016
Neg logit contributions
 salon-0.038
aring-0.035
spe-0.032
Instead-0.032
ho-0.031
Token filled
Token ID5901
Feature activation+2.35e-01

Pos logit contributions
CA+0.022
 emergencies+0.021
agons+0.020
rob+0.020
 pans+0.019
Neg logit contributions
 salon-0.024
aring-0.021
spe-0.020
Instead-0.019
ho-0.018
Token with
Token ID351
Feature activation+7.36e-01

Pos logit contributions
CA+0.013
 steam+0.013
 emergencies+0.013
 sailors+0.013
kins+0.013
Neg logit contributions
 salon-0.014
aring-0.012
Instead-0.010
spe-0.010
ho-0.010
Token delicious
Token ID12625
Feature activation+8.21e-01

Pos logit contributions
CA+0.030
 emergencies+0.030
 steam+0.030
 sailors+0.028
 lava+0.028
Neg logit contributions
 salon-0.055
aring-0.051
spe-0.045
Instead-0.045
ho-0.044
Token ch
Token ID442
Feature activation+1.06e+00

Pos logit contributions
CA+0.037
 emergencies+0.033
kins+0.030
 sailors+0.030
 batteries+0.030
Neg logit contributions
 salon-0.057
aring-0.052
spe-0.048
ho-0.047
Instead-0.046
Tokenocol
Token ID4668
Feature activation+3.22e+00

Pos logit contributions
CA+0.038
 emergencies+0.034
rob+0.032
 steam+0.032
 batteries+0.031
Neg logit contributions
 salon-0.082
aring-0.082
spe-0.071
ho-0.070
Instead-0.069
Tokenates
Token ID689
Feature activation+1.98e+00

Pos logit contributions
CA+0.135
 steam+0.129
 emergencies+0.123
 shark+0.114
 batteries+0.107
Neg logit contributions
ared-0.222
aring-0.221
 pad-0.214
ho-0.213
 salon-0.205
Token.
Token ID13
Feature activation+8.55e-02

Pos logit contributions
CA+0.058
 steam+0.058
 emergencies+0.057
 sailors+0.057
kins+0.055
Neg logit contributions
 salon-0.166
aring-0.151
Instead-0.142
spe-0.139
 Sadly-0.135
Token He
Token ID679
Feature activation-2.66e-01

Pos logit contributions
CA+0.005
 emergencies+0.004
 sailors+0.004
 steam+0.004
 lava+0.004
Neg logit contributions
 salon-0.005
aring-0.005
ho-0.004
spe-0.004
Instead-0.004
Token was
Token ID373
Feature activation-1.61e-01

Pos logit contributions
 salon+0.018
aring+0.017
Instead+0.014
spe+0.014
itating+0.013
Neg logit contributions
CA-0.013
 steam-0.013
 sailors-0.012
kins-0.011
 lava-0.011
Token happy
Token ID3772
Feature activation+1.50e-01

Pos logit contributions
 salon+0.010
aring+0.010
 tant+0.009
Instead+0.009
ho+0.008
Neg logit contributions
 steam-0.008
 sailors-0.008
CA-0.007
 lava-0.007
ull-0.007
Token,
Token ID11
Feature activation+6.77e-02

Pos logit contributions
 steam+0.033
kins+0.032
 sailors+0.032
CA+0.031
 emergencies+0.031
Neg logit contributions
 salon-0.078
aring-0.073
Instead-0.068
spe-0.066
 Sadly-0.065
Token cup
Token ID6508
Feature activation+5.99e-01

Pos logit contributions
 steam+0.003
 batteries+0.003
 lava+0.003
 sailors+0.003
CA+0.003
Neg logit contributions
aring-0.005
 salon-0.005
Instead-0.004
ared-0.004
spe-0.004
Tokencakes
Token ID37263
Feature activation+1.06e+00

Pos logit contributions
CA+0.027
 steam+0.027
 lava+0.026
 emergencies+0.026
kins+0.025
Neg logit contributions
 salon-0.040
aring-0.037
Instead-0.034
spe-0.033
 Sadly-0.032
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 steam+0.043
kins+0.041
CA+0.041
 lava+0.041
rob+0.039
Neg logit contributions
 salon-0.073
aring-0.072
Instead-0.064
spe-0.063
 Sadly-0.062
Token ch
Token ID442
Feature activation+9.16e-01

Pos logit contributions
 steam+0.053
 pans+0.051
 lava+0.049
 sailors+0.049
 batteries+0.048
Neg logit contributions
aring-0.092
 salon-0.087
itating-0.078
Instead-0.075
olding-0.075
Tokenocol
Token ID4668
Feature activation+3.20e+00

Pos logit contributions
CA+0.022
 emergencies+0.020
 steam+0.018
 sailors+0.018
 lava+0.017
Neg logit contributions
 salon-0.085
aring-0.078
spe-0.073
Instead-0.073
ho-0.071
Tokenates
Token ID689
Feature activation+1.54e+00

Pos logit contributions
CA+0.115
 steam+0.109
 emergencies+0.107
 aliens+0.097
 shark+0.091
Neg logit contributions
 salon-0.243
ared-0.232
aring-0.229
ho-0.229
 pad-0.225
Token.
Token ID13
Feature activation+2.44e-02

Pos logit contributions
 steam+0.044
kins+0.044
 sailors+0.043
CA+0.041
 lava+0.041
Neg logit contributions
 salon-0.130
aring-0.120
Instead-0.112
 Sadly-0.110
spe-0.109
Token
Token ID220
Feature activation-1.00e+00

Pos logit contributions
CA+0.001
 emergencies+0.001
 batteries+0.001
 steam+0.001
 sailors+0.001
Neg logit contributions
 salon-0.002
aring-0.002
ho-0.001
spe-0.001
Instead-0.001
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
 salon+0.065
aring+0.059
spe+0.053
Instead+0.052
ho+0.051
Neg logit contributions
CA-0.051
 emergencies-0.049
 steam-0.047
 sailors-0.046
 lava-0.045
Token
Token ID198
Feature activation+4.52e-01

Pos logit contributions
CA+0.007
 emergencies+0.006
 steam+0.006
 sailors+0.006
 batteries+0.006
Neg logit contributions
 salon-0.011
aring-0.010
ho-0.010
spe-0.009
Instead-0.009
Token was
Token ID373
Feature activation+5.02e-01

Pos logit contributions
CA+0.035
 emergencies+0.033
 steam+0.032
 sailors+0.031
 lava+0.031
Neg logit contributions
 salon-0.050
aring-0.045
spe-0.041
Instead-0.041
ho-0.040
Token a
Token ID257
Feature activation+5.02e-01

Pos logit contributions
CA+0.018
 steam+0.018
 emergencies+0.018
 lava+0.016
 batteries+0.016
Neg logit contributions
 salon-0.040
aring-0.038
spe-0.034
Instead-0.033
ho-0.033
Token box
Token ID3091
Feature activation+2.64e-01

Pos logit contributions
 steam+0.020
 emergencies+0.018
 pans+0.018
CA+0.018
 lava+0.017
Neg logit contributions
aring-0.038
 salon-0.038
ared-0.035
Instead-0.033
ashing-0.032
Token of
Token ID286
Feature activation+1.02e+00

Pos logit contributions
 steam+0.008
kins+0.007
 sailors+0.007
 batteries+0.007
CA+0.007
Neg logit contributions
 salon-0.022
aring-0.020
Instead-0.020
 tant-0.019
 Even-0.019
Token ch
Token ID442
Feature activation+7.21e-01

Pos logit contributions
CA+0.039
 emergencies+0.038
 steam+0.036
 sailors+0.035
 lava+0.035
Neg logit contributions
 salon-0.079
aring-0.072
spe-0.066
Instead-0.065
ho-0.064
Tokenocol
Token ID4668
Feature activation+3.15e+00

Pos logit contributions
CA+0.018
 emergencies+0.016
 steam+0.015
 sailors+0.014
 lava+0.013
Neg logit contributions
 salon-0.066
aring-0.062
spe-0.057
Instead-0.057
ho-0.056
Tokenates
Token ID689
Feature activation+1.67e+00

Pos logit contributions
CA+0.124
 steam+0.118
 shark+0.111
 emergencies+0.107
 aliens+0.105
Neg logit contributions
 salon-0.219
ared-0.217
aring-0.216
 pad-0.214
ho-0.205
Token!
Token ID0
Feature activation-3.22e-02

Pos logit contributions
 steam+0.042
kins+0.040
 sailors+0.040
 emergencies+0.040
CA+0.039
Neg logit contributions
 salon-0.147
aring-0.137
Instead-0.129
spe-0.127
 Sadly-0.125
Token Alice
Token ID14862
Feature activation-9.02e-01

Pos logit contributions
 salon+0.002
aring+0.002
ho+0.002
spe+0.002
ashing+0.002
Neg logit contributions
CA-0.001
 emergencies-0.001
 batteries-0.001
 Farmer-0.001
 pans-0.001
Token and
Token ID290
Feature activation-8.47e-01

Pos logit contributions
 salon+0.065
aring+0.060
Instead+0.052
 tant+0.052
spe+0.051
Neg logit contributions
CA-0.039
 steam-0.037
 sailors-0.035
kins-0.034
 pans-0.033
Token her
Token ID607
Feature activation-2.14e-01

Pos logit contributions
aring+0.082
 salon+0.077
ashing+0.072
ho+0.070
spe+0.070
Neg logit contributions
pa-0.015
 his-0.014
 batteries-0.014
 emergencies-0.014
 steam-0.013
Token a
Token ID257
Feature activation+4.53e-01

Pos logit contributions
 salon+0.009
aring+0.008
 pad+0.007
 Sadly+0.007
 While+0.007
Neg logit contributions
CA-0.016
 emergencies-0.015
kins-0.014
agons-0.014
 pans-0.014
Token big
Token ID1263
Feature activation+4.78e-01

Pos logit contributions
 steam+0.015
CA+0.014
 coal+0.013
 emergencies+0.012
 batteries+0.012
Neg logit contributions
aring-0.037
 salon-0.036
Instead-0.034
ared-0.033
 Even-0.033
Token box
Token ID3091
Feature activation+4.95e-01

Pos logit contributions
 steam+0.020
CA+0.019
 lava+0.019
 coal+0.019
 emergencies+0.018
Neg logit contributions
 salon-0.033
aring-0.033
Instead-0.032
itating-0.030
spe-0.030
Token of
Token ID286
Feature activation+8.40e-01

Pos logit contributions
 steam+0.020
 sailors+0.020
 batteries+0.020
CA+0.019
ull+0.018
Neg logit contributions
 salon-0.035
aring-0.030
Instead-0.030
spe-0.029
 Even-0.028
Token ch
Token ID442
Feature activation+8.02e-01

Pos logit contributions
CA+0.033
 emergencies+0.029
kins+0.027
agons+0.026
 sailors+0.026
Neg logit contributions
 salon-0.064
aring-0.056
spe-0.054
Instead-0.052
ho-0.052
Tokenocol
Token ID4668
Feature activation+3.14e+00

Pos logit contributions
CA+0.028
 emergencies+0.027
 steam+0.025
rob+0.024
 batteries+0.024
Neg logit contributions
 salon-0.064
aring-0.061
spe-0.054
ho-0.054
ared-0.053
Tokenates
Token ID689
Feature activation+1.71e+00

Pos logit contributions
CA+0.114
 steam+0.112
 emergencies+0.104
 shark+0.093
 lava+0.091
Neg logit contributions
aring-0.227
 salon-0.226
ared-0.219
ho-0.218
 pad-0.214
Token to
Token ID284
Feature activation+8.70e-01

Pos logit contributions
 sailors+0.069
 steam+0.069
kins+0.068
CA+0.067
 batteries+0.066
Neg logit contributions
 salon-0.121
aring-0.111
Instead-0.105
spe-0.101
 Sadly-0.099
Token share
Token ID2648
Feature activation+3.61e-01

Pos logit contributions
CA+0.054
 emergencies+0.052
 steam+0.050
 lava+0.049
 sailors+0.049
Neg logit contributions
 salon-0.048
aring-0.040
Instead-0.036
spe-0.035
ho-0.034
Token with
Token ID351
Feature activation-8.01e-02

Pos logit contributions
CA+0.020
 emergencies+0.018
 steam+0.017
agons+0.017
 lava+0.017
Neg logit contributions
 salon-0.022
aring-0.020
spe-0.018
ho-0.018
Instead-0.017
Token the
Token ID262
Feature activation+4.86e-02

Pos logit contributions
 salon+0.005
 Even+0.005
Instead+0.004
aring+0.004
 While+0.004
Neg logit contributions
CA-0.004
 emergencies-0.004
agons-0.004
 pans-0.004
 steam-0.003
Token colorful
Token ID20239
Feature activation+7.77e-01

Pos logit contributions
CA+0.013
 emergencies+0.013
 steam+0.012
 sailors+0.012
 lava+0.012
Neg logit contributions
 salon-0.026
aring-0.023
spe-0.021
Instead-0.021
ho-0.021
Token cand
Token ID2658
Feature activation+3.71e-01

Pos logit contributions
CA+0.029
 emergencies+0.026
 steam+0.024
 lava+0.024
 sailors+0.023
Neg logit contributions
 salon-0.061
aring-0.055
spe-0.052
Instead-0.051
ho-0.050
Tokenies
Token ID444
Feature activation+9.73e-01

Pos logit contributions
CA+0.017
 emergencies+0.016
 steam+0.016
 sailors+0.016
kins+0.016
Neg logit contributions
 salon-0.026
aring-0.023
spe-0.021
Instead-0.021
ho-0.020
Token and
Token ID290
Feature activation+6.10e-01

Pos logit contributions
 steam+0.040
kins+0.040
 sailors+0.039
 emergencies+0.038
 lava+0.037
Neg logit contributions
 salon-0.070
aring-0.064
Instead-0.060
spe-0.059
 Sadly-0.057
Token ch
Token ID442
Feature activation+7.63e-01

Pos logit contributions
 steam+0.026
 pans+0.025
 sailors+0.025
 batteries+0.024
kins+0.024
Neg logit contributions
aring-0.046
 salon-0.045
itating-0.037
Instead-0.037
ared-0.037
Tokenocol
Token ID4668
Feature activation+3.09e+00

Pos logit contributions
CA+0.024
 emergencies+0.023
 steam+0.022
 lava+0.020
 sailors+0.020
Neg logit contributions
 salon-0.064
aring-0.060
spe-0.055
ho-0.054
Instead-0.054
Tokenates
Token ID689
Feature activation+1.45e+00

Pos logit contributions
CA+0.123
 steam+0.119
 emergencies+0.112
 shark+0.100
 aliens+0.096
Neg logit contributions
ared-0.220
 salon-0.216
aring-0.213
ho-0.213
 pad-0.209
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
kins+0.043
 steam+0.040
 sailors+0.038
 lava+0.036
 batteries+0.035
Neg logit contributions
 salon-0.127
aring-0.117
Instead-0.109
 Sadly-0.107
 While-0.104
Token She
Token ID1375
Feature activation-4.63e-01

Pos logit contributions
 salon+0.021
aring+0.020
spe+0.017
Instead+0.016
ared+0.016
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.023
 batteries-0.022
 lava-0.022
Token said
Token ID531
Feature activation-2.60e-01

Pos logit contributions
 salon+0.034
aring+0.033
itating+0.027
 perspective+0.027
olding+0.027
Neg logit contributions
CA-0.020
 steam-0.019
kins-0.018
 sailors-0.018
 pans-0.017
Token to
Token ID284
Feature activation+2.07e-01

Pos logit contributions
 salon+0.018
aring+0.016
Instead+0.015
spe+0.015
 pad+0.014
Neg logit contributions
CA-0.011
 steam-0.011
 sailors-0.011
 lava-0.011
kins-0.011
Token a
Token ID257
Feature activation+3.92e-01

Pos logit contributions
 salon+0.009
aring+0.009
spe+0.008
Instead+0.008
ho+0.008
Neg logit contributions
CA-0.005
 emergencies-0.004
 steam-0.004
 sailors-0.004
 lava-0.004
Token big
Token ID1263
Feature activation+3.11e-01

Pos logit contributions
 steam+0.017
 emergencies+0.015
CA+0.015
 coal+0.014
 pans+0.014
Neg logit contributions
aring-0.028
 salon-0.028
ared-0.026
Instead-0.025
ouncing-0.025
Token box
Token ID3091
Feature activation+3.28e-01

Pos logit contributions
 steam+0.017
 lava+0.016
 shark+0.016
 coal+0.015
CA+0.015
Neg logit contributions
 salon-0.018
aring-0.018
Instead-0.017
itating-0.016
spe-0.016
Token of
Token ID286
Feature activation+8.78e-01

Pos logit contributions
 steam+0.010
 sailors+0.010
 batteries+0.010
CA+0.010
kins+0.009
Neg logit contributions
 salon-0.026
aring-0.023
Instead-0.023
 While-0.022
 Even-0.022
Token ch
Token ID442
Feature activation+6.45e-01

Pos logit contributions
CA+0.035
 emergencies+0.033
 steam+0.032
 sailors+0.031
 lava+0.031
Neg logit contributions
 salon-0.067
aring-0.061
spe-0.056
Instead-0.055
ho-0.054
Tokenocol
Token ID4668
Feature activation+3.07e+00

Pos logit contributions
CA+0.018
 emergencies+0.016
 steam+0.015
 lava+0.014
 sailors+0.014
Neg logit contributions
 salon-0.057
aring-0.053
spe-0.049
Instead-0.048
ho-0.048
Tokenates
Token ID689
Feature activation+1.61e+00

Pos logit contributions
CA+0.118
 steam+0.115
 emergencies+0.105
 shark+0.098
 aliens+0.097
Neg logit contributions
ared-0.216
aring-0.211
 pad-0.208
 salon-0.206
ho-0.203
Token!
Token ID0
Feature activation-4.15e-01

Pos logit contributions
CA+0.050
 steam+0.048
 emergencies+0.048
 sailors+0.047
kins+0.046
Neg logit contributions
 salon-0.131
aring-0.121
Instead-0.113
spe-0.111
 Even-0.107
Token<|endoftext|>
Token ID50256
Feature activation-6.66e-01

Pos logit contributions
 salon+0.028
aring+0.025
spe+0.023
ho+0.022
Instead+0.022
Neg logit contributions
CA-0.020
 emergencies-0.019
 steam-0.018
 sailors-0.018
 lava-0.018
TokenOnce
Token ID7454
Feature activation+7.45e-01

Pos logit contributions
 salon+0.043
aring+0.038
 Even+0.038
 Sadly+0.038
Instead+0.038
Neg logit contributions
 emergencies-0.031
 sailors-0.029
 steam-0.029
CA-0.028
 pans-0.028
Token upon
Token ID2402
Feature activation+5.97e-02

Pos logit contributions
CA+0.050
 emergencies+0.048
 steam+0.047
kins+0.047
 sailors+0.046
Neg logit contributions
 salon-0.035
aring-0.030
Instead-0.026
spe-0.025
ho-0.024
Token sign
Token ID1051
Feature activation-4.98e-01

Pos logit contributions
 steam+0.001
CA+0.001
 lava+0.001
 pans+0.001
 coal+0.001
Neg logit contributions
 salon-0.002
aring-0.002
spe-0.001
ared-0.001
Instead-0.001
Token that
Token ID326
Feature activation+8.38e-01

Pos logit contributions
 salon+0.039
aring+0.036
Instead+0.035
spe+0.034
 Sadly+0.034
Neg logit contributions
 steam-0.017
CA-0.017
 emergencies-0.016
 batteries-0.016
 sailors-0.015
Token says
Token ID1139
Feature activation+5.51e-01

Pos logit contributions
CA+0.046
 emergencies+0.045
 steam+0.042
 sailors+0.042
 lava+0.042
Neg logit contributions
 salon-0.051
aring-0.045
spe-0.040
Instead-0.040
ho-0.039
Token "
Token ID366
Feature activation+2.29e-01

Pos logit contributions
CA+0.038
rob+0.037
 emergencies+0.036
agons+0.036
 batteries+0.035
Neg logit contributions
 salon-0.026
aring-0.022
ho-0.019
spe-0.019
Instead-0.018
TokenCirc
Token ID31560
Feature activation+1.20e+00

Pos logit contributions
CA+0.012
 emergencies+0.012
 steam+0.011
 lava+0.011
 sailors+0.011
Neg logit contributions
 salon-0.014
aring-0.013
spe-0.012
Instead-0.011
ho-0.011
Tokenus
Token ID385
Feature activation+3.06e+00

Pos logit contributions
CA+0.058
 emergencies+0.052
 steam+0.049
 lava+0.048
 batteries+0.048
Neg logit contributions
 salon-0.085
aring-0.081
spe-0.073
ho-0.071
Instead-0.069
Token".
Token ID1911
Feature activation+8.67e-01

Pos logit contributions
CA+0.123
 emergencies+0.116
 steam+0.112
 sailors+0.108
 lava+0.107
Neg logit contributions
 salon-0.232
aring-0.210
spe-0.193
Instead-0.191
ho-0.187
Token Lily
Token ID20037
Feature activation+4.17e-01

Pos logit contributions
CA+0.038
 emergencies+0.035
 steam+0.034
 batteries+0.033
 sailors+0.032
Neg logit contributions
 salon-0.061
aring-0.058
ho-0.053
spe-0.053
Instead-0.050
Token and
Token ID290
Feature activation-4.88e-01

Pos logit contributions
CA+0.023
 steam+0.022
 emergencies+0.022
 sailors+0.021
 batteries+0.021
Neg logit contributions
 salon-0.025
aring-0.022
spe-0.020
Instead-0.019
ho-0.019
Token Tom
Token ID4186
Feature activation+2.32e-01

Pos logit contributions
 salon+0.031
aring+0.027
Instead+0.024
ho+0.024
spe+0.024
Neg logit contributions
CA-0.026
 emergencies-0.025
 steam-0.024
 lava-0.024
 sailors-0.024
Token are
Token ID389
Feature activation-7.76e-01

Pos logit contributions
 him+0.012
 sailors+0.012
 steam+0.012
CA+0.012
 aliens+0.011
Neg logit contributions
 salon-0.015
ress-0.013
spe-0.012
aring-0.012
 glimpse-0.010
Token smiled
Token ID13541
Feature activation+7.12e-01

Pos logit contributions
CA+0.007
 steam+0.007
 lava+0.007
kins+0.007
 sailors+0.007
Neg logit contributions
 salon-0.009
aring-0.009
spe-0.007
Instead-0.007
 perspective-0.007
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
CA+0.034
 emergencies+0.033
rob+0.030
agons+0.030
 steam+0.029
Neg logit contributions
 salon-0.048
aring-0.045
spe-0.041
Instead-0.041
ho-0.040
Token "
Token ID366
Feature activation+2.16e-01

Pos logit contributions
 salon+0.013
aring+0.011
spe+0.011
ho+0.010
Instead+0.010
Neg logit contributions
CA-0.009
 emergencies-0.008
 steam-0.008
 lava-0.008
 batteries-0.007
TokenThese
Token ID4711
Feature activation-2.14e-01

Pos logit contributions
CA+0.011
 steam+0.010
 emergencies+0.010
 lava+0.010
 sailors+0.010
Neg logit contributions
 salon-0.015
aring-0.013
spe-0.012
ho-0.011
ared-0.011
Token sa
Token ID473
Feature activation+7.73e-01

Pos logit contributions
 salon+0.017
aring+0.015
spe+0.014
ho+0.014
Instead+0.013
Neg logit contributions
 emergencies-0.008
CA-0.008
 steam-0.008
 batteries-0.008
 sailors-0.007
Tokenus
Token ID385
Feature activation+3.06e+00

Pos logit contributions
CA+0.017
 emergencies+0.015
 steam+0.013
 lava+0.012
 sailors+0.012
Neg logit contributions
 salon-0.074
aring-0.069
spe-0.064
Instead-0.064
ho-0.064
Tokenages
Token ID1095
Feature activation+1.54e+00

Pos logit contributions
CA+0.164
 emergencies+0.159
 steam+0.154
 sailors+0.152
 lava+0.150
Neg logit contributions
 salon-0.190
aring-0.166
spe-0.150
Instead-0.149
ho-0.143
Token are
Token ID389
Feature activation+2.47e-01

Pos logit contributions
 steam+0.091
 lava+0.089
CA+0.088
kins+0.088
 emergencies+0.087
Neg logit contributions
 salon-0.085
aring-0.073
spe-0.066
Instead-0.065
 pad-0.062
Token not
Token ID407
Feature activation+1.02e+00

Pos logit contributions
CA+0.013
 emergencies+0.012
 steam+0.012
 lava+0.012
 sailors+0.012
Neg logit contributions
 salon-0.016
aring-0.014
spe-0.013
Instead-0.012
ho-0.012
Token bitter
Token ID12922
Feature activation-8.04e-01

Pos logit contributions
 emergencies+0.048
CA+0.048
 steam+0.048
 lava+0.046
 sailors+0.046
Neg logit contributions
 salon-0.069
aring-0.061
spe-0.056
ho-0.055
Instead-0.055
Token at
Token ID379
Feature activation-5.60e-01

Pos logit contributions
 salon+0.058
aring+0.048
spe+0.048
Instead+0.047
 Sadly+0.045
Neg logit contributions
 lava-0.035
 emergencies-0.034
 steam-0.033
CA-0.033
 sailors-0.033
Token sign
Token ID1051
Feature activation-4.80e-01

Pos logit contributions
 salon+0.002
aring+0.001
spe+0.001
ared+0.001
ress+0.001
Neg logit contributions
 steam-0.001
CA-0.001
 lava-0.001
 pans-0.001
 coal-0.001
Token that
Token ID326
Feature activation+8.66e-01

Pos logit contributions
 salon+0.037
aring+0.033
Instead+0.032
spe+0.031
 Sadly+0.030
Neg logit contributions
CA-0.018
 steam-0.018
 emergencies-0.018
 batteries-0.016
 sailors-0.016
Token said
Token ID531
Feature activation+4.28e-01

Pos logit contributions
 emergencies+0.052
CA+0.051
agons+0.049
 sailors+0.048
agles+0.047
Neg logit contributions
 salon-0.045
aring-0.038
ho-0.036
spe-0.036
Instead-0.035
Token "
Token ID366
Feature activation+1.94e-01

Pos logit contributions
CA+0.029
 emergencies+0.028
rob+0.028
agons+0.027
 batteries+0.027
Neg logit contributions
 salon-0.020
aring-0.017
ho-0.015
spe-0.015
Instead-0.014
TokenCirc
Token ID31560
Feature activation+1.24e+00

Pos logit contributions
 emergencies+0.010
CA+0.010
 steam+0.010
 lava+0.010
 sailors+0.009
Neg logit contributions
 salon-0.012
aring-0.011
spe-0.010
ho-0.010
Instead-0.010
Tokenus
Token ID385
Feature activation+3.06e+00

Pos logit contributions
CA+0.044
 emergencies+0.037
 steam+0.034
 lava+0.032
 batteries+0.032
Neg logit contributions
aring-0.101
 salon-0.101
spe-0.092
ho-0.091
Instead-0.087
Token".
Token ID1911
Feature activation+7.84e-01

Pos logit contributions
CA+0.130
 emergencies+0.124
 steam+0.118
 sailors+0.114
 lava+0.113
Neg logit contributions
 salon-0.223
aring-0.204
spe-0.186
Instead-0.183
ho-0.181
Token They
Token ID1119
Feature activation+4.91e-01

Pos logit contributions
CA+0.042
 emergencies+0.040
 steam+0.039
 sailors+0.038
 lava+0.038
Neg logit contributions
 salon-0.050
aring-0.044
spe-0.040
Instead-0.039
ho-0.039
Token ran
Token ID4966
Feature activation+4.49e-01

Pos logit contributions
CA+0.026
 sailors+0.025
 steam+0.025
kins+0.023
 lava+0.023
Neg logit contributions
 salon-0.032
aring-0.031
spe-0.026
ress-0.025
olding-0.024
Token inside
Token ID2641
Feature activation+4.51e-01

Pos logit contributions
CA+0.023
 steam+0.022
 sailors+0.021
 lava+0.021
 emergencies+0.021
Neg logit contributions
 salon-0.030
aring-0.026
spe-0.024
Instead-0.024
ho-0.021
Token the
Token ID262
Feature activation+9.00e-01

Pos logit contributions
CA+0.020
 emergencies+0.019
 steam+0.019
 sailors+0.018
 lava+0.018
Neg logit contributions
 salon-0.032
aring-0.029
spe-0.027
Instead-0.026
ho-0.026
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
kins+0.053
 steam+0.053
 sailors+0.050
 lava+0.050
 pans+0.050
Neg logit contributions
 salon-0.099
aring-0.091
Instead-0.085
 Sadly-0.083
spe-0.083
Token her
Token ID607
Feature activation+5.45e-01

Pos logit contributions
 steam+0.047
 pans+0.045
 lava+0.044
 emergencies+0.044
 sailors+0.043
Neg logit contributions
 salon-0.080
aring-0.080
itating-0.067
Instead-0.067
ared-0.067
Token favourite
Token ID12507
Feature activation+1.13e+00

Pos logit contributions
CA+0.031
 emergencies+0.029
 steam+0.027
rob+0.027
 sailors+0.027
Neg logit contributions
 salon-0.033
aring-0.028
spe-0.026
ho-0.026
Instead-0.025
Token,
Token ID11
Feature activation+5.61e-01

Pos logit contributions
 steam+0.048
CA+0.048
 emergencies+0.046
 batteries+0.046
 lava+0.045
Neg logit contributions
 salon-0.080
aring-0.076
spe-0.067
Instead-0.067
ho-0.065
Token ch
Token ID442
Feature activation+9.95e-01

Pos logit contributions
 steam+0.026
CA+0.024
 emergencies+0.024
 lava+0.023
 sailors+0.023
Neg logit contributions
 salon-0.039
aring-0.038
Instead-0.033
ared-0.032
spe-0.032
Tokenocol
Token ID4668
Feature activation+3.05e+00

Pos logit contributions
CA+0.020
 emergencies+0.018
 steam+0.016
 sailors+0.015
 lava+0.015
Neg logit contributions
 salon-0.096
aring-0.089
spe-0.084
Instead-0.084
ho-0.082
Tokenates
Token ID689
Feature activation+1.80e+00

Pos logit contributions
CA+0.120
 steam+0.115
 emergencies+0.113
 aliens+0.100
 batteries+0.095
Neg logit contributions
 salon-0.221
ared-0.217
ho-0.214
aring-0.213
 pad-0.213
Token!
Token ID0
Feature activation+1.54e-01

Pos logit contributions
 steam+0.054
kins+0.054
 sailors+0.051
 lava+0.051
CA+0.049
Neg logit contributions
 salon-0.148
aring-0.137
Instead-0.128
 Sadly-0.125
spe-0.124
Token She
Token ID1375
Feature activation-2.98e-01

Pos logit contributions
CA+0.009
 steam+0.008
 emergencies+0.008
 sailors+0.008
 lava+0.008
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.007
ho-0.007
Instead-0.007
Token asked
Token ID1965
Feature activation+2.18e-01

Pos logit contributions
 salon+0.020
aring+0.020
itating+0.016
Instead+0.016
 perspective+0.016
Neg logit contributions
CA-0.014
 steam-0.013
kins-0.013
 sailors-0.013
 pans-0.012
Token mummy
Token ID38567
Feature activation-2.29e-01

Pos logit contributions
CA+0.011
 emergencies+0.011
 steam+0.010
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.014
aring-0.013
spe-0.012
Instead-0.011
ho-0.011
Token a
Token ID257
Feature activation+5.31e-01

Pos logit contributions
 steam+0.016
 emergencies+0.015
 batteries+0.015
 lava+0.013
 sparks+0.013
Neg logit contributions
aring-0.055
 salon-0.052
ared-0.049
Instead-0.049
ashing-0.048
Token big
Token ID1263
Feature activation+6.76e-01

Pos logit contributions
 steam+0.021
CA+0.019
 pans+0.019
 emergencies+0.019
 coal+0.018
Neg logit contributions
aring-0.042
 salon-0.039
ared-0.038
Instead-0.036
ashing-0.035
Token box
Token ID3091
Feature activation+2.21e-01

Pos logit contributions
 steam+0.028
 lava+0.027
 coal+0.026
 batteries+0.025
CA+0.025
Neg logit contributions
aring-0.052
 salon-0.048
Instead-0.047
itating-0.045
spe-0.044
Token of
Token ID286
Feature activation+1.04e+00

Pos logit contributions
 steam+0.006
CA+0.005
 lava+0.005
kins+0.005
 emergencies+0.005
Neg logit contributions
 salon-0.019
aring-0.018
Instead-0.017
 tant-0.017
 Sadly-0.016
Token ch
Token ID442
Feature activation+7.51e-01

Pos logit contributions
 emergencies+0.037
CA+0.037
 steam+0.036
 batteries+0.035
 lava+0.034
Neg logit contributions
 salon-0.084
aring-0.080
spe-0.071
Instead-0.070
ho-0.070
Tokenocol
Token ID4668
Feature activation+3.05e+00

Pos logit contributions
CA+0.017
 emergencies+0.016
 steam+0.014
 sailors+0.013
 lava+0.013
Neg logit contributions
 salon-0.070
aring-0.065
spe-0.060
Instead-0.060
ho-0.059
Tokenates
Token ID689
Feature activation+1.51e+00

Pos logit contributions
CA+0.108
 steam+0.108
 emergencies+0.101
 shark+0.097
 sailors+0.092
Neg logit contributions
 salon-0.219
ared-0.217
aring-0.215
 pad-0.214
ho-0.209
Token!
Token ID0
Feature activation-1.11e-01

Pos logit contributions
 steam+0.043
kins+0.041
CA+0.040
 lava+0.040
 emergencies+0.040
Neg logit contributions
 salon-0.127
aring-0.119
Instead-0.112
spe-0.111
 Sadly-0.108
Token
Token ID220
Feature activation-1.18e+00

Pos logit contributions
 salon+0.007
aring+0.007
spe+0.006
itating+0.006
ho+0.006
Neg logit contributions
CA-0.005
 Bert-0.005
 Pig-0.005
 steam-0.005
 emergencies-0.005
Token
Token ID198
Feature activation+4.46e-02

Pos logit contributions
 salon+0.081
aring+0.072
spe+0.066
ho+0.065
Instead+0.064
Neg logit contributions
CA-0.056
 emergencies-0.054
 steam-0.051
 sailors-0.050
 lava-0.049
Token
Token ID198
Feature activation+3.46e-01

Pos logit contributions
CA+0.002
 emergencies+0.002
 steam+0.001
 sailors+0.001
kins+0.001
Neg logit contributions
 salon-0.003
aring-0.003
spe-0.003
ho-0.003
Instead-0.003
Token sign
Token ID1051
Feature activation-1.29e-01

Pos logit contributions
 steam+0.023
CA+0.022
 pans+0.021
 lava+0.021
 emergencies+0.020
Neg logit contributions
aring-0.037
 salon-0.037
ared-0.033
spe-0.032
Instead-0.031
Token that
Token ID326
Feature activation+1.00e+00

Pos logit contributions
 salon+0.010
aring+0.009
Instead+0.008
spe+0.008
 Sadly+0.008
Neg logit contributions
 steam-0.005
CA-0.005
 batteries-0.005
 emergencies-0.005
 sailors-0.004
Token said
Token ID531
Feature activation+4.53e-01

Pos logit contributions
CA+0.059
 emergencies+0.059
agons+0.056
 lava+0.055
 sailors+0.055
Neg logit contributions
 salon-0.055
aring-0.046
Instead-0.043
spe-0.042
ho-0.042
Token "
Token ID366
Feature activation+1.21e-01

Pos logit contributions
CA+0.030
 emergencies+0.029
agons+0.028
 steam+0.028
 sailors+0.028
Neg logit contributions
 salon-0.022
aring-0.019
spe-0.016
Instead-0.016
ho-0.016
TokenCirc
Token ID31560
Feature activation+1.24e+00

Pos logit contributions
CA+0.006
 emergencies+0.006
 steam+0.006
 sailors+0.006
 lava+0.006
Neg logit contributions
 salon-0.008
aring-0.007
spe-0.006
Instead-0.006
ho-0.006
Tokenus
Token ID385
Feature activation+3.04e+00

Pos logit contributions
CA+0.046
 emergencies+0.038
 steam+0.035
 lava+0.034
 batteries+0.033
Neg logit contributions
 salon-0.103
aring-0.101
spe-0.092
ho-0.089
Instead-0.086
Token".
Token ID1911
Feature activation+8.49e-01

Pos logit contributions
CA+0.135
 emergencies+0.125
 steam+0.119
 lava+0.114
 batteries+0.113
Neg logit contributions
 salon-0.219
aring-0.205
spe-0.184
ho-0.181
Instead-0.179
Token Mom
Token ID11254
Feature activation+1.80e-01

Pos logit contributions
CA+0.034
 steam+0.030
 emergencies+0.030
 pans+0.029
 batteries+0.029
Neg logit contributions
 salon-0.062
aring-0.061
ho-0.055
spe-0.055
 glimpse-0.051
Token bought
Token ID5839
Feature activation+4.12e-01

Pos logit contributions
CA+0.009
 steam+0.008
 emergencies+0.008
 sailors+0.008
 batteries+0.008
Neg logit contributions
 salon-0.012
aring-0.011
spe-0.010
Instead-0.010
ho-0.010
Token tickets
Token ID8587
Feature activation+5.50e-01

Pos logit contributions
 steam+0.015
CA+0.014
 emergencies+0.014
 batteries+0.013
 lava+0.013
Neg logit contributions
 salon-0.033
aring-0.031
spe-0.028
Instead-0.028
ho-0.027
Token for
Token ID329
Feature activation+4.75e-02

Pos logit contributions
 steam+0.025
CA+0.025
 sailors+0.025
 emergencies+0.025
 batteries+0.025
Neg logit contributions
 salon-0.037
aring-0.033
Instead-0.030
spe-0.030
 Sadly-0.029
Token a
Token ID257
Feature activation-1.88e-02

Pos logit contributions
 steam+0.017
 emergencies+0.015
 batteries+0.015
 lava+0.015
CA+0.015
Neg logit contributions
 salon-0.035
aring-0.034
spe-0.030
ho-0.030
Instead-0.029
Token big
Token ID1263
Feature activation+2.62e-02

Pos logit contributions
aring+0.001
ared+0.001
 salon+0.001
Instead+0.001
 Even+0.001
Neg logit contributions
 steam-0.001
 pans-0.001
CA-0.001
 emergencies-0.001
 batteries-0.001
Token box
Token ID3091
Feature activation-3.87e-02

Pos logit contributions
 steam+0.001
 lava+0.001
 emergencies+0.001
 batteries+0.001
CA+0.001
Neg logit contributions
aring-0.002
 salon-0.002
Instead-0.002
spe-0.002
ared-0.002
Token of
Token ID286
Feature activation+6.88e-01

Pos logit contributions
 salon+0.003
aring+0.003
Instead+0.003
 tant+0.003
 Sadly+0.003
Neg logit contributions
 steam-0.001
CA-0.001
 sailors-0.001
 batteries-0.001
kins-0.001
Token ch
Token ID442
Feature activation+5.58e-01

Pos logit contributions
CA+0.027
 emergencies+0.025
 steam+0.024
 sailors+0.023
 lava+0.023
Neg logit contributions
 salon-0.053
aring-0.048
spe-0.044
Instead-0.044
ho-0.043
Tokenocol
Token ID4668
Feature activation+3.03e+00

Pos logit contributions
CA+0.018
 emergencies+0.017
 steam+0.016
rob+0.015
 lava+0.014
Neg logit contributions
 salon-0.046
aring-0.044
spe-0.039
ho-0.039
Instead-0.038
Tokenates
Token ID689
Feature activation+1.36e+00

Pos logit contributions
CA+0.104
 steam+0.103
 emergencies+0.095
 aliens+0.085
 shark+0.082
Neg logit contributions
 salon-0.231
ared-0.221
aring-0.220
 pad-0.218
ho-0.216
Token.
Token ID13
Feature activation-5.35e-03

Pos logit contributions
 steam+0.036
CA+0.036
 emergencies+0.036
kins+0.035
 sailors+0.035
Neg logit contributions
 salon-0.117
aring-0.109
Instead-0.101
spe-0.101
 Sadly-0.098
Token It
Token ID632
Feature activation-2.60e-01

Pos logit contributions
 salon+0.000
aring+0.000
spe+0.000
ho+0.000
Instead+0.000
Neg logit contributions
CA-0.000
 emergencies-0.000
 steam-0.000
 lava-0.000
 sailors-0.000
Token was
Token ID373
Feature activation+1.04e-01

Pos logit contributions
 salon+0.017
aring+0.015
spe+0.013
Instead+0.013
ho+0.013
Neg logit contributions
CA-0.014
 steam-0.013
 emergencies-0.013
 lava-0.012
 batteries-0.012
Token so
Token ID523
Feature activation-3.08e-01

Pos logit contributions
CA+0.005
 emergencies+0.005
 steam+0.004
 sailors+0.004
 lava+0.004
Neg logit contributions
 salon-0.007
aring-0.006
spe-0.006
Instead-0.006
ho-0.006
Token cakes
Token ID30849
Feature activation-2.70e-01

Pos logit contributions
 lava+0.008
 steam+0.007
 sailors+0.007
 pans+0.007
 aliens+0.007
Neg logit contributions
aring-0.013
 salon-0.012
ared-0.011
olding-0.011
itating-0.011
Token and
Token ID290
Feature activation+9.60e-01

Pos logit contributions
 salon+0.018
aring+0.017
Instead+0.016
spe+0.015
 Sadly+0.015
Neg logit contributions
kins-0.012
 steam-0.012
 lava-0.012
CA-0.012
 emergencies-0.012
Token cookies
Token ID14746
Feature activation+2.53e-01

Pos logit contributions
 steam+0.035
CA+0.035
 lava+0.034
 emergencies+0.034
 pans+0.033
Neg logit contributions
 salon-0.075
aring-0.074
spe-0.064
Instead-0.064
ho-0.063
Token and
Token ID290
Feature activation+9.42e-01

Pos logit contributions
CA+0.012
 emergencies+0.011
 steam+0.011
 lava+0.011
kins+0.011
Neg logit contributions
 salon-0.017
aring-0.016
Instead-0.014
spe-0.014
 Sadly-0.014
Token ch
Token ID442
Feature activation+1.04e+00

Pos logit contributions
 steam+0.034
 lava+0.033
 emergencies+0.033
CA+0.031
 sailors+0.031
Neg logit contributions
 salon-0.076
aring-0.074
Instead-0.065
itating-0.065
ared-0.064
Tokenocol
Token ID4668
Feature activation+3.02e+00

Pos logit contributions
CA+0.032
 emergencies+0.029
 steam+0.028
 sailors+0.026
 lava+0.026
Neg logit contributions
 salon-0.089
aring-0.082
spe-0.076
Instead-0.075
ho-0.074
Tokenates
Token ID689
Feature activation+1.55e+00

Pos logit contributions
CA+0.120
 steam+0.113
 shark+0.110
 emergencies+0.108
 batteries+0.096
Neg logit contributions
ared-0.203
aring-0.202
ho-0.197
 pad-0.196
 salon-0.191
Token and
Token ID290
Feature activation+7.99e-01

Pos logit contributions
 steam+0.050
CA+0.049
kins+0.048
 emergencies+0.048
 lava+0.047
Neg logit contributions
 salon-0.127
aring-0.116
Instead-0.108
spe-0.106
 Sadly-0.103
Token ice
Token ID4771
Feature activation+1.01e+00

Pos logit contributions
 steam+0.030
 emergencies+0.029
 lava+0.029
CA+0.028
 sailors+0.028
Neg logit contributions
 salon-0.063
aring-0.061
Instead-0.053
spe-0.053
itating-0.052
Token cream
Token ID8566
Feature activation+6.60e-01

Pos logit contributions
CA+0.043
 emergencies+0.041
 steam+0.038
 sailors+0.037
 batteries+0.036
Neg logit contributions
 salon-0.075
aring-0.068
spe-0.062
ho-0.061
Instead-0.061
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
CA+0.025
 emergencies+0.023
 steam+0.022
 sailors+0.021
 lava+0.020
Neg logit contributions
 salon-0.052
aring-0.048
spe-0.044
ho-0.043
Instead-0.043
Token
Token ID198
Feature activation+4.38e-01

Pos logit contributions
CA+0.002
 emergencies+0.002
 steam+0.002
 sailors+0.002
 batteries+0.002
Neg logit contributions
 salon-0.004
aring-0.003
spe-0.003
Instead-0.003
ho-0.003
Token"
Token ID1
Feature activation+9.27e-01

Pos logit contributions
CA+0.026
 steam+0.024
 emergencies+0.024
 pans+0.023
kins+0.023
Neg logit contributions
 salon-0.026
aring-0.023
spe-0.020
ho-0.020
ared-0.019
TokenCh
Token ID1925
Feature activation+1.05e+00

Pos logit contributions
CA+0.056
 emergencies+0.055
 steam+0.053
 sailors+0.052
 lava+0.052
Neg logit contributions
 salon-0.052
aring-0.045
spe-0.040
Instead-0.039
ho-0.038
Tokenoo
Token ID2238
Feature activation+1.58e+00

Pos logit contributions
CA+0.058
 pans+0.055
 emergencies+0.054
 lava+0.053
 steam+0.053
Neg logit contributions
 salon-0.064
aring-0.064
spe-0.053
 Even-0.050
olding-0.049
Token cho
Token ID1727
Feature activation+1.16e+00

Pos logit contributions
CA+0.078
 emergencies+0.075
 steam+0.069
 sailors+0.069
 lava+0.068
Neg logit contributions
 salon-0.106
aring-0.097
spe-0.087
Instead-0.085
ho-0.084
Tokeno
Token ID78
Feature activation+2.99e+00

Pos logit contributions
CA+0.063
 emergencies+0.060
 steam+0.059
 sailors+0.058
 lava+0.057
Neg logit contributions
 salon-0.070
aring-0.061
spe-0.056
Instead-0.055
ho-0.053
Token,
Token ID11
Feature activation+1.68e+00

Pos logit contributions
 steam+0.115
CA+0.115
 sailors+0.107
 emergencies+0.106
 lava+0.105
Neg logit contributions
 salon-0.223
aring-0.192
Instead-0.189
spe-0.185
 Sadly-0.181
Token this
Token ID428
Feature activation+5.23e-01

Pos logit contributions
CA+0.074
 emergencies+0.070
 steam+0.067
 sailors+0.065
 lava+0.065
Neg logit contributions
 salon-0.121
aring-0.109
spe-0.100
Instead-0.098
ho-0.097
Token is
Token ID318
Feature activation+6.77e-01

Pos logit contributions
CA+0.027
 emergencies+0.026
 steam+0.025
 sailors+0.024
 lava+0.024
Neg logit contributions
 salon-0.034
aring-0.030
spe-0.027
Instead-0.027
ho-0.026
Token the
Token ID262
Feature activation+4.26e-01

Pos logit contributions
kins+0.035
CA+0.034
agles+0.032
rob+0.032
agons+0.031
Neg logit contributions
 salon-0.042
aring-0.038
spe-0.034
Instead-0.034
 Even-0.032
Token red
Token ID2266
Feature activation+3.47e-01

Pos logit contributions
CA+0.021
 emergencies+0.020
 steam+0.019
 sailors+0.018
 lava+0.018
Neg logit contributions
 salon-0.029
aring-0.026
spe-0.024
Instead-0.023
ho-0.023
Token and
Token ID290
Feature activation-1.90e-01

Pos logit contributions
CA+0.010
rob+0.010
 emergencies+0.009
agons+0.009
kins+0.009
Neg logit contributions
 salon-0.014
aring-0.013
ho-0.012
 Even-0.012
spe-0.012
Token laughed
Token ID13818
Feature activation+9.05e-01

Pos logit contributions
 salon+0.013
aring+0.013
Instead+0.011
ench+0.011
spe+0.011
Neg logit contributions
 steam-0.009
 sailors-0.009
 lava-0.008
CA-0.008
 aliens-0.008
Token and
Token ID290
Feature activation+4.28e-01

Pos logit contributions
CA+0.047
 emergencies+0.044
rob+0.041
agons+0.040
 pans+0.040
Neg logit contributions
 salon-0.057
aring-0.054
Instead-0.048
spe-0.047
 Even-0.046
Token ate
Token ID15063
Feature activation+8.28e-01

Pos logit contributions
CA+0.021
 steam+0.021
 sailors+0.020
 emergencies+0.020
 lava+0.020
Neg logit contributions
 salon-0.028
aring-0.026
Instead-0.023
spe-0.023
ho-0.021
Token ch
Token ID442
Feature activation+7.07e-01

Pos logit contributions
CA+0.041
 emergencies+0.037
agons+0.035
 sailors+0.034
 steam+0.034
Neg logit contributions
 salon-0.056
aring-0.049
spe-0.045
ho-0.045
Instead-0.045
Tokenocol
Token ID4668
Feature activation+2.98e+00

Pos logit contributions
CA+0.031
 emergencies+0.027
rob+0.026
 steam+0.025
 batteries+0.024
Neg logit contributions
aring-0.051
 salon-0.047
ared-0.044
 tant-0.043
ashing-0.043
Tokenates
Token ID689
Feature activation+1.58e+00

Pos logit contributions
CA+0.153
 steam+0.140
 emergencies+0.139
 shark+0.124
 alien+0.116
Neg logit contributions
ared-0.173
ho-0.172
aring-0.171
 salon-0.162
a-0.161
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
CA+0.060
 emergencies+0.056
 steam+0.052
 sailors+0.050
 lava+0.050
Neg logit contributions
 salon-0.125
aring-0.114
spe-0.105
Instead-0.104
ho-0.103
Token They
Token ID1119
Feature activation+2.96e-02

Pos logit contributions
CA+0.011
 emergencies+0.011
 steam+0.011
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.011
aring-0.009
spe-0.008
Instead-0.008
ho-0.008
Token had
Token ID550
Feature activation+9.40e-02

Pos logit contributions
CA+0.002
 steam+0.002
 sailors+0.002
 lava+0.002
kins+0.002
Neg logit contributions
 salon-0.002
aring-0.002
Instead-0.001
spe-0.001
olding-0.001
Token a
Token ID257
Feature activation-4.18e-01

Pos logit contributions
CA+0.004
 emergencies+0.004
 steam+0.004
 sailors+0.004
 lava+0.004
Neg logit contributions
 salon-0.007
aring-0.006
spe-0.006
Instead-0.006
ho-0.005
Token her
Token ID607
Feature activation+4.90e-01

Pos logit contributions
 salon+0.042
aring+0.036
Instead+0.033
ho+0.033
 pad+0.032
Neg logit contributions
CA-0.032
 emergencies-0.030
 sailors-0.029
 lava-0.029
agons-0.029
Token a
Token ID257
Feature activation+7.06e-02

Pos logit contributions
CA+0.023
 emergencies+0.022
 lava+0.020
agons+0.020
rob+0.019
Neg logit contributions
 salon-0.035
aring-0.030
Instead-0.028
spe-0.027
ho-0.026
Token box
Token ID3091
Feature activation+1.80e-01

Pos logit contributions
CA+0.003
 steam+0.003
 emergencies+0.003
 sailors+0.003
 batteries+0.003
Neg logit contributions
 salon-0.005
aring-0.005
spe-0.004
Instead-0.004
ho-0.004
Token of
Token ID286
Feature activation+6.03e-01

Pos logit contributions
 steam+0.008
CA+0.008
 batteries+0.008
 sailors+0.008
 emergencies+0.008
Neg logit contributions
 salon-0.012
aring-0.010
Instead-0.010
spe-0.010
 Even-0.009
Token ch
Token ID442
Feature activation+4.44e-01

Pos logit contributions
CA+0.028
ator+0.025
 emergencies+0.024
rob+0.024
we+0.023
Neg logit contributions
 salon-0.039
 tant-0.032
 few-0.032
Instead-0.031
aring-0.031
Tokenocol
Token ID4668
Feature activation+2.98e+00

Pos logit contributions
 emergencies+0.021
CA+0.020
rob+0.019
 steam+0.019
 batteries+0.019
Neg logit contributions
 salon-0.029
aring-0.028
ared-0.025
ho-0.024
Instead-0.023
Tokenates
Token ID689
Feature activation+1.36e+00

Pos logit contributions
CA+0.114
 steam+0.111
 emergencies+0.107
 aliens+0.096
 lava+0.094
Neg logit contributions
aring-0.207
ared-0.202
 salon-0.198
ho-0.197
 pad-0.189
Token.
Token ID13
Feature activation-2.81e-01

Pos logit contributions
CA+0.065
 emergencies+0.062
 steam+0.057
 lava+0.056
 sailors+0.056
Neg logit contributions
 salon-0.095
aring-0.085
spe-0.077
ho-0.076
Instead-0.076
Token Lily
Token ID20037
Feature activation-6.07e-01

Pos logit contributions
 salon+0.020
aring+0.018
spe+0.017
ho+0.016
Instead+0.016
Neg logit contributions
CA-0.013
 emergencies-0.012
 steam-0.012
 batteries-0.011
 lava-0.011
Token opened
Token ID4721
Feature activation+5.20e-01

Pos logit contributions
 salon+0.038
aring+0.035
spe+0.031
Instead+0.030
ho+0.030
Neg logit contributions
CA-0.032
 steam-0.030
 emergencies-0.029
 sailors-0.029
 batteries-0.029
Token the
Token ID262
Feature activation+6.59e-01

Pos logit contributions
CA+0.022
 emergencies+0.022
agons+0.021
 sailors+0.020
kins+0.019
Neg logit contributions
 salon-0.038
aring-0.031
ho-0.031
spe-0.031
Instead-0.030
Token learned
Token ID4499
Feature activation+2.24e-01

Pos logit contributions
 salon+0.002
aring+0.002
spe+0.002
Instead+0.002
ho+0.002
Neg logit contributions
 sailors-0.002
CA-0.002
 steam-0.002
 aliens-0.002
 batteries-0.002
Token not
Token ID407
Feature activation+2.80e-01

Pos logit contributions
CA+0.013
 emergencies+0.012
 steam+0.012
 lava+0.012
kins+0.012
Neg logit contributions
 salon-0.013
aring-0.012
spe-0.010
Instead-0.010
ho-0.010
Token to
Token ID284
Feature activation-3.55e-01

Pos logit contributions
 emergencies+0.010
 sailors+0.009
 aliens+0.009
 happened+0.009
 steam+0.009
Neg logit contributions
 salon-0.024
ress-0.020
aney-0.019
aman-0.019
 checkout-0.019
Token judge
Token ID5052
Feature activation-1.68e+00

Pos logit contributions
 salon+0.023
spe+0.019
aring+0.019
 Sadly+0.019
ress+0.019
Neg logit contributions
 emergencies-0.017
 happen-0.016
 sailors-0.016
 him-0.016
 steam-0.015
Token by
Token ID416
Feature activation+1.34e-01

Pos logit contributions
 salon+0.130
aring+0.120
spe+0.110
Instead+0.108
ho+0.107
Neg logit contributions
CA-0.065
 emergencies-0.058
 steam-0.056
 lava-0.055
 sailors-0.053
Token appearances
Token ID11057
Feature activation-3.01e+00

Pos logit contributions
CA+0.007
 emergencies+0.006
 steam+0.006
 sailors+0.006
 lava+0.006
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.007
Instead-0.007
ho-0.007
Token.
Token ID13
Feature activation-4.24e-02

Pos logit contributions
 salon+0.254
aring+0.225
Instead+0.219
spe+0.215
 Sadly+0.211
Neg logit contributions
 emergencies-0.088
 aliens-0.085
 sailors-0.085
CA-0.084
 steam-0.084
Token They
Token ID1119
Feature activation-1.60e-01

Pos logit contributions
 salon+0.002
aring+0.002
Instead+0.001
 Even+0.001
spe+0.001
Neg logit contributions
CA-0.003
 steam-0.003
 emergencies-0.003
 lava-0.003
kins-0.003
Token learned
Token ID4499
Feature activation+1.08e-01

Pos logit contributions
 salon+0.010
aring+0.009
spe+0.007
ress+0.007
Instead+0.007
Neg logit contributions
 sailors-0.009
CA-0.009
 steam-0.009
 aliens-0.009
 batteries-0.008
Token to
Token ID284
Feature activation-2.38e-01

Pos logit contributions
CA+0.007
 emergencies+0.006
 steam+0.006
 lava+0.006
kins+0.006
Neg logit contributions
 salon-0.006
aring-0.005
spe-0.005
Instead-0.005
ho-0.005
Token help
Token ID1037
Feature activation+2.89e-01

Pos logit contributions
 salon+0.016
spe+0.014
aring+0.013
aney+0.013
 tant+0.012
Neg logit contributions
 emergencies-0.011
 sailors-0.011
 steam-0.011
 batteries-0.011
agons-0.011
Token happy
Token ID3772
Feature activation-1.12e-01

Pos logit contributions
 salon+0.058
aring+0.048
 pad+0.046
ho+0.045
 perspective+0.045
Neg logit contributions
 sailors-0.038
CA-0.037
 steam-0.035
 emergencies-0.034
kins-0.033
Token to
Token ID284
Feature activation+2.11e-01

Pos logit contributions
 salon+0.007
aring+0.006
spe+0.006
Instead+0.006
ho+0.006
Neg logit contributions
CA-0.006
 emergencies-0.006
 steam-0.005
 sailors-0.005
 lava-0.005
Token have
Token ID423
Feature activation-1.76e-01

Pos logit contributions
CA+0.015
 emergencies+0.014
 steam+0.014
 lava+0.014
 batteries+0.014
Neg logit contributions
 salon-0.010
aring-0.008
spe-0.007
Instead-0.007
ho-0.007
Token won
Token ID1839
Feature activation-4.12e-01

Pos logit contributions
 salon+0.010
aring+0.009
Instead+0.009
spe+0.008
 pad+0.008
Neg logit contributions
CA-0.010
agons-0.009
 emergencies-0.009
 pans-0.009
 steam-0.009
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
 salon+0.030
aring+0.027
spe+0.025
Instead+0.024
 Even+0.024
Neg logit contributions
CA-0.019
 emergencies-0.016
 pans-0.016
 steam-0.016
 lava-0.015
Token tournament
Token ID7756
Feature activation-2.92e+00

Pos logit contributions
 salon+0.046
aring+0.041
spe+0.037
ho+0.036
Instead+0.036
Neg logit contributions
CA-0.042
 emergencies-0.040
 steam-0.038
 lava-0.038
kins-0.037
Token and
Token ID290
Feature activation-2.85e-01

Pos logit contributions
 salon+0.213
aring+0.191
Instead+0.180
ho+0.175
spe+0.171
Neg logit contributions
 emergencies-0.115
CA-0.114
 sailors-0.112
 steam-0.109
 batteries-0.108
Token learned
Token ID4499
Feature activation+2.56e-01

Pos logit contributions
 salon+0.022
aring+0.021
Instead+0.019
ared+0.019
ashing+0.019
Neg logit contributions
 sailors-0.011
 emergencies-0.010
 steam-0.010
 lava-0.010
 batteries-0.009
Token what
Token ID644
Feature activation-4.18e-02

Pos logit contributions
 emergencies+0.011
 steam+0.011
 batteries+0.011
CA+0.011
 sailors+0.010
Neg logit contributions
 salon-0.019
aring-0.016
ho-0.015
spe-0.015
 pad-0.015
Token mild
Token ID11607
Feature activation-3.94e-01

Pos logit contributions
 salon+0.002
spe+0.002
aring+0.002
Instead+0.002
 hundred+0.002
Neg logit contributions
CA-0.002
agons-0.002
unks-0.002
ags-0.002
ator-0.002
Token mornings
Token ID31143
Feature activation+4.22e-01

Pos logit contributions
 salon+0.028
aring+0.026
spe+0.023
Instead+0.023
ho+0.023
Neg logit contributions
CA-0.017
 emergencies-0.017
 steam-0.016
 sailors-0.015
 lava-0.015
Token worry
Token ID5490
Feature activation-1.02e-03

Pos logit contributions
CA+0.057
 steam+0.055
 emergencies+0.055
 happen+0.050
 sailors+0.050
Neg logit contributions
 salon-0.053
spe-0.043
 pad-0.040
aring-0.039
 Sadly-0.038
Token,
Token ID11
Feature activation+5.03e-01

Pos logit contributions
 salon+0.000
aring+0.000
spe+0.000
Instead+0.000
ho+0.000
Neg logit contributions
 emergencies-0.000
CA-0.000
 steam-0.000
 lava-0.000
 batteries-0.000
Token Lily
Token ID20037
Feature activation+1.18e+00

Pos logit contributions
CA+0.018
 emergencies+0.018
 steam+0.018
 lava+0.017
 sailors+0.016
Neg logit contributions
 salon-0.039
aring-0.036
spe-0.034
ared-0.033
ho-0.033
Token.
Token ID13
Feature activation+7.30e-01

Pos logit contributions
CA+0.055
 emergencies+0.049
 steam+0.046
 sailors+0.046
 lava+0.046
Neg logit contributions
 salon-0.084
aring-0.080
spe-0.071
Instead-0.071
ho-0.070
Token Po
Token ID7695
Feature activation-4.63e-01

Pos logit contributions
CA+0.037
 emergencies+0.035
 steam+0.034
 sailors+0.033
 batteries+0.032
Neg logit contributions
 salon-0.048
aring-0.040
spe-0.039
Instead-0.038
 pad-0.037
Tokenpp
Token ID381
Feature activation-2.90e+00

Pos logit contributions
 salon+0.026
aring+0.024
ho+0.020
 pad+0.019
Instead+0.019
Neg logit contributions
CA-0.028
 emergencies-0.027
 lava-0.026
 sailors-0.026
 steam-0.026
Tokenies
Token ID444
Feature activation+5.31e-02

Pos logit contributions
 salon+0.208
aring+0.182
spe+0.169
Instead+0.165
ho+0.162
Neg logit contributions
CA-0.130
 emergencies-0.123
 steam-0.122
 sailors-0.119
kins-0.118
Token are
Token ID389
Feature activation-5.36e-01

Pos logit contributions
 steam+0.003
 emergencies+0.003
CA+0.003
kins+0.003
 sailors+0.003
Neg logit contributions
 salon-0.003
aring-0.003
spe-0.002
Instead-0.002
ress-0.002
Token soft
Token ID2705
Feature activation-2.36e-01

Pos logit contributions
 salon+0.033
aring+0.030
spe+0.027
Instead+0.026
ho+0.026
Neg logit contributions
CA-0.029
 emergencies-0.028
 steam-0.028
 sailors-0.027
 lava-0.026
Token and
Token ID290
Feature activation+2.57e-01

Pos logit contributions
 salon+0.012
aring+0.010
ho+0.008
Instead+0.008
spe+0.008
Neg logit contributions
CA-0.016
 emergencies-0.015
 steam-0.014
agons-0.014
 sailors-0.014
Token gentle
Token ID10296
Feature activation-2.72e-01

Pos logit contributions
CA+0.012
 emergencies+0.012
 steam+0.012
 sailors+0.011
 lava+0.011
Neg logit contributions
 salon-0.017
aring-0.016
spe-0.014
Instead-0.014
ho-0.014
Token you
Token ID345
Feature activation-9.14e-01

Pos logit contributions
 salon+0.013
aring+0.011
Instead+0.011
 Even+0.010
spe+0.010
Neg logit contributions
CA-0.010
rob-0.009
 steam-0.008
agons-0.008
 Tech-0.008
Token so
Token ID523
Feature activation-7.21e-01

Pos logit contributions
 salon+0.081
aring+0.071
spe+0.069
Instead+0.067
ho+0.066
Neg logit contributions
 emergencies-0.025
CA-0.024
 steam-0.023
 sailors-0.023
 lava-0.022
Token you
Token ID345
Feature activation-9.65e-01

Pos logit contributions
 salon+0.047
aring+0.040
spe+0.036
ho+0.035
Instead+0.035
Neg logit contributions
 emergencies-0.038
CA-0.037
 steam-0.036
 lava-0.036
 sailors-0.036
Token can
Token ID460
Feature activation-8.17e-01

Pos logit contributions
 salon+0.055
aring+0.046
spe+0.042
Instead+0.041
ho+0.040
Neg logit contributions
CA-0.057
 emergencies-0.055
 steam-0.055
 sailors-0.054
 lava-0.053
Token do
Token ID466
Feature activation-9.97e-01

Pos logit contributions
 salon+0.048
aring+0.042
spe+0.039
Instead+0.037
ho+0.037
Neg logit contributions
CA-0.045
 emergencies-0.044
 steam-0.044
 sailors-0.043
 lava-0.042
Token your
Token ID534
Feature activation-2.76e+00

Pos logit contributions
 salon+0.068
aring+0.063
Instead+0.056
spe+0.056
 Even+0.054
Neg logit contributions
CA-0.048
 emergencies-0.043
 steam-0.041
 sailors-0.040
rob-0.040
Token best
Token ID1266
Feature activation-1.30e+00

Pos logit contributions
 salon+0.172
aring+0.152
spe+0.136
Instead+0.135
ho+0.131
Neg logit contributions
CA-0.150
 emergencies-0.143
 steam-0.138
 sailors-0.135
 lava-0.134
Token."
Token ID526
Feature activation-1.85e-01

Pos logit contributions
 salon+0.099
aring+0.091
spe+0.082
Instead+0.082
 pad+0.079
Neg logit contributions
CA-0.054
 emergencies-0.048
 steam-0.046
 lava-0.045
rob-0.044
Token
Token ID198
Feature activation-3.37e-01

Pos logit contributions
 salon+0.010
aring+0.009
spe+0.008
Instead+0.008
ho+0.008
Neg logit contributions
CA-0.011
 emergencies-0.011
 steam-0.010
 batteries-0.010
 sailors-0.010
Token
Token ID198
Feature activation+1.67e-02

Pos logit contributions
 salon+0.017
aring+0.015
Instead+0.014
 Even+0.014
 Sadly+0.013
Neg logit contributions
 emergencies-0.021
CA-0.021
 batteries-0.021
 lava-0.020
 sailors-0.020
TokenJoe
Token ID19585
Feature activation-1.12e-01

Pos logit contributions
CA+0.001
 emergencies+0.001
 steam+0.001
 sailors+0.001
 lava+0.001
Neg logit contributions
 salon-0.001
aring-0.001
spe-0.001
ho-0.001
Instead-0.001
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
 salon+0.056
aring+0.050
spe+0.050
Instead+0.049
ho+0.049
Neg logit contributions
 emergencies-0.014
 sailors-0.013
kins-0.013
 steam-0.012
 batteries-0.011
Token You
Token ID921
Feature activation-1.24e+00

Pos logit contributions
 salon+0.008
aring+0.008
Instead+0.007
spe+0.007
ho+0.006
Neg logit contributions
CA-0.008
 emergencies-0.007
 steam-0.007
 lava-0.007
 sailors-0.007
Token did
Token ID750
Feature activation-3.11e-01

Pos logit contributions
 salon+0.061
aring+0.053
spe+0.046
Instead+0.045
ho+0.044
Neg logit contributions
CA-0.083
 emergencies-0.080
 steam-0.078
 sailors-0.076
 lava-0.076
Token not
Token ID407
Feature activation-3.54e-01

Pos logit contributions
 salon+0.017
aring+0.014
spe+0.013
ho+0.012
Instead+0.012
Neg logit contributions
CA-0.020
 emergencies-0.019
 steam-0.019
 sailors-0.018
 lava-0.018
Token do
Token ID466
Feature activation-1.00e+00

Pos logit contributions
 salon+0.021
spe+0.017
aring+0.016
ho+0.016
 Sadly+0.015
Neg logit contributions
 emergencies-0.020
 steam-0.020
 sailors-0.020
CA-0.020
 lava-0.019
Token your
Token ID534
Feature activation-2.74e+00

Pos logit contributions
 salon+0.071
aring+0.064
spe+0.060
Instead+0.058
ho+0.058
Neg logit contributions
CA-0.044
 emergencies-0.044
 steam-0.042
 sailors-0.040
 lava-0.040
Token homework
Token ID26131
Feature activation-1.52e+00

Pos logit contributions
 salon+0.173
aring+0.154
spe+0.138
Instead+0.136
ho+0.133
Neg logit contributions
CA-0.147
 emergencies-0.140
 steam-0.136
 sailors-0.132
 lava-0.132
Token and
Token ID290
Feature activation-8.87e-01

Pos logit contributions
 salon+0.118
aring+0.112
Instead+0.104
spe+0.104
ho+0.104
Neg logit contributions
 emergencies-0.048
CA-0.046
 batteries-0.044
kins-0.044
 sailors-0.043
Token clean
Token ID3424
Feature activation+2.82e-01

Pos logit contributions
 salon+0.065
aring+0.061
Instead+0.056
spe+0.056
ho+0.055
Neg logit contributions
 emergencies-0.036
 steam-0.034
CA-0.032
 batteries-0.032
 sailors-0.032
Token.
Token ID13
Feature activation-2.13e-01

Pos logit contributions
CA+0.013
 emergencies+0.012
 steam+0.012
 sailors+0.012
 lava+0.012
Neg logit contributions
 salon-0.020
aring-0.018
spe-0.016
Instead-0.016
ho-0.016
Token You
Token ID921
Feature activation-1.31e+00

Pos logit contributions
 salon+0.012
aring+0.011
Instead+0.010
spe+0.009
 Even+0.009
Neg logit contributions
CA-0.012
 steam-0.012
 emergencies-0.012
 lava-0.011
kins-0.011
Token.
Token ID13
Feature activation-5.86e-02

Pos logit contributions
 salon+0.051
aring+0.046
spe+0.041
Instead+0.040
ho+0.039
Neg logit contributions
CA-0.043
 emergencies-0.040
 steam-0.039
 lava-0.038
 sailors-0.038
Token If
Token ID1002
Feature activation-4.88e-01

Pos logit contributions
 salon+0.003
aring+0.003
 Even+0.002
 Sadly+0.002
Instead+0.002
Neg logit contributions
CA-0.004
 steam-0.004
kins-0.004
 lava-0.004
agons-0.004
Token you
Token ID345
Feature activation-5.36e-01

Pos logit contributions
 salon+0.038
aring+0.034
Instead+0.031
spe+0.031
ho+0.031
Neg logit contributions
CA-0.020
 emergencies-0.017
 steam-0.017
 lava-0.016
agons-0.016
Token do
Token ID466
Feature activation-6.17e-01

Pos logit contributions
 salon+0.028
aring+0.024
spe+0.022
Instead+0.021
ho+0.020
Neg logit contributions
CA-0.033
 emergencies-0.032
 steam-0.032
 sailors-0.031
 batteries-0.031
Token not
Token ID407
Feature activation-2.93e-01

Pos logit contributions
 salon+0.040
aring+0.036
spe+0.034
ho+0.033
Instead+0.032
Neg logit contributions
 emergencies-0.031
CA-0.029
 steam-0.029
 sailors-0.028
 batteries-0.028
Token store
Token ID3650
Feature activation-2.72e+00

Pos logit contributions
 salon+0.019
spe+0.015
aring+0.015
ho+0.014
 pad+0.014
Neg logit contributions
 emergencies-0.015
CA-0.015
 steam-0.014
 sailors-0.014
 batteries-0.014
Token your
Token ID534
Feature activation-2.07e+00

Pos logit contributions
 salon+0.187
aring+0.168
spe+0.151
Instead+0.149
ho+0.145
Neg logit contributions
CA-0.133
 emergencies-0.123
 steam-0.120
 lava-0.116
 sailors-0.116
Token toys
Token ID14958
Feature activation-7.40e-01

Pos logit contributions
 salon+0.143
aring+0.125
spe+0.114
Instead+0.111
ho+0.108
Neg logit contributions
CA-0.101
 emergencies-0.093
 steam-0.092
 lava-0.091
 sailors-0.090
Token,
Token ID11
Feature activation-6.85e-01

Pos logit contributions
 salon+0.048
aring+0.044
spe+0.041
Instead+0.040
ho+0.039
Neg logit contributions
 emergencies-0.035
CA-0.034
 batteries-0.032
kins-0.032
 sailors-0.032
Token you
Token ID345
Feature activation-5.83e-01

Pos logit contributions
 salon+0.062
aring+0.059
spe+0.056
Instead+0.055
ared+0.054
Neg logit contributions
 emergencies-0.016
 sailors-0.015
 steam-0.015
CA-0.014
 batteries-0.013
Token will
Token ID481
Feature activation-8.17e-01

Pos logit contributions
 salon+0.036
aring+0.031
spe+0.030
Instead+0.029
 glimpse+0.029
Neg logit contributions
 emergencies-0.029
 batteries-0.028
CA-0.028
 steam-0.027
 sailors-0.027
Token car
Token ID1097
Feature activation-2.33e-01

Pos logit contributions
 emergencies+0.008
 steam+0.007
 batteries+0.007
CA+0.007
 sailors+0.007
Neg logit contributions
 salon-0.008
aring-0.008
Instead-0.007
spe-0.007
ared-0.006
Token again
Token ID757
Feature activation-2.73e-01

Pos logit contributions
 salon+0.016
aring+0.015
Instead+0.014
 tant+0.013
 Even+0.013
Neg logit contributions
 steam-0.009
 batteries-0.009
 emergencies-0.009
CA-0.009
 sailors-0.009
Token and
Token ID290
Feature activation-9.35e-02

Pos logit contributions
 salon+0.019
aring+0.017
spe+0.016
Instead+0.016
ho+0.015
Neg logit contributions
CA-0.013
 emergencies-0.012
 steam-0.012
 sailors-0.011
 lava-0.011
Token Lily
Token ID20037
Feature activation-6.58e-01

Pos logit contributions
aring+0.008
 salon+0.008
Instead+0.007
ared+0.007
 perspective+0.007
Neg logit contributions
 steam-0.003
 sailors-0.002
 emergencies-0.002
 batteries-0.002
CA-0.002
Token insisted
Token ID11189
Feature activation-1.06e+00

Pos logit contributions
 salon+0.043
aring+0.042
 perspective+0.036
ho+0.035
olding+0.035
Neg logit contributions
CA-0.029
 steam-0.029
 sailors-0.027
 batteries-0.027
 Pig-0.025
Token one
Token ID530
Feature activation-2.72e+00

Pos logit contributions
 salon+0.074
aring+0.067
spe+0.061
Instead+0.060
ho+0.059
Neg logit contributions
CA-0.049
 emergencies-0.047
 steam-0.045
 sailors-0.044
 lava-0.044
Token more
Token ID517
Feature activation-1.01e+00

Pos logit contributions
 salon+0.197
aring+0.183
 Sadly+0.178
Instead+0.173
spe+0.171
Neg logit contributions
 steam-0.105
 emergencies-0.101
CA-0.096
 batteries-0.094
 sailors-0.092
Token time
Token ID640
Feature activation-4.21e-01

Pos logit contributions
 salon+0.074
aring+0.067
ho+0.063
Instead+0.062
spe+0.061
Neg logit contributions
 emergencies-0.042
CA-0.041
 steam-0.040
 batteries-0.038
 sailors-0.038
Token.
Token ID13
Feature activation-5.11e-01

Pos logit contributions
 salon+0.029
aring+0.027
Instead+0.026
ho+0.024
spe+0.024
Neg logit contributions
 emergencies-0.018
 sailors-0.017
 steam-0.017
CA-0.017
 batteries-0.016
Token Her
Token ID2332
Feature activation-8.66e-01

Pos logit contributions
 salon+0.027
aring+0.024
spe+0.021
ho+0.021
Instead+0.020
Neg logit contributions
CA-0.032
 emergencies-0.030
 steam-0.029
 batteries-0.028
 lava-0.028
Token mom
Token ID1995
Feature activation-8.30e-01

Pos logit contributions
 salon+0.064
aring+0.057
spe+0.053
Instead+0.052
ho+0.051
Neg logit contributions
CA-0.038
 emergencies-0.036
 steam-0.034
 lava-0.033
 sailors-0.033
Token?
Token ID30
Feature activation+1.38e-01

Pos logit contributions
CA+0.008
 sailors+0.007
 emergencies+0.007
 aliens+0.007
 lava+0.007
Neg logit contributions
 salon-0.018
aring-0.016
Instead-0.015
spe-0.014
ho-0.014
Token You
Token ID921
Feature activation-9.23e-01

Pos logit contributions
CA+0.007
 emergencies+0.007
 steam+0.006
 batteries+0.006
 lava+0.006
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.007
Instead-0.007
ho-0.007
Token did
Token ID750
Feature activation-2.79e-01

Pos logit contributions
 salon+0.052
aring+0.046
spe+0.040
Instead+0.040
ho+0.039
Neg logit contributions
CA-0.055
 emergencies-0.053
 steam-0.052
 sailors-0.051
 lava-0.050
Token not
Token ID407
Feature activation-2.84e-01

Pos logit contributions
 salon+0.016
aring+0.014
spe+0.013
ho+0.013
Instead+0.012
Neg logit contributions
CA-0.016
 emergencies-0.016
 steam-0.016
 lava-0.015
 batteries-0.015
Token do
Token ID466
Feature activation-9.56e-01

Pos logit contributions
 salon+0.017
spe+0.014
ho+0.014
aring+0.014
 pad+0.013
Neg logit contributions
 emergencies-0.016
 steam-0.016
CA-0.016
 sailors-0.015
 lava-0.015
Token your
Token ID534
Feature activation-2.72e+00

Pos logit contributions
 salon+0.068
aring+0.062
spe+0.056
Instead+0.056
ho+0.055
Neg logit contributions
CA-0.043
 emergencies-0.041
 steam-0.039
 sailors-0.038
 lava-0.038
Token chores
Token ID46173
Feature activation-1.58e+00

Pos logit contributions
 salon+0.178
aring+0.160
spe+0.145
Instead+0.143
ho+0.141
Neg logit contributions
CA-0.138
 emergencies-0.133
 steam-0.128
 sailors-0.124
 batteries-0.123
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
 salon+0.127
aring+0.120
Instead+0.110
spe+0.110
ho+0.108
Neg logit contributions
CA-0.048
 emergencies-0.048
 steam-0.045
 batteries-0.044
kins-0.043
Token You
Token ID921
Feature activation-1.23e+00

Pos logit contributions
 salon+0.011
aring+0.010
Instead+0.009
spe+0.009
ho+0.008
Neg logit contributions
CA-0.011
 emergencies-0.010
 steam-0.010
 sailors-0.010
 lava-0.010
Token did
Token ID750
Feature activation-4.11e-01

Pos logit contributions
 salon+0.064
aring+0.055
spe+0.048
Instead+0.047
ho+0.046
Neg logit contributions
CA-0.080
 emergencies-0.077
 steam-0.075
 sailors-0.074
 lava-0.073
Token not
Token ID407
Feature activation-4.73e-01

Pos logit contributions
 salon+0.022
aring+0.020
spe+0.018
ho+0.017
Instead+0.017
Neg logit contributions
CA-0.025
 emergencies-0.025
 steam-0.024
 lava-0.023
 sailors-0.023
Token him
Token ID683
Feature activation+1.66e-02

Pos logit contributions
 salon+0.027
aring+0.024
Instead+0.022
spe+0.022
ho+0.021
Neg logit contributions
CA-0.016
 emergencies-0.015
 steam-0.014
kins-0.014
 sailors-0.014
Token.
Token ID13
Feature activation-8.05e-01

Pos logit contributions
 his+0.000
 him+0.000
.+0.000
 steam+0.000
CA+0.000
Neg logit contributions
 salon-0.002
spe-0.002
Instead-0.002
aring-0.002
 Sadly-0.001
Token He
Token ID679
Feature activation-4.36e-01

Pos logit contributions
 salon+0.042
aring+0.038
 Even+0.034
Instead+0.033
 Sadly+0.033
Neg logit contributions
CA-0.049
 emergencies-0.048
 steam-0.047
kins-0.047
 sailors-0.047
Token pulls
Token ID16194
Feature activation-9.03e-02

Pos logit contributions
 salon+0.027
aring+0.025
spe+0.023
Instead+0.022
ho+0.022
Neg logit contributions
CA-0.023
 steam-0.022
 emergencies-0.021
 batteries-0.021
 sailors-0.020
Token the
Token ID262
Feature activation-3.42e-01

Pos logit contributions
 salon+0.008
aring+0.007
spe+0.007
Instead+0.007
ho+0.006
Neg logit contributions
CA-0.003
 emergencies-0.003
 steam-0.003
 sailors-0.002
 lava-0.002
Token trigger
Token ID7616
Feature activation-2.65e+00

Pos logit contributions
 salon+0.023
aring+0.021
spe+0.019
Instead+0.019
ho+0.018
Neg logit contributions
CA-0.017
 emergencies-0.016
 steam-0.015
 sailors-0.015
 lava-0.015
Token.
Token ID13
Feature activation-6.24e-01

Pos logit contributions
 salon+0.255
spe+0.227
aring+0.218
Instead+0.216
 Sadly+0.214
Neg logit contributions
CA-0.056
 steam-0.046
 sailors-0.043
 lava-0.041
 emergencies-0.039
Token Bang
Token ID9801
Feature activation+1.36e-01

Pos logit contributions
 salon+0.034
aring+0.030
 Even+0.027
 Sadly+0.026
Instead+0.026
Neg logit contributions
CA-0.037
 emergencies-0.037
 sailors-0.036
 steam-0.035
agons-0.035
Token!
Token ID0
Feature activation-3.80e-01

Pos logit contributions
CA+0.007
 emergencies+0.007
 sailors+0.007
ator+0.007
 aliens+0.006
Neg logit contributions
 salon-0.008
aring-0.008
Instead-0.007
 Even-0.007
ared-0.006
Token
Token ID198
Feature activation-1.92e-01

Pos logit contributions
 salon+0.023
aring+0.020
 Even+0.018
Instead+0.018
 Sadly+0.018
Neg logit contributions
CA-0.021
 emergencies-0.020
agons-0.020
 sailors-0.019
kins-0.019
Token
Token ID198
Feature activation+9.18e-02

Pos logit contributions
 salon+0.009
aring+0.008
 Even+0.008
Instead+0.007
 Sadly+0.007
Neg logit contributions
CA-0.012
 emergencies-0.012
 sailors-0.012
 steam-0.012
kins-0.012
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 salon+0.145
aring+0.133
Instead+0.127
spe+0.127
 Sadly+0.123
Neg logit contributions
 emergencies-0.039
CA-0.037
 sailors-0.034
 steam-0.034
 batteries-0.033
Token You
Token ID921
Feature activation-1.14e+00

Pos logit contributions
 salon+0.015
aring+0.013
spe+0.012
Instead+0.012
ho+0.011
Neg logit contributions
CA-0.013
 emergencies-0.013
 steam-0.012
 sailors-0.012
 lava-0.012
Token do
Token ID466
Feature activation-5.59e-01

Pos logit contributions
 salon+0.063
aring+0.055
spe+0.050
Instead+0.048
ho+0.046
Neg logit contributions
CA-0.068
 steam-0.067
 emergencies-0.066
 sailors-0.064
 batteries-0.064
Token not
Token ID407
Feature activation-3.13e-01

Pos logit contributions
 salon+0.036
spe+0.031
aring+0.030
ho+0.029
Instead+0.027
Neg logit contributions
 emergencies-0.029
 steam-0.028
CA-0.027
 batteries-0.027
 sailors-0.027
Token do
Token ID466
Feature activation-8.42e-01

Pos logit contributions
 salon+0.019
spe+0.016
 Sadly+0.015
ress+0.015
aring+0.015
Neg logit contributions
 steam-0.017
 emergencies-0.016
CA-0.016
 sailors-0.015
 lava-0.015
Token your
Token ID534
Feature activation-2.64e+00

Pos logit contributions
 salon+0.058
aring+0.052
spe+0.047
Instead+0.046
ho+0.045
Neg logit contributions
CA-0.040
 emergencies-0.038
 steam-0.037
 sailors-0.036
 lava-0.036
Token work
Token ID670
Feature activation-7.03e-01

Pos logit contributions
 salon+0.169
aring+0.150
spe+0.133
Instead+0.133
ho+0.130
Neg logit contributions
CA-0.140
 emergencies-0.133
 steam-0.128
 sailors-0.126
 lava-0.126
Token.
Token ID13
Feature activation-3.95e-01

Pos logit contributions
 salon+0.059
aring+0.055
ho+0.052
Instead+0.052
spe+0.051
Neg logit contributions
 emergencies-0.019
CA-0.018
kins-0.018
 batteries-0.018
 steam-0.017
Token You
Token ID921
Feature activation-1.23e+00

Pos logit contributions
 salon+0.023
aring+0.021
Instead+0.018
spe+0.018
ho+0.018
Neg logit contributions
CA-0.022
 emergencies-0.021
 steam-0.021
 lava-0.020
 sailors-0.020
Token do
Token ID466
Feature activation-6.25e-01

Pos logit contributions
 salon+0.066
aring+0.058
spe+0.052
Instead+0.050
ho+0.049
Neg logit contributions
CA-0.075
 emergencies-0.074
 steam-0.074
 sailors-0.071
 batteries-0.071
Token not
Token ID407
Feature activation-3.86e-01

Pos logit contributions
 salon+0.040
spe+0.034
aring+0.034
ho+0.033
Instead+0.031
Neg logit contributions
 emergencies-0.033
 steam-0.032
CA-0.031
 batteries-0.030
 sailors-0.030
Token,
Token ID11
Feature activation-1.49e-01

Pos logit contributions
CA+0.019
 emergencies+0.017
 steam+0.017
 sailors+0.017
 lava+0.017
Neg logit contributions
 salon-0.016
aring-0.014
Instead-0.012
spe-0.012
ho-0.012
Token sweet
Token ID6029
Feature activation+5.41e-01

Pos logit contributions
 salon+0.011
aring+0.010
spe+0.010
ho+0.010
ared+0.009
Neg logit contributions
 steam-0.006
 emergencies-0.006
CA-0.006
 batteries-0.006
 sailors-0.006
Tokenie
Token ID494
Feature activation+1.32e+00

Pos logit contributions
CA+0.029
 emergencies+0.027
 steam+0.025
 sailors+0.025
 lava+0.025
Neg logit contributions
 salon-0.035
aring-0.031
Instead-0.028
spe-0.027
ho-0.027
Token.
Token ID13
Feature activation+7.62e-01

Pos logit contributions
CA+0.044
 emergencies+0.041
 steam+0.039
 sailors+0.037
 lava+0.037
Neg logit contributions
 salon-0.109
aring-0.100
spe-0.093
Instead-0.092
ho-0.090
Token Po
Token ID7695
Feature activation-3.50e-01

Pos logit contributions
CA+0.046
 emergencies+0.045
 steam+0.043
agons+0.043
 sailors+0.043
Neg logit contributions
 salon-0.041
aring-0.037
Instead-0.031
ho-0.031
spe-0.031
Tokenpp
Token ID381
Feature activation-2.64e+00

Pos logit contributions
 salon+0.019
aring+0.018
ho+0.015
 pad+0.014
Instead+0.013
Neg logit contributions
CA-0.022
 emergencies-0.021
 lava-0.020
 sailors-0.020
 steam-0.020
Tokenies
Token ID444
Feature activation+7.48e-02

Pos logit contributions
 salon+0.191
aring+0.166
spe+0.156
Instead+0.153
ho+0.149
Neg logit contributions
CA-0.116
 steam-0.110
 emergencies-0.110
 sailors-0.109
kins-0.108
Token are
Token ID389
Feature activation-3.86e-01

Pos logit contributions
 steam+0.004
 emergencies+0.004
CA+0.004
kins+0.004
 batteries+0.004
Neg logit contributions
 salon-0.004
spe-0.004
aring-0.004
Instead-0.003
ho-0.003
Token very
Token ID845
Feature activation+6.96e-01

Pos logit contributions
 salon+0.020
aring+0.018
Instead+0.015
ho+0.014
spe+0.014
Neg logit contributions
CA-0.025
rob-0.023
 emergencies-0.023
agons-0.022
 sailors-0.022
Token delicate
Token ID19217
Feature activation-5.62e-01

Pos logit contributions
CA+0.037
 emergencies+0.036
 steam+0.034
 sailors+0.034
 lava+0.033
Neg logit contributions
 salon-0.044
aring-0.039
spe-0.035
Instead-0.035
ho-0.034
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
 salon+0.041
aring+0.038
spe+0.034
Instead+0.034
ho+0.033
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.021
 sailors-0.021
 lava-0.021
Token tiger
Token ID26241
Feature activation-3.31e-01

Pos logit contributions
 salon+0.022
aring+0.021
Instead+0.019
spe+0.018
ared+0.018
Neg logit contributions
 steam-0.010
CA-0.010
 emergencies-0.009
 lava-0.009
 sailors-0.009
Token's
Token ID338
Feature activation-8.64e-01

Pos logit contributions
 salon+0.024
aring+0.022
Instead+0.020
 perspective+0.019
 While+0.019
Neg logit contributions
 steam-0.013
CA-0.013
 sparks-0.011
 happened-0.011
 lava-0.011
Token journey
Token ID7002
Feature activation-2.47e-01

Pos logit contributions
 salon+0.063
aring+0.059
Instead+0.053
spe+0.052
ho+0.051
Neg logit contributions
 steam-0.037
 emergencies-0.035
CA-0.035
 sailors-0.034
 batteries-0.034
Token didn
Token ID1422
Feature activation-4.02e-01

Pos logit contributions
 salon+0.016
aring+0.015
Instead+0.013
spe+0.012
ho+0.012
Neg logit contributions
CA-0.013
 emergencies-0.012
 steam-0.012
 batteries-0.011
kins-0.011
Token't
Token ID470
Feature activation-3.62e-01

Pos logit contributions
 salon+0.023
aring+0.021
Instead+0.019
spe+0.018
 Even+0.018
Neg logit contributions
CA-0.023
 emergencies-0.022
 sailors-0.022
 steam-0.022
kins-0.022
Token end
Token ID886
Feature activation-2.63e+00

Pos logit contributions
 salon+0.019
aring+0.017
spe+0.015
Instead+0.014
ho+0.014
Neg logit contributions
CA-0.023
 emergencies-0.022
 steam-0.021
 sailors-0.021
 lava-0.021
Token there
Token ID612
Feature activation-1.12e+00

Pos logit contributions
 salon+0.196
aring+0.179
spe+0.164
Instead+0.162
ho+0.159
Neg logit contributions
CA-0.109
 emergencies-0.102
 steam-0.097
 sailors-0.095
 lava-0.094
Token -
Token ID532
Feature activation+5.09e-01

Pos logit contributions
 salon+0.088
aring+0.083
Instead+0.075
spe+0.073
 Sadly+0.071
Neg logit contributions
 emergencies-0.036
CA-0.035
 steam-0.033
kins-0.032
 batteries-0.031
Token as
Token ID355
Feature activation+8.24e-03

Pos logit contributions
 emergencies+0.018
 steam+0.018
CA+0.016
 batteries+0.016
 lava+0.016
Neg logit contributions
 salon-0.039
aring-0.039
ared-0.035
ashing-0.034
ench-0.034
Token soon
Token ID2582
Feature activation+1.39e-01

Pos logit contributions
CA+0.000
 emergencies+0.000
agons+0.000
 steam+0.000
 lava+0.000
Neg logit contributions
 salon-0.001
aring-0.000
spe-0.000
Instead-0.000
ho-0.000
Token as
Token ID355
Feature activation-1.47e-01

Pos logit contributions
CA+0.008
 emergencies+0.008
agons+0.007
kins+0.007
 sailors+0.007
Neg logit contributions
 salon-0.008
aring-0.007
Instead-0.006
spe-0.006
 Even-0.006
Token was
Token ID373
Feature activation-1.14e-01

Pos logit contributions
 salon+0.008
aring+0.007
spe+0.006
Instead+0.006
ho+0.006
Neg logit contributions
CA-0.008
 emergencies-0.008
 steam-0.008
 sailors-0.008
 lava-0.008
Token glad
Token ID9675
Feature activation+3.02e-01

Pos logit contributions
 salon+0.007
aring+0.006
Instead+0.005
ho+0.005
spe+0.005
Neg logit contributions
 sailors-0.006
 steam-0.006
CA-0.006
 emergencies-0.006
 lava-0.006
Token it
Token ID340
Feature activation-1.65e-01

Pos logit contributions
CA+0.015
 emergencies+0.014
 steam+0.014
 sailors+0.014
 lava+0.013
Neg logit contributions
 salon-0.020
aring-0.018
spe-0.016
Instead-0.016
ho-0.016
Token didn
Token ID1422
Feature activation-3.09e-01

Pos logit contributions
 salon+0.007
aring+0.006
spe+0.006
Instead+0.006
ho+0.006
Neg logit contributions
 emergencies-0.011
CA-0.011
agons-0.011
 sailors-0.010
 pans-0.010
Token't
Token ID470
Feature activation-2.83e-01

Pos logit contributions
 salon+0.018
aring+0.016
Instead+0.015
spe+0.015
 Even+0.014
Neg logit contributions
CA-0.017
 emergencies-0.017
 sailors-0.016
kins-0.016
 pans-0.016
Token end
Token ID886
Feature activation-2.60e+00

Pos logit contributions
 salon+0.017
aring+0.015
Instead+0.013
ho+0.013
spe+0.013
Neg logit contributions
CA-0.015
 emergencies-0.015
 steam-0.015
 lava-0.015
 sailors-0.015
Token too
Token ID1165
Feature activation-4.67e-01

Pos logit contributions
aring+0.142
 salon+0.141
spe+0.126
Instead+0.125
ho+0.118
Neg logit contributions
CA-0.149
agons-0.129
 sailors-0.129
 emergencies-0.129
rob-0.127
Token soon
Token ID2582
Feature activation+7.63e-02

Pos logit contributions
 salon+0.024
aring+0.021
spe+0.018
Instead+0.018
ho+0.017
Neg logit contributions
CA-0.031
 emergencies-0.030
 steam-0.029
 sailors-0.028
 lava-0.028
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
CA+0.003
 emergencies+0.003
 steam+0.003
 sailors+0.003
 lava+0.003
Neg logit contributions
 salon-0.006
aring-0.005
spe-0.005
Instead-0.005
ho-0.005
Token He
Token ID679
Feature activation-2.90e-01

Pos logit contributions
 salon+0.011
aring+0.010
spe+0.009
ho+0.009
Instead+0.008
Neg logit contributions
CA-0.009
 emergencies-0.008
 steam-0.008
 sailors-0.008
 lava-0.008
Token went
Token ID1816
Feature activation-8.67e-01

Pos logit contributions
 salon+0.017
aring+0.015
spe+0.013
Instead+0.013
ho+0.013
Neg logit contributions
CA-0.017
 steam-0.016
 emergencies-0.016
 sailors-0.015
 lava-0.015
Token Sam
Token ID3409
Feature activation-4.70e-01

Pos logit contributions
 salon+0.078
aring+0.072
spe+0.067
Instead+0.066
ho+0.065
Neg logit contributions
CA-0.027
 emergencies-0.025
 steam-0.024
 sailors-0.022
 lava-0.022
Token.
Token ID13
Feature activation-9.08e-01

Pos logit contributions
 salon+0.051
Of+0.046
Instead+0.045
spe+0.045
 While+0.044
Neg logit contributions
 him-0.001
 batteries-0.001
.-0.001
 emergencies-0.001
 his-0.000
Token He
Token ID679
Feature activation-6.66e-01

Pos logit contributions
 salon+0.046
aring+0.042
 Even+0.038
Instead+0.036
 Sadly+0.035
Neg logit contributions
CA-0.056
 emergencies-0.055
agons-0.054
kins-0.053
 pans-0.053
Token pulls
Token ID16194
Feature activation-3.35e-01

Pos logit contributions
 salon+0.044
aring+0.040
spe+0.037
Instead+0.036
ho+0.036
Neg logit contributions
CA-0.033
 steam-0.032
 batteries-0.031
 emergencies-0.031
 sailors-0.029
Token the
Token ID262
Feature activation-2.92e-01

Pos logit contributions
 salon+0.029
aring+0.026
spe+0.024
Instead+0.024
ho+0.024
Neg logit contributions
CA-0.011
 emergencies-0.010
 steam-0.009
 sailors-0.009
 lava-0.009
Token trigger
Token ID7616
Feature activation-2.60e+00

Pos logit contributions
 salon+0.020
aring+0.019
Instead+0.017
spe+0.017
ho+0.017
Neg logit contributions
CA-0.014
 emergencies-0.013
 steam-0.013
 batteries-0.013
 sailors-0.013
Token.
Token ID13
Feature activation-7.90e-01

Pos logit contributions
 salon+0.258
spe+0.227
aring+0.222
Instead+0.220
 Sadly+0.217
Neg logit contributions
CA-0.046
 steam-0.036
 sailors-0.035
 lava-0.031
 emergencies-0.031
Token
Token ID198
Feature activation-7.83e-01

Pos logit contributions
 salon+0.041
aring+0.037
 Even+0.034
 Sadly+0.032
Instead+0.032
Neg logit contributions
CA-0.047
 emergencies-0.047
agons-0.046
 sailors-0.045
kins-0.045
Token
Token ID198
Feature activation-4.26e-01

Pos logit contributions
 salon+0.033
aring+0.032
 Even+0.029
Instead+0.028
 Sadly+0.027
Neg logit contributions
CA-0.052
 steam-0.052
 emergencies-0.052
 lava-0.052
 sailors-0.051
TokenThe
Token ID464
Feature activation-3.31e-01

Pos logit contributions
 salon+0.025
aring+0.022
spe+0.020
Instead+0.019
ho+0.019
Neg logit contributions
CA-0.025
 emergencies-0.024
 steam-0.023
 sailors-0.023
 lava-0.023
Token gun
Token ID2485
Feature activation-5.17e-01

Pos logit contributions
 salon+0.024
aring+0.022
Instead+0.020
spe+0.020
ho+0.019
Neg logit contributions
CA-0.015
 emergencies-0.014
 steam-0.014
 sailors-0.013
 lava-0.013
Token Mia
Token ID32189
Feature activation-1.89e-01

Pos logit contributions
 salon+0.043
aring+0.037
ho+0.035
spe+0.035
Instead+0.035
Neg logit contributions
CA-0.023
 emergencies-0.021
 steam-0.020
agons-0.019
 sailors-0.019
Token.
Token ID13
Feature activation-5.01e-01

Pos logit contributions
 salon+0.014
Instead+0.013
spe+0.013
Of+0.013
aring+0.013
Neg logit contributions
 him-0.006
 steam-0.005
pa-0.005
 emergencies-0.005
 batteries-0.005
Token He
Token ID679
Feature activation-3.68e-01

Pos logit contributions
 salon+0.032
aring+0.028
spe+0.026
Instead+0.025
ho+0.025
Neg logit contributions
CA-0.026
 emergencies-0.025
 steam-0.024
 sailors-0.024
 lava-0.024
Token pulls
Token ID16194
Feature activation-1.19e-01

Pos logit contributions
 salon+0.024
aring+0.022
spe+0.020
Instead+0.020
ho+0.019
Neg logit contributions
CA-0.019
 steam-0.018
 batteries-0.018
 sailors-0.017
 emergencies-0.017
Token the
Token ID262
Feature activation-3.99e-01

Pos logit contributions
 salon+0.011
aring+0.010
spe+0.009
Instead+0.009
ho+0.009
Neg logit contributions
CA-0.003
 steam-0.003
 emergencies-0.003
 lava-0.003
 batteries-0.003
Token trigger
Token ID7616
Feature activation-2.59e+00

Pos logit contributions
 salon+0.030
aring+0.028
Instead+0.025
 Sadly+0.025
spe+0.025
Neg logit contributions
 steam-0.017
 sailors-0.016
 batteries-0.016
CA-0.016
 lava-0.016
Token.
Token ID13
Feature activation-5.17e-01

Pos logit contributions
 salon+0.237
spe+0.208
aring+0.203
Instead+0.202
 Sadly+0.199
Neg logit contributions
CA-0.064
 steam-0.055
 sailors-0.053
 aliens-0.050
ull-0.050
Token But
Token ID887
Feature activation-5.30e-01

Pos logit contributions
 salon+0.032
aring+0.028
spe+0.025
Instead+0.025
ho+0.024
Neg logit contributions
CA-0.028
 emergencies-0.027
 steam-0.026
 sailors-0.026
 lava-0.025
Token nothing
Token ID2147
Feature activation+9.48e-01

Pos logit contributions
 salon+0.047
aring+0.047
Instead+0.043
spe+0.042
ench+0.041
Neg logit contributions
 steam-0.012
CA-0.012
 lava-0.012
 emergencies-0.012
kins-0.011
Token happens
Token ID4325
Feature activation+2.08e-01

Pos logit contributions
CA+0.036
 emergencies+0.036
 sailors+0.034
 pans+0.033
agons+0.033
Neg logit contributions
 salon-0.071
aring-0.066
Instead-0.058
spe-0.058
ho-0.057
Token.
Token ID13
Feature activation-3.16e-01

Pos logit contributions
CA+0.005
 emergencies+0.005
 steam+0.005
 sailors+0.005
kins+0.005
Neg logit contributions
 salon-0.018
aring-0.017
Instead-0.016
spe-0.016
ho-0.015
Token fort
Token ID6285
Feature activation-4.63e-01

Pos logit contributions
 salon+0.104
aring+0.099
Instead+0.090
spe+0.086
ho+0.084
Neg logit contributions
 steam-0.072
CA-0.072
 emergencies-0.071
 sailors-0.069
 batteries-0.068
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
 salon+0.031
aring+0.030
Instead+0.027
ho+0.026
ared+0.026
Neg logit contributions
kins-0.021
 steam-0.020
 batteries-0.019
 lava-0.019
 sailors-0.019
Token you
Token ID345
Feature activation-5.04e-01

Pos logit contributions
 salon+0.010
aring+0.010
Instead+0.009
ared+0.009
spe+0.008
Neg logit contributions
 steam-0.007
 sailors-0.007
 emergencies-0.007
 batteries-0.007
 lava-0.006
Token can
Token ID460
Feature activation-5.63e-01

Pos logit contributions
 salon+0.030
aring+0.027
spe+0.024
Instead+0.024
ho+0.023
Neg logit contributions
CA-0.027
 steam-0.026
 sailors-0.026
 batteries-0.025
 emergencies-0.025
Token do
Token ID466
Feature activation-6.91e-01

Pos logit contributions
 salon+0.033
aring+0.031
spe+0.028
Instead+0.027
ho+0.026
Neg logit contributions
CA-0.029
 steam-0.029
 emergencies-0.029
 sailors-0.028
 lava-0.028
Token your
Token ID534
Feature activation-2.59e+00

Pos logit contributions
 salon+0.056
aring+0.051
spe+0.047
Instead+0.046
ho+0.046
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.022
 sailors-0.021
 lava-0.021
Token painting
Token ID12036
Feature activation-7.34e-01

Pos logit contributions
 salon+0.157
aring+0.138
spe+0.124
Instead+0.122
ho+0.118
Neg logit contributions
CA-0.145
 emergencies-0.138
 steam-0.134
 sailors-0.131
 lava-0.131
Token too
Token ID1165
Feature activation-1.81e-01

Pos logit contributions
 salon+0.047
aring+0.041
spe+0.037
Instead+0.036
ho+0.035
Neg logit contributions
CA-0.039
 emergencies-0.038
 steam-0.036
 sailors-0.035
 lava-0.035
Token!"
Token ID2474
Feature activation-4.43e-01

Pos logit contributions
 salon+0.016
aring+0.014
spe+0.013
ho+0.013
Instead+0.013
Neg logit contributions
CA-0.005
 emergencies-0.005
 steam-0.005
 lava-0.004
kins-0.004
Token
Token ID198
Feature activation-3.30e-01

Pos logit contributions
 salon+0.028
aring+0.025
spe+0.023
Instead+0.022
ho+0.022
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.022
 sailors-0.021
 batteries-0.021
Token
Token ID198
Feature activation+5.50e-02

Pos logit contributions
 salon+0.015
aring+0.013
Instead+0.012
 Even+0.012
 Sadly+0.011
Neg logit contributions
 lava-0.023
CA-0.022
 emergencies-0.022
 steam-0.021
 pans-0.021
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
 salon+0.049
aring+0.046
Instead+0.045
spe+0.043
 Sadly+0.043
Neg logit contributions
 steam-0.016
 emergencies-0.016
pa-0.016
 batteries-0.016
kins-0.015
Token She
Token ID1375
Feature activation-3.67e-01

Pos logit contributions
 salon+0.014
aring+0.012
spe+0.011
Instead+0.011
ho+0.010
Neg logit contributions
CA-0.013
 emergencies-0.013
 steam-0.013
 sailors-0.012
 lava-0.012
Token did
Token ID750
Feature activation-4.49e-01

Pos logit contributions
 salon+0.024
aring+0.023
spe+0.020
Instead+0.020
 perspective+0.019
Neg logit contributions
CA-0.018
 steam-0.017
 emergencies-0.016
 sailors-0.016
 batteries-0.016
Token not
Token ID407
Feature activation-3.54e-01

Pos logit contributions
 salon+0.024
aring+0.021
spe+0.018
Instead+0.018
ho+0.018
Neg logit contributions
CA-0.028
 emergencies-0.028
 steam-0.027
 sailors-0.026
 lava-0.026
Token have
Token ID423
Feature activation-1.07e+00

Pos logit contributions
 salon+0.019
aring+0.015
spe+0.015
ho+0.015
Instead+0.015
Neg logit contributions
 sailors-0.022
 steam-0.022
CA-0.022
 emergencies-0.022
 lava-0.021
Token one
Token ID530
Feature activation-2.55e+00

Pos logit contributions
 salon+0.070
aring+0.066
spe+0.059
ho+0.058
Instead+0.057
Neg logit contributions
CA-0.053
 emergencies-0.052
 steam-0.051
 batteries-0.050
 sailors-0.049
Token.
Token ID13
Feature activation-2.56e-01

Pos logit contributions
 salon+0.190
aring+0.179
spe+0.173
Instead+0.172
 Sadly+0.165
Neg logit contributions
 steam-0.090
 emergencies-0.090
CA-0.089
 batteries-0.086
 lava-0.083
Token He
Token ID679
Feature activation-1.52e-01

Pos logit contributions
 salon+0.012
aring+0.011
Instead+0.009
spe+0.009
ho+0.009
Neg logit contributions
CA-0.017
 emergencies-0.017
 steam-0.017
 sailors-0.016
 lava-0.016
Token looked
Token ID3114
Feature activation+3.29e-01

Pos logit contributions
 salon+0.009
aring+0.009
spe+0.008
Instead+0.007
ho+0.007
Neg logit contributions
CA-0.008
 steam-0.008
 emergencies-0.007
 batteries-0.007
 sailors-0.007
Token at
Token ID379
Feature activation-6.71e-01

Pos logit contributions
 steam+0.017
CA+0.016
 emergencies+0.016
 sailors+0.015
 lava+0.015
Neg logit contributions
 salon-0.022
aring-0.019
spe-0.018
Instead-0.018
ress-0.018
Token the
Token ID262
Feature activation+1.97e-01

Pos logit contributions
 salon+0.055
aring+0.051
spe+0.047
Instead+0.046
ho+0.046
Neg logit contributions
CA-0.023
 emergencies-0.022
 steam-0.020
 sailors-0.020
 lava-0.019
Token The
Token ID383
Feature activation-5.63e-01

Pos logit contributions
 salon+0.055
aring+0.046
ho+0.042
spe+0.042
 glimpse+0.040
Neg logit contributions
CA-0.039
 emergencies-0.038
 steam-0.037
 sailors-0.035
 lava-0.035
Token two
Token ID734
Feature activation-9.48e-01

Pos logit contributions
 salon+0.031
aring+0.027
spe+0.024
Instead+0.024
ho+0.023
Neg logit contributions
CA-0.034
 emergencies-0.033
 steam-0.032
 lava-0.031
 sailors-0.031
Token friends
Token ID2460
Feature activation+7.67e-01

Pos logit contributions
 salon+0.066
aring+0.060
ho+0.055
Instead+0.053
spe+0.053
Neg logit contributions
CA-0.043
 emergencies-0.043
 sailors-0.041
 steam-0.041
 batteries-0.041
Token didn
Token ID1422
Feature activation-3.94e-01

Pos logit contributions
 sailors+0.033
 steam+0.033
CA+0.032
 aliens+0.031
 emergencies+0.030
Neg logit contributions
 salon-0.055
aring-0.048
Instead-0.043
itating-0.042
 glimpse-0.042
Token't
Token ID470
Feature activation-3.14e-01

Pos logit contributions
 salon+0.020
aring+0.018
 Even+0.016
Instead+0.016
 Sadly+0.015
Neg logit contributions
CA-0.026
 sailors-0.025
kins-0.025
 pans-0.024
 emergencies-0.024
Token end
Token ID886
Feature activation-2.54e+00

Pos logit contributions
 salon+0.022
ho+0.018
aman+0.018
spe+0.017
ress+0.016
Neg logit contributions
 sailors-0.016
 emergencies-0.015
 him-0.014
 aliens-0.014
 guys-0.014
Token up
Token ID510
Feature activation-1.75e+00

Pos logit contributions
 salon+0.150
aring+0.140
spe+0.124
Instead+0.121
ho+0.117
Neg logit contributions
CA-0.143
 emergencies-0.131
 steam-0.128
 sailors-0.127
 lava-0.126
Token playing
Token ID2712
Feature activation-3.61e-02

Pos logit contributions
 salon+0.109
aring+0.097
Instead+0.086
spe+0.085
ho+0.084
Neg logit contributions
CA-0.094
 emergencies-0.092
 steam-0.088
 sailors-0.087
 batteries-0.086
Token together
Token ID1978
Feature activation-2.62e-01

Pos logit contributions
 salon+0.002
aring+0.002
Instead+0.002
ho+0.002
spe+0.002
Neg logit contributions
 emergencies-0.002
CA-0.002
 steam-0.002
 batteries-0.002
 sailors-0.002
Token anymore
Token ID7471
Feature activation+5.33e-02

Pos logit contributions
 salon+0.020
aring+0.019
Instead+0.018
Of+0.016
 While+0.016
Neg logit contributions
 emergencies-0.009
kins-0.009
 him-0.009
 sailors-0.008
 batteries-0.008
Token and
Token ID290
Feature activation-3.43e-01

Pos logit contributions
CA+0.002
 emergencies+0.002
 steam+0.002
 sailors+0.002
 lava+0.002
Neg logit contributions
 salon-0.004
aring-0.004
spe-0.004
Instead-0.004
ho-0.004
Token.
Token ID13
Feature activation+5.58e-02

Pos logit contributions
 salon+0.038
aring+0.035
spe+0.033
Instead+0.031
ho+0.029
Neg logit contributions
CA-0.024
 emergencies-0.022
 steam-0.021
 lava-0.021
 sailors-0.021
Token The
Token ID383
Feature activation-2.98e-01

Pos logit contributions
rob+0.004
CA+0.004
 emergencies+0.004
 sailors+0.004
agons+0.004
Neg logit contributions
 salon-0.002
aring-0.002
 Even-0.002
 Sadly-0.002
Instead-0.002
Token day
Token ID1110
Feature activation+2.23e-02

Pos logit contributions
 salon+0.022
aring+0.020
spe+0.018
Instead+0.018
ho+0.017
Neg logit contributions
CA-0.013
 emergencies-0.012
 steam-0.012
 sailors-0.011
 lava-0.011
Token did
Token ID750
Feature activation-2.25e-01

Pos logit contributions
CA+0.001
rob+0.001
agons+0.001
 emergencies+0.001
 pans+0.001
Neg logit contributions
 salon-0.001
aring-0.001
spe-0.001
Instead-0.001
ho-0.001
Token not
Token ID407
Feature activation-1.67e-01

Pos logit contributions
 salon+0.011
aring+0.009
Instead+0.008
spe+0.008
ho+0.007
Neg logit contributions
CA-0.016
 emergencies-0.015
 steam-0.015
 sailors-0.015
 lava-0.015
Token end
Token ID886
Feature activation-2.53e+00

Pos logit contributions
 salon+0.009
aring+0.008
spe+0.007
Instead+0.007
ho+0.007
Neg logit contributions
CA-0.010
 emergencies-0.010
 steam-0.010
 sailors-0.010
 lava-0.010
Token well
Token ID880
Feature activation-6.59e-01

Pos logit contributions
 salon+0.135
aring+0.134
spe+0.119
Instead+0.113
 where+0.106
Neg logit contributions
CA-0.139
rob-0.139
agons-0.128
ates-0.125
ags-0.121
Token for
Token ID329
Feature activation-8.59e-01

Pos logit contributions
 salon+0.047
aring+0.043
spe+0.038
ho+0.038
Instead+0.036
Neg logit contributions
CA-0.032
 emergencies-0.028
 steam-0.027
agons-0.026
 pans-0.026
Token Tim
Token ID5045
Feature activation-5.74e-01

Pos logit contributions
 salon+0.043
Instead+0.036
 Even+0.035
 nine+0.035
aring+0.035
Neg logit contributions
CA-0.054
rob-0.052
agons-0.046
kins-0.045
 pans-0.044
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
 salon+0.043
aring+0.039
spe+0.038
Instead+0.038
ho+0.036
Neg logit contributions
 emergencies-0.020
CA-0.020
 steam-0.019
 batteries-0.019
 sailors-0.018
Token Sam
Token ID3409
Feature activation-7.33e-01

Pos logit contributions
 salon+0.098
aring+0.090
spe+0.084
Instead+0.083
ho+0.083
Neg logit contributions
CA-0.036
 emergencies-0.032
 steam-0.030
 sailors-0.029
kins-0.029
Token named
Token ID3706
Feature activation+2.97e-03

Pos logit contributions
 salon+0.020
aring+0.018
spe+0.016
Instead+0.016
ho+0.015
Neg logit contributions
CA-0.018
 emergencies-0.017
 steam-0.017
 sailors-0.016
 lava-0.016
Token Lily
Token ID20037
Feature activation+7.01e-01

Pos logit contributions
CA+0.000
 emergencies+0.000
 steam+0.000
 lava+0.000
 pans+0.000
Neg logit contributions
 salon-0.000
aring-0.000
spe-0.000
Instead-0.000
ho-0.000
Token who
Token ID508
Feature activation+3.12e-01

Pos logit contributions
CA+0.025
 emergencies+0.023
 steam+0.022
 sailors+0.021
 lava+0.021
Neg logit contributions
 salon-0.057
aring-0.052
spe-0.048
Instead-0.048
ho-0.047
Token loved
Token ID6151
Feature activation-1.16e-01

Pos logit contributions
CA+0.022
 emergencies+0.021
 sailors+0.020
 steam+0.020
 lava+0.020
Neg logit contributions
 salon-0.015
aring-0.013
Instead-0.011
spe-0.011
ho-0.011
Token po
Token ID745
Feature activation-7.94e-01

Pos logit contributions
 salon+0.005
aring+0.003
ho+0.003
spe+0.003
Instead+0.003
Neg logit contributions
kins-0.009
CA-0.009
ator-0.008
agons-0.008
rob-0.008
Tokenpp
Token ID381
Feature activation-2.52e+00

Pos logit contributions
 salon+0.038
aring+0.033
spe+0.028
Instead+0.027
ho+0.027
Neg logit contributions
CA-0.055
 emergencies-0.053
 steam-0.052
 sailors-0.051
 lava-0.051
Tokenies
Token ID444
Feature activation-2.89e-01

Pos logit contributions
 salon+0.167
aring+0.150
spe+0.135
Instead+0.134
ho+0.131
Neg logit contributions
CA-0.125
 emergencies-0.120
 steam-0.116
 sailors-0.113
 lava-0.112
Token.
Token ID13
Feature activation-7.11e-01

Pos logit contributions
 salon+0.023
aring+0.021
spe+0.020
Instead+0.019
ho+0.019
Neg logit contributions
CA-0.011
 emergencies-0.010
 steam-0.009
 lava-0.009
 sailors-0.009
Token She
Token ID1375
Feature activation-4.90e-01

Pos logit contributions
 salon+0.034
aring+0.032
spe+0.029
ho+0.028
ared+0.025
Neg logit contributions
CA-0.046
 emergencies-0.043
 steam-0.042
 batteries-0.042
 aliens-0.041
Token had
Token ID550
Feature activation-1.82e-01

Pos logit contributions
 salon+0.025
aring+0.023
spe+0.020
Instead+0.019
ho+0.018
Neg logit contributions
CA-0.032
 emergencies-0.030
 steam-0.030
 sailors-0.029
 batteries-0.028
Token a
Token ID257
Feature activation-3.86e-01

Pos logit contributions
 salon+0.015
aring+0.014
spe+0.013
ho+0.012
Instead+0.012
Neg logit contributions
CA-0.006
 steam-0.006
 emergencies-0.006
 sailors-0.005
 batteries-0.005
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
kins+0.053
 steam+0.053
 sailors+0.050
 lava+0.050
 pans+0.050
Neg logit contributions
 salon-0.099
aring-0.091
Instead-0.085
 Sadly-0.083
spe-0.083
Token her
Token ID607
Feature activation+5.45e-01

Pos logit contributions
 steam+0.047
 pans+0.045
 lava+0.044
 emergencies+0.044
 sailors+0.043
Neg logit contributions
 salon-0.080
aring-0.080
itating-0.067
Instead-0.067
ared-0.067
Token favourite
Token ID12507
Feature activation+1.13e+00

Pos logit contributions
CA+0.031
 emergencies+0.029
 steam+0.027
rob+0.027
 sailors+0.027
Neg logit contributions
 salon-0.033
aring-0.028
spe-0.026
ho-0.026
Instead-0.025
Token,
Token ID11
Feature activation+5.61e-01

Pos logit contributions
 steam+0.048
CA+0.048
 emergencies+0.046
 batteries+0.046
 lava+0.045
Neg logit contributions
 salon-0.080
aring-0.076
spe-0.067
Instead-0.067
ho-0.065
Token ch
Token ID442
Feature activation+9.95e-01

Pos logit contributions
 steam+0.026
CA+0.024
 emergencies+0.024
 lava+0.023
 sailors+0.023
Neg logit contributions
 salon-0.039
aring-0.038
Instead-0.033
ared-0.032
spe-0.032
Tokenocol
Token ID4668
Feature activation+3.05e+00

Pos logit contributions
CA+0.020
 emergencies+0.018
 steam+0.016
 sailors+0.015
 lava+0.015
Neg logit contributions
 salon-0.096
aring-0.089
spe-0.084
Instead-0.084
ho-0.082
Tokenates
Token ID689
Feature activation+1.80e+00

Pos logit contributions
CA+0.120
 steam+0.115
 emergencies+0.113
 aliens+0.100
 batteries+0.095
Neg logit contributions
 salon-0.221
ared-0.217
ho-0.214
aring-0.213
 pad-0.213
Token!
Token ID0
Feature activation+1.54e-01

Pos logit contributions
 steam+0.054
kins+0.054
 sailors+0.051
 lava+0.051
CA+0.049
Neg logit contributions
 salon-0.148
aring-0.137
Instead-0.128
 Sadly-0.125
spe-0.124
Token She
Token ID1375
Feature activation-2.98e-01

Pos logit contributions
CA+0.009
 steam+0.008
 emergencies+0.008
 sailors+0.008
 lava+0.008
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.007
ho-0.007
Instead-0.007
Token asked
Token ID1965
Feature activation+2.18e-01

Pos logit contributions
 salon+0.020
aring+0.020
itating+0.016
Instead+0.016
 perspective+0.016
Neg logit contributions
CA-0.014
 steam-0.013
kins-0.013
 sailors-0.013
 pans-0.012
Token mummy
Token ID38567
Feature activation-2.29e-01

Pos logit contributions
CA+0.011
 emergencies+0.011
 steam+0.010
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.014
aring-0.013
spe-0.012
Instead-0.011
ho-0.011
Token like
Token ID588
Feature activation-6.21e-01

Pos logit contributions
 salon+0.012
aring+0.011
spe+0.010
ho+0.010
Instead+0.010
Neg logit contributions
 steam-0.011
 emergencies-0.011
 sailors-0.011
 batteries-0.010
 pans-0.010
Token lions
Token ID31420
Feature activation-2.14e-02

Pos logit contributions
 salon+0.050
aring+0.046
spe+0.042
Instead+0.042
ho+0.041
Neg logit contributions
CA-0.022
 emergencies-0.021
 steam-0.020
 sailors-0.020
 lava-0.019
Token,
Token ID11
Feature activation+4.07e-01

Pos logit contributions
 salon+0.001
aring+0.001
spe+0.001
Instead+0.001
ho+0.001
Neg logit contributions
CA-0.001
 emergencies-0.001
 steam-0.001
 sailors-0.001
 lava-0.001
Token gir
Token ID37370
Feature activation-8.58e-02

Pos logit contributions
 steam+0.015
CA+0.015
 sailors+0.014
 lava+0.014
 emergencies+0.014
Neg logit contributions
 salon-0.032
aring-0.030
Instead-0.028
spe-0.028
 Sadly-0.027
Tokenaff
Token ID2001
Feature activation+3.60e-01

Pos logit contributions
 salon+0.004
aring+0.004
ho+0.003
spe+0.003
Instead+0.003
Neg logit contributions
CA-0.006
 emergencies-0.005
 steam-0.005
kins-0.005
 batteries-0.005
Tokenes
Token ID274
Feature activation+1.98e+00

Pos logit contributions
CA+0.019
 emergencies+0.018
 steam+0.017
 batteries+0.016
 lava+0.016
Neg logit contributions
 salon-0.023
aring-0.022
ho-0.020
spe-0.019
 pad-0.019
Token,
Token ID11
Feature activation+6.36e-01

Pos logit contributions
CA+0.094
 emergencies+0.094
 steam+0.094
 sailors+0.091
kins+0.090
Neg logit contributions
 salon-0.128
aring-0.115
spe-0.106
Instead-0.106
 Sadly-0.099
Token and
Token ID290
Feature activation+9.80e-01

Pos logit contributions
 steam+0.028
 sailors+0.026
CA+0.026
 lava+0.025
 aliens+0.025
Neg logit contributions
 salon-0.046
aring-0.044
spe-0.040
Instead-0.040
 Sadly-0.039
Token elephants
Token ID25368
Feature activation+5.99e-01

Pos logit contributions
 steam+0.032
 sailors+0.032
 emergencies+0.031
 aliens+0.030
 lava+0.029
Neg logit contributions
 salon-0.083
aring-0.078
Instead-0.072
spe-0.071
ared-0.070
Token.
Token ID13
Feature activation+5.39e-01

Pos logit contributions
 emergencies+0.014
 steam+0.013
 sailors+0.013
CA+0.012
 lava+0.012
Neg logit contributions
 salon-0.054
aring-0.049
Instead-0.047
spe-0.046
 Sadly-0.046
Token
Token ID198
Feature activation+3.91e-01

Pos logit contributions
CA+0.027
 emergencies+0.025
 steam+0.024
 lava+0.023
 sailors+0.023
Neg logit contributions
 salon-0.036
aring-0.032
spe-0.030
Instead-0.027
ho-0.027
Token and
Token ID290
Feature activation+6.80e-01

Pos logit contributions
 steam+0.028
CA+0.027
 emergencies+0.026
 lava+0.025
 sailors+0.024
Neg logit contributions
 salon-0.048
aring-0.041
Instead-0.039
spe-0.039
ho-0.037
Token noisy
Token ID31210
Feature activation+3.57e-01

Pos logit contributions
 steam+0.031
CA+0.030
 emergencies+0.029
 sailors+0.028
 batteries+0.028
Neg logit contributions
 salon-0.048
aring-0.044
Instead-0.038
spe-0.037
ho-0.037
Token voice
Token ID3809
Feature activation+3.19e-01

Pos logit contributions
 steam+0.016
 emergencies+0.015
 lava+0.015
CA+0.015
 sailors+0.015
Neg logit contributions
 salon-0.026
aring-0.023
Instead-0.022
spe-0.021
ho-0.020
Token,
Token ID11
Feature activation+1.55e-01

Pos logit contributions
CA+0.015
 emergencies+0.015
 steam+0.015
 sailors+0.014
 lava+0.014
Neg logit contributions
 salon-0.021
aring-0.019
Instead-0.017
spe-0.017
ho-0.017
Token "
Token ID366
Feature activation+6.08e-01

Pos logit contributions
 steam+0.008
CA+0.007
 emergencies+0.007
 sailors+0.007
 lava+0.007
Neg logit contributions
 salon-0.010
aring-0.009
Instead-0.008
spe-0.008
ench-0.008
TokenJohn
Token ID7554
Feature activation+1.92e+00

Pos logit contributions
CA+0.031
 steam+0.028
 emergencies+0.028
 sailors+0.027
 batteries+0.026
Neg logit contributions
 salon-0.041
aring-0.036
 pad-0.032
ho-0.032
ench-0.031
Token,
Token ID11
Feature activation+7.61e-01

Pos logit contributions
CA+0.104
 steam+0.101
 emergencies+0.101
 sailors+0.098
 lava+0.096
Neg logit contributions
 salon-0.118
aring-0.099
Instead-0.091
spe-0.090
ho-0.086
Token these
Token ID777
Feature activation-4.51e-02

Pos logit contributions
 steam+0.036
 emergencies+0.035
 lava+0.033
 sailors+0.033
 batteries+0.032
Neg logit contributions
 salon-0.052
aring-0.046
ared-0.045
Instead-0.044
spe-0.043
Token caul
Token ID46087
Feature activation+7.38e-01

Pos logit contributions
 salon+0.003
aring+0.003
spe+0.003
Instead+0.003
ho+0.003
Neg logit contributions
CA-0.002
 emergencies-0.002
 steam-0.002
 lava-0.002
 sailors-0.002
Tokenif
Token ID361
Feature activation+2.73e-01

Pos logit contributions
CA+0.010
 emergencies+0.009
 steam+0.008
 sailors+0.007
 lava+0.006
Neg logit contributions
 salon-0.075
aring-0.070
spe-0.066
Instead-0.065
ho-0.064
Tokenl
Token ID75
Feature activation+1.60e+00

Pos logit contributions
CA+0.011
 emergencies+0.010
 steam+0.010
 sailors+0.009
 lava+0.009
Neg logit contributions
 salon-0.021
aring-0.019
spe-0.018
Instead-0.017
ho-0.017
Token playing
Token ID2712
Feature activation+4.41e-01

Pos logit contributions
CA+0.011
 emergencies+0.011
 steam+0.011
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.014
aring-0.012
spe-0.011
Instead-0.011
ho-0.010
Token together
Token ID1978
Feature activation+2.29e-01

Pos logit contributions
CA+0.030
 emergencies+0.027
agons+0.026
 pans+0.026
agles+0.026
Neg logit contributions
 salon-0.021
aring-0.017
spe-0.016
Instead-0.015
 Even-0.015
Token,
Token ID11
Feature activation-1.36e-01

Pos logit contributions
 emergencies+0.008
 steam+0.008
 sailors+0.008
CA+0.008
kins+0.008
Neg logit contributions
 salon-0.018
aring-0.016
Instead-0.015
spe-0.014
 Sadly-0.014
Token and
Token ID290
Feature activation+1.44e-01

Pos logit contributions
 salon+0.011
aring+0.010
Instead+0.010
ared+0.010
ench+0.009
Neg logit contributions
 steam-0.005
 sailors-0.005
 lava-0.005
CA-0.004
 emergencies-0.004
Token showed
Token ID3751
Feature activation+1.05e-01

Pos logit contributions
 steam+0.004
 sailors+0.004
 lava+0.004
 emergencies+0.004
 Bert+0.004
Neg logit contributions
 salon-0.013
aring-0.012
Instead-0.011
olding-0.011
ench-0.011
Token each
Token ID1123
Feature activation+2.07e+00

Pos logit contributions
CA+0.005
 emergencies+0.004
 steam+0.004
 sailors+0.004
 lava+0.004
Neg logit contributions
 salon-0.008
aring-0.007
spe-0.006
Instead-0.006
ho-0.006
Token other
Token ID584
Feature activation+1.08e+00

Pos logit contributions
CA+0.079
 emergencies+0.079
 steam+0.078
 sailors+0.075
 batteries+0.074
Neg logit contributions
 salon-0.161
aring-0.149
spe-0.135
ho-0.134
Instead-0.132
Token their
Token ID511
Feature activation+7.99e-01

Pos logit contributions
 steam+0.038
 sailors+0.036
 batteries+0.036
 emergencies+0.036
 aliens+0.034
Neg logit contributions
 salon-0.089
aring-0.079
ho-0.076
Instead-0.074
 Sadly-0.072
Token famous
Token ID5863
Feature activation+4.79e-01

Pos logit contributions
CA+0.041
rob+0.037
kins+0.037
 lava+0.036
 emergencies+0.036
Neg logit contributions
 salon-0.049
aring-0.046
spe-0.045
Instead-0.041
 pad-0.040
Token toys
Token ID14958
Feature activation+1.12e+00

Pos logit contributions
CA+0.024
 emergencies+0.022
 lava+0.021
kins+0.021
 pans+0.021
Neg logit contributions
 salon-0.031
aring-0.029
spe-0.027
Instead-0.025
 pad-0.025
Token.
Token ID13
Feature activation+3.19e-01

Pos logit contributions
CA+0.041
 emergencies+0.038
 steam+0.036
 sailors+0.035
 lava+0.035
Neg logit contributions
 salon-0.089
aring-0.081
spe-0.075
Instead-0.074
ho-0.073
Token flour
Token ID10601
Feature activation-1.45e-01

Pos logit contributions
CA+0.043
 emergencies+0.041
 sailors+0.037
 lava+0.035
 steam+0.035
Neg logit contributions
 salon-0.079
aring-0.068
spe-0.064
ho-0.063
Instead-0.063
Token,
Token ID11
Feature activation+1.83e+00

Pos logit contributions
 salon+0.009
aring+0.008
spe+0.007
Instead+0.007
ho+0.007
Neg logit contributions
CA-0.008
 emergencies-0.007
 steam-0.007
 sailors-0.007
 lava-0.007
Token water
Token ID1660
Feature activation+1.10e+00

Pos logit contributions
CA+0.074
 steam+0.070
 emergencies+0.070
 pans+0.067
 lava+0.066
Neg logit contributions
 salon-0.137
aring-0.130
spe-0.116
Instead-0.115
ho-0.112
Token,
Token ID11
Feature activation+1.31e+00

Pos logit contributions
CA+0.057
 steam+0.055
 emergencies+0.055
 lava+0.053
kins+0.053
Neg logit contributions
 salon-0.069
aring-0.063
Instead-0.057
spe-0.057
 Sadly-0.052
Token yeast
Token ID20146
Feature activation+2.93e-01

Pos logit contributions
 steam+0.055
CA+0.054
 pans+0.052
 emergencies+0.052
 lava+0.051
Neg logit contributions
 salon-0.096
aring-0.094
spe-0.083
Instead-0.082
ho-0.078
Token and
Token ID290
Feature activation+2.25e+00

Pos logit contributions
CA+0.014
 steam+0.014
kins+0.014
 lava+0.014
 emergencies+0.013
Neg logit contributions
 salon-0.019
aring-0.018
Instead-0.016
spe-0.016
 Sadly-0.015
Token salt
Token ID8268
Feature activation+4.46e-01

Pos logit contributions
CA+0.085
 emergencies+0.082
 steam+0.081
 lava+0.076
 sailors+0.076
Neg logit contributions
 salon-0.176
aring-0.165
spe-0.150
Instead-0.147
ho-0.145
Token in
Token ID287
Feature activation-1.27e-02

Pos logit contributions
CA+0.023
 emergencies+0.022
 steam+0.021
 sailors+0.021
 lava+0.020
Neg logit contributions
 salon-0.029
aring-0.026
spe-0.023
ho-0.023
Instead-0.023
Token a
Token ID257
Feature activation+4.25e-01

Pos logit contributions
 salon+0.001
aring+0.001
spe+0.001
Instead+0.001
ho+0.001
Neg logit contributions
CA-0.000
 steam-0.000
 emergencies-0.000
 lava-0.000
 batteries-0.000
Token big
Token ID1263
Feature activation+5.82e-01

Pos logit contributions
 steam+0.018
 pans+0.018
CA+0.017
 emergencies+0.017
 lava+0.016
Neg logit contributions
aring-0.031
 salon-0.031
ared-0.027
spe-0.027
ouncing-0.026
Token bowl
Token ID9396
Feature activation+3.81e-01

Pos logit contributions
 steam+0.026
CA+0.024
 lava+0.024
 pans+0.023
 emergencies+0.023
Neg logit contributions
aring-0.042
 salon-0.042
spe-0.037
Instead-0.037
ared-0.036
Token were
Token ID547
Feature activation+1.26e-01

Pos logit contributions
 steam+0.009
CA+0.009
 sailors+0.009
kins+0.008
 aliens+0.008
Neg logit contributions
 salon-0.013
aring-0.013
Instead-0.010
spe-0.010
olding-0.010
Token all
Token ID477
Feature activation-8.03e-01

Pos logit contributions
 steam+0.007
 sailors+0.006
 emergencies+0.006
CA+0.006
 lava+0.006
Neg logit contributions
 salon-0.008
aring-0.007
ho-0.007
Instead-0.007
spe-0.006
Token wearing
Token ID5762
Feature activation+6.60e-01

Pos logit contributions
 salon+0.049
aring+0.044
Instead+0.040
ho+0.040
 While+0.038
Neg logit contributions
 steam-0.043
CA-0.041
 sailors-0.041
 emergencies-0.041
 lava-0.040
Token matching
Token ID12336
Feature activation+7.42e-02

Pos logit contributions
CA+0.031
 emergencies+0.028
 sailors+0.026
 lava+0.026
 steam+0.026
Neg logit contributions
 salon-0.046
aring-0.040
spe-0.038
Instead-0.037
ho-0.037
Token outfits
Token ID27655
Feature activation+5.32e-01

Pos logit contributions
CA+0.003
 emergencies+0.003
 steam+0.003
 sailors+0.003
 lava+0.003
Neg logit contributions
 salon-0.005
aring-0.005
spe-0.005
Instead-0.005
ho-0.004
Token.
Token ID13
Feature activation+3.79e-01

Pos logit contributions
CA+0.025
 steam+0.024
 sailors+0.024
kins+0.024
 batteries+0.024
Neg logit contributions
 salon-0.035
aring-0.032
Instead-0.029
spe-0.028
 Sadly-0.028
Token
Token ID198
Feature activation+5.25e-01

Pos logit contributions
CA+0.021
 emergencies+0.020
 steam+0.019
 sailors+0.019
 lava+0.019
Neg logit contributions
 salon-0.023
aring-0.021
spe-0.018
ho-0.018
Instead-0.018
Token
Token ID198
Feature activation+7.79e-01

Pos logit contributions
CA+0.027
 emergencies+0.026
 steam+0.025
 sailors+0.025
 lava+0.025
Neg logit contributions
 salon-0.034
aring-0.030
spe-0.027
Instead-0.027
ho-0.026
TokenBilly
Token ID49640
Feature activation-7.27e-02

Pos logit contributions
CA+0.043
 emergencies+0.040
 steam+0.039
 sailors+0.037
agons+0.036
Neg logit contributions
 salon-0.048
aring-0.043
ho-0.039
spe-0.037
ared-0.037
Token ran
Token ID4966
Feature activation+7.44e-02

Pos logit contributions
 salon+0.005
aring+0.005
Instead+0.004
 tant+0.004
 perspective+0.004
Neg logit contributions
CA-0.003
 steam-0.003
 sailors-0.003
pa-0.003
 batteries-0.003
Token over
Token ID625
Feature activation-4.30e-01

Pos logit contributions
 sailors+0.003
 steam+0.003
 batteries+0.003
CA+0.003
 him+0.003
Neg logit contributions
 salon-0.005
aring-0.005
Instead-0.005
spe-0.005
ho-0.005
Token made
Token ID925
Feature activation-6.84e-01

Pos logit contributions
CA+0.044
 steam+0.042
 emergencies+0.041
 lava+0.040
 sailors+0.039
Neg logit contributions
 salon-0.091
aring-0.083
spe-0.076
Instead-0.076
ho-0.072
Token it
Token ID340
Feature activation-2.35e-01

Pos logit contributions
 salon+0.051
aring+0.047
Instead+0.043
spe+0.042
ho+0.041
Neg logit contributions
CA-0.027
 emergencies-0.027
 steam-0.026
 lava-0.025
 sailors-0.025
Token look
Token ID804
Feature activation-4.81e-02

Pos logit contributions
 salon+0.017
aring+0.015
Instead+0.014
 Sadly+0.013
ho+0.013
Neg logit contributions
 steam-0.011
 lava-0.010
 sailors-0.010
CA-0.010
 sparks-0.010
Token nice
Token ID3621
Feature activation+2.54e-02

Pos logit contributions
 salon+0.003
aring+0.003
Instead+0.003
spe+0.003
ho+0.002
Neg logit contributions
CA-0.002
 steam-0.002
 emergencies-0.002
 sailors-0.002
 lava-0.002
Token and
Token ID290
Feature activation+1.04e+00

Pos logit contributions
 steam+0.001
CA+0.001
 sailors+0.001
 emergencies+0.001
 batteries+0.001
Neg logit contributions
 salon-0.002
aring-0.002
Instead-0.002
spe-0.002
 Sadly-0.002
Token delicious
Token ID12625
Feature activation+6.56e-01

Pos logit contributions
CA+0.043
 steam+0.042
 emergencies+0.041
 pans+0.041
 sailors+0.041
Neg logit contributions
 salon-0.078
aring-0.071
ho-0.062
spe-0.062
Instead-0.062
Token.
Token ID13
Feature activation+6.83e-01

Pos logit contributions
CA+0.027
 emergencies+0.024
 steam+0.022
 sailors+0.021
agons+0.021
Neg logit contributions
 salon-0.050
aring-0.046
spe-0.042
ho-0.042
Instead-0.041
Token He
Token ID679
Feature activation-1.26e-01

Pos logit contributions
CA+0.036
 emergencies+0.035
 steam+0.034
 sailors+0.033
 lava+0.033
Neg logit contributions
 salon-0.043
aring-0.038
spe-0.033
ho-0.033
Instead-0.033
Token eagerly
Token ID30130
Feature activation+6.34e-01

Pos logit contributions
 salon+0.008
aring+0.008
Instead+0.007
itating+0.007
 perspective+0.007
Neg logit contributions
 steam-0.006
CA-0.006
 sailors-0.005
kins-0.005
 lava-0.005
Token picked
Token ID6497
Feature activation+7.89e-01

Pos logit contributions
 steam+0.030
CA+0.027
 sailors+0.026
 lava+0.025
 pans+0.025
Neg logit contributions
 salon-0.042
aring-0.040
Instead-0.035
itating-0.035
spe-0.034
Token it
Token ID340
Feature activation+3.73e-01

Pos logit contributions
CA+0.028
 steam+0.026
 emergencies+0.026
 sailors+0.025
 lava+0.025
Neg logit contributions
 salon-0.064
aring-0.059
spe-0.054
Instead-0.053
ho-0.052
Token save
Token ID3613
Feature activation+5.39e-01

Pos logit contributions
 emergencies+0.031
CA+0.030
 steam+0.029
 sailors+0.028
 batteries+0.028
Neg logit contributions
 salon-0.046
aring-0.042
spe-0.038
Instead-0.037
ho-0.037
Token herself
Token ID5223
Feature activation+9.52e-01

Pos logit contributions
CA+0.020
 emergencies+0.019
 steam+0.018
 sailors+0.017
 lava+0.017
Neg logit contributions
 salon-0.043
aring-0.039
spe-0.036
Instead-0.036
ho-0.035
Token.
Token ID13
Feature activation-5.26e-02

Pos logit contributions
 emergencies+0.023
kins+0.022
 steam+0.021
 batteries+0.020
CA+0.020
Neg logit contributions
 salon-0.086
aring-0.077
Instead-0.073
ho-0.072
spe-0.071
Token The
Token ID383
Feature activation-1.94e-01

Pos logit contributions
 salon+0.003
aring+0.003
spe+0.003
ho+0.003
Instead+0.003
Neg logit contributions
CA-0.003
 emergencies-0.003
 steam-0.003
 sailors-0.002
 lava-0.002
Token girl
Token ID2576
Feature activation-4.94e-01

Pos logit contributions
 salon+0.012
aring+0.012
spe+0.010
ho+0.010
ared+0.010
Neg logit contributions
 steam-0.010
CA-0.010
 emergencies-0.010
 sailors-0.009
 batteries-0.009
Token lived
Token ID5615
Feature activation+4.09e-01

Pos logit contributions
 salon+0.033
aring+0.031
Instead+0.027
itating+0.026
ashing+0.026
Neg logit contributions
 steam-0.022
CA-0.022
 sailors-0.022
kins-0.021
pa-0.020
Token a
Token ID257
Feature activation+7.51e-03

Pos logit contributions
CA+0.020
kins+0.020
 emergencies+0.019
 sailors+0.019
 steam+0.019
Neg logit contributions
 salon-0.026
aring-0.025
Instead-0.021
spe-0.021
ho-0.020
Token happy
Token ID3772
Feature activation+3.12e-01

Pos logit contributions
 steam+0.000
CA+0.000
 sailors+0.000
 emergencies+0.000
 pans+0.000
Neg logit contributions
 salon-0.000
aring-0.000
ared-0.000
Instead-0.000
ouncing-0.000
Token life
Token ID1204
Feature activation-7.55e-01

Pos logit contributions
 steam+0.013
 sailors+0.013
 alien+0.013
 shark+0.012
 sunrise+0.012
Neg logit contributions
aring-0.022
 salon-0.021
Instead-0.020
itating-0.020
ared-0.020
Token.
Token ID13
Feature activation-2.13e-01

Pos logit contributions
 salon+0.053
aring+0.048
Instead+0.045
spe+0.042
 While+0.042
Neg logit contributions
 emergencies-0.032
CA-0.031
 steam-0.031
 sailors-0.030
 batteries-0.030
Token<|endoftext|>
Token ID50256
Feature activation-3.93e-01

Pos logit contributions
 salon+0.013
aring+0.012
spe+0.010
Instead+0.010
ho+0.010
Neg logit contributions
CA-0.012
 emergencies-0.011
 steam-0.011
 sailors-0.011
 lava-0.011
TokenYes
Token ID5297
Feature activation+1.46e+00

Pos logit contributions
CA+0.061
 steam+0.056
 pans+0.055
 emergencies+0.055
 batteries+0.053
Neg logit contributions
 salon-0.036
aring-0.033
spe-0.028
 pad-0.026
ared-0.025
Token,
Token ID11
Feature activation+7.53e-01

Pos logit contributions
CA+0.094
 emergencies+0.090
 steam+0.086
 sailors+0.086
 batteries+0.085
Neg logit contributions
 salon-0.077
aring-0.067
Instead-0.058
spe-0.058
ho-0.057
Token you
Token ID345
Feature activation+6.45e-01

Pos logit contributions
CA+0.042
 emergencies+0.041
 steam+0.040
 sailors+0.039
 lava+0.038
Neg logit contributions
 salon-0.046
aring-0.040
spe-0.037
Instead-0.036
ho-0.035
Token can
Token ID460
Feature activation+3.28e-01

Pos logit contributions
CA+0.028
 steam+0.027
 emergencies+0.027
 sailors+0.026
 lava+0.026
Neg logit contributions
 salon-0.049
aring-0.042
spe-0.041
ho-0.038
Instead-0.037
Token share
Token ID2648
Feature activation+4.69e-01

Pos logit contributions
CA+0.014
 steam+0.013
 emergencies+0.013
 lava+0.012
kins+0.012
Neg logit contributions
 salon-0.024
aring-0.021
spe-0.021
Instead-0.019
ho-0.019
Token it
Token ID340
Feature activation+4.61e-01

Pos logit contributions
CA+0.019
 emergencies+0.018
 steam+0.016
 sailors+0.016
 lava+0.016
Neg logit contributions
 salon-0.036
aring-0.032
Instead-0.029
spe-0.029
ho-0.029
Token.
Token ID13
Feature activation+6.74e-01

Pos logit contributions
kins+0.017
 pans+0.016
 steam+0.016
 batteries+0.016
CA+0.016
Neg logit contributions
 salon-0.035
aring-0.031
spe-0.030
Instead-0.029
ho-0.029
Token But
Token ID887
Feature activation+1.23e-01

Pos logit contributions
CA+0.033
 emergencies+0.032
 steam+0.031
 sailors+0.030
 batteries+0.030
Neg logit contributions
 salon-0.046
spe-0.038
aring-0.037
 tant-0.035
ho-0.035
Token wash
Token ID13502
Feature activation+6.65e-01

Pos logit contributions
 emergencies+0.005
 steam+0.005
CA+0.005
 sailors+0.005
 lava+0.005
Neg logit contributions
 salon-0.008
aring-0.008
spe-0.007
Instead-0.007
 Sadly-0.007
Token it
Token ID340
Feature activation+8.37e-01

Pos logit contributions
CA+0.021
 emergencies+0.021
 steam+0.021
kins+0.019
 sailors+0.019
Neg logit contributions
 salon-0.055
aring-0.051
spe-0.047
Instead-0.046
ho-0.046
Token first
Token ID717
Feature activation+5.14e-01

Pos logit contributions
 steam+0.037
kins+0.036
 pans+0.036
CA+0.035
 lava+0.035
Neg logit contributions
 salon-0.059
aring-0.053
spe-0.049
Instead-0.046
ho-0.046
Token something
Token ID1223
Feature activation-2.82e-01

Pos logit contributions
 salon+0.025
 few+0.023
 Even+0.022
 nine+0.022
Instead+0.021
Neg logit contributions
CA-0.028
rob-0.026
agons-0.025
kins-0.025
unks-0.024
Token to
Token ID284
Feature activation+1.33e-01

Pos logit contributions
 salon+0.017
aring+0.015
spe+0.013
Instead+0.013
ho+0.012
Neg logit contributions
CA-0.016
 emergencies-0.016
 steam-0.015
 sailors-0.015
 lava-0.015
Token happen
Token ID1645
Feature activation-6.19e-01

Pos logit contributions
CA+0.009
 emergencies+0.009
 lava+0.009
 steam+0.009
 sailors+0.009
Neg logit contributions
 salon-0.006
aring-0.005
Instead-0.005
spe-0.004
ho-0.004
Token.
Token ID13
Feature activation+2.10e-02

Pos logit contributions
 salon+0.048
aring+0.043
spe+0.040
Instead+0.039
ho+0.039
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.022
 sailors-0.021
 lava-0.021
Token Nothing
Token ID10528
Feature activation+4.11e-01

Pos logit contributions
CA+0.001
 emergencies+0.001
 lava+0.001
 steam+0.001
 Bert+0.001
Neg logit contributions
 salon-0.001
aring-0.001
ho-0.001
spe-0.001
 glimpse-0.001
Token did
Token ID750
Feature activation+4.52e-01

Pos logit contributions
CA+0.016
 emergencies+0.016
agons+0.015
 sailors+0.015
 pans+0.015
Neg logit contributions
 salon-0.030
aring-0.028
spe-0.026
Instead-0.025
ho-0.024
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
CA+0.020
 emergencies+0.019
 steam+0.018
 sailors+0.018
 lava+0.018
Neg logit contributions
 salon-0.032
aring-0.029
spe-0.027
Instead-0.026
ho-0.026
Token
Token ID220
Feature activation-1.16e+00

Pos logit contributions
CA+0.022
 emergencies+0.022
 lava+0.021
 steam+0.021
 batteries+0.021
Neg logit contributions
 salon-0.029
aring-0.025
ho-0.022
spe-0.022
 glimpse-0.021
Token
Token ID198
Feature activation-1.89e-02

Pos logit contributions
 salon+0.071
aring+0.064
Instead+0.057
spe+0.057
 Even+0.054
Neg logit contributions
CA-0.063
 emergencies-0.060
 steam-0.059
 sailors-0.058
 lava-0.058
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
 salon+0.001
aring+0.001
spe+0.001
ho+0.001
Instead+0.001
Neg logit contributions
CA-0.001
 emergencies-0.001
 steam-0.001
 sailors-0.001
 lava-0.001
TokenThe
Token ID464
Feature activation-1.62e-01

Pos logit contributions
CA+0.015
 emergencies+0.014
 steam+0.013
 sailors+0.013
 lava+0.012
Neg logit contributions
 salon-0.018
aring-0.015
ho-0.015
ared-0.013
 pad-0.013
Token her
Token ID607
Feature activation-1.22e-01

Pos logit contributions
 salon+0.067
aring+0.061
spe+0.056
Instead+0.055
ho+0.054
Neg logit contributions
CA-0.037
 emergencies-0.035
 steam-0.034
 sailors-0.033
 lava-0.032
Token plan
Token ID1410
Feature activation-2.00e-01

Pos logit contributions
aring+0.008
 salon+0.008
Instead+0.007
ho+0.007
spe+0.007
Neg logit contributions
 steam-0.006
CA-0.006
 emergencies-0.005
kins-0.005
 pans-0.005
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
 salon+0.016
aring+0.015
spe+0.014
ho+0.014
Instead+0.014
Neg logit contributions
 emergencies-0.006
CA-0.006
 steam-0.006
 batteries-0.006
 sailors-0.006
Token She
Token ID1375
Feature activation-1.97e-01

Pos logit contributions
CA+0.010
 emergencies+0.010
 steam+0.010
 batteries+0.010
 Bert+0.010
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.008
ho-0.007
Instead-0.007
Token decided
Token ID3066
Feature activation-1.30e-01

Pos logit contributions
 salon+0.012
aring+0.011
Instead+0.010
spe+0.010
ho+0.009
Neg logit contributions
CA-0.011
 steam-0.010
 sailors-0.010
 emergencies-0.010
 batteries-0.010
Token to
Token ID284
Feature activation-2.60e-02

Pos logit contributions
 salon+0.010
aring+0.009
spe+0.009
Instead+0.009
 tant+0.008
Neg logit contributions
 emergencies-0.004
 steam-0.004
CA-0.004
 him-0.004
 his-0.004
Token bake
Token ID28450
Feature activation+1.68e-01

Pos logit contributions
 salon+0.002
aring+0.002
spe+0.001
ouncing+0.001
ashing+0.001
Neg logit contributions
 steam-0.001
 emergencies-0.001
 sailors-0.001
 lava-0.001
CA-0.001
Token a
Token ID257
Feature activation+6.08e-01

Pos logit contributions
CA+0.007
 emergencies+0.007
 steam+0.007
 lava+0.006
 sailors+0.006
Neg logit contributions
 salon-0.012
aring-0.011
spe-0.010
Instead-0.010
ho-0.010
Token cake
Token ID12187
Feature activation+9.09e-03

Pos logit contributions
 steam+0.024
 emergencies+0.022
CA+0.021
 pans+0.021
 lava+0.021
Neg logit contributions
aring-0.045
 salon-0.044
ared-0.042
Instead-0.040
spe-0.039
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
 steam+0.000
CA+0.000
kins+0.000
 emergencies+0.000
 lava+0.000
Neg logit contributions
 salon-0.001
aring-0.001
Instead-0.000
spe-0.000
 Sadly-0.000
Token buy
Token ID2822
Feature activation+3.80e-01

Pos logit contributions
 steam+0.007
 emergencies+0.006
CA+0.006
 sailors+0.006
 batteries+0.006
Neg logit contributions
 salon-0.008
aring-0.008
spe-0.007
Instead-0.007
ho-0.007
Token worried
Token ID7960
Feature activation+2.66e-01

Pos logit contributions
 salon+0.000
aring+0.000
ho+0.000
spe+0.000
Instead+0.000
Neg logit contributions
 emergencies-0.000
CA-0.000
 steam-0.000
 sailors-0.000
 batteries-0.000
Token that
Token ID326
Feature activation-2.39e-01

Pos logit contributions
 emergencies+0.012
CA+0.012
 steam+0.012
 lava+0.011
 batteries+0.011
Neg logit contributions
 salon-0.019
aring-0.017
spe-0.016
ho-0.015
Instead-0.015
Token she
Token ID673
Feature activation+2.89e-01

Pos logit contributions
aring+0.016
 salon+0.016
Instead+0.014
spe+0.013
ared+0.013
Neg logit contributions
 emergencies-0.011
 steam-0.011
CA-0.011
 batteries-0.010
 lava-0.010
Token wasn
Token ID2492
Feature activation-4.76e-01

Pos logit contributions
CA+0.017
 emergencies+0.016
 steam+0.016
 sailors+0.015
 lava+0.015
Neg logit contributions
 salon-0.017
aring-0.015
spe-0.013
Instead-0.013
ho-0.013
Token't
Token ID470
Feature activation-1.14e-03

Pos logit contributions
 salon+0.029
aring+0.026
Instead+0.023
spe+0.022
ho+0.022
Neg logit contributions
CA-0.027
 emergencies-0.026
 steam-0.025
 sailors-0.025
 lava-0.025
Token good
Token ID922
Feature activation-9.63e-01

Pos logit contributions
 salon+0.000
aring+0.000
Instead+0.000
spe+0.000
 pad+0.000
Neg logit contributions
CA-0.000
 emergencies-0.000
 steam-0.000
 lava-0.000
rob-0.000
Token enough
Token ID1576
Feature activation-1.33e+00

Pos logit contributions
 salon+0.048
aring+0.043
spe+0.036
Instead+0.035
ho+0.034
Neg logit contributions
CA-0.065
 emergencies-0.060
 steam-0.060
 lava-0.059
kins-0.057
Token.
Token ID13
Feature activation+1.90e-04

Pos logit contributions
 salon+0.084
aring+0.076
spe+0.067
Instead+0.067
ho+0.065
Neg logit contributions
CA-0.071
 emergencies-0.066
 steam-0.064
 sailors-0.062
 lava-0.062
Token
Token ID220
Feature activation-1.25e+00

Pos logit contributions
CA+0.000
 emergencies+0.000
 steam+0.000
 Farmer+0.000
 Bert+0.000
Neg logit contributions
 salon-0.000
aring-0.000
spe-0.000
ho-0.000
 glimpse-0.000
Token
Token ID198
Feature activation-2.03e-01

Pos logit contributions
 salon+0.077
aring+0.069
Instead+0.062
spe+0.061
ho+0.059
Neg logit contributions
CA-0.068
 emergencies-0.065
 steam-0.064
 sailors-0.062
 lava-0.062
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
 salon+0.015
aring+0.014
spe+0.013
ho+0.012
Instead+0.012
Neg logit contributions
CA-0.008
 emergencies-0.008
 steam-0.007
 batteries-0.007
 sailors-0.007
Token oranges
Token ID48389
Feature activation-1.00e-01

Pos logit contributions
CA+0.023
 lava+0.022
 steam+0.022
 sparks+0.020
 pans+0.020
Neg logit contributions
 salon-0.055
aring-0.052
spe-0.047
itating-0.046
olding-0.045
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
 salon+0.008
aring+0.007
spe+0.007
Instead+0.006
 Sadly+0.006
Neg logit contributions
CA-0.004
 lava-0.004
 steam-0.004
kins-0.003
 emergencies-0.003
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
CA+0.017
 emergencies+0.015
 steam+0.015
 batteries+0.015
 lava+0.014
Neg logit contributions
 salon-0.024
aring-0.022
spe-0.021
ho-0.020
Instead-0.019
Token
Token ID198
Feature activation+6.24e-01

Pos logit contributions
CA+0.018
 emergencies+0.017
 steam+0.017
 sailors+0.016
 lava+0.016
Neg logit contributions
 salon-0.022
aring-0.020
spe-0.018
Instead-0.018
ho-0.017
TokenL
Token ID43
Feature activation+1.21e-01

Pos logit contributions
CA+0.027
B+0.023
 pans+0.021
 emergencies+0.020
 steam+0.020
Neg logit contributions
 salon-0.047
ho-0.043
spe-0.042
aring-0.041
ared-0.039
Tokenily
Token ID813
Feature activation+5.41e-02

Pos logit contributions
CA+0.005
 emergencies+0.005
 steam+0.005
 sailors+0.005
 lava+0.005
Neg logit contributions
 salon-0.009
aring-0.008
spe-0.007
Instead-0.007
ho-0.007
Token said
Token ID531
Feature activation-2.16e-01

Pos logit contributions
CA+0.003
 steam+0.002
pa+0.002
 pans+0.002
 sailors+0.002
Neg logit contributions
 salon-0.004
aring-0.003
spe-0.003
 tant-0.003
 glimpse-0.003
Token,
Token ID11
Feature activation-9.93e-01

Pos logit contributions
 salon+0.015
aring+0.013
spe+0.012
Instead+0.012
 pad+0.011
Neg logit contributions
CA-0.010
 steam-0.009
 emergencies-0.009
 lava-0.009
kins-0.009
Token "
Token ID366
Feature activation+2.70e-01

Pos logit contributions
 salon+0.052
aring+0.045
spe+0.039
Instead+0.039
ho+0.038
Neg logit contributions
CA-0.063
 emergencies-0.062
 steam-0.059
 sailors-0.058
 lava-0.058
TokenI
Token ID40
Feature activation+5.86e-01

Pos logit contributions
CA+0.013
 steam+0.011
 pans+0.010
 emergencies+0.010
rob+0.010
Neg logit contributions
 salon-0.020
aring-0.019
spe-0.016
olding-0.016
ared-0.015
Token want
Token ID765
Feature activation-1.19e-01

Pos logit contributions
CA+0.031
 steam+0.029
 happened+0.029
?"+0.028
?+0.028
Neg logit contributions
 salon-0.038
aring-0.032
spe-0.030
Instead-0.029
itating-0.029
Token help
Token ID1037
Feature activation+5.46e-01

Pos logit contributions
 salon+0.051
aring+0.047
Instead+0.042
spe+0.042
ho+0.040
Neg logit contributions
CA-0.035
 emergencies-0.034
 steam-0.033
 sailors-0.031
 lava-0.031
Token."
Token ID526
Feature activation-1.56e-01

Pos logit contributions
 emergencies+0.015
 steam+0.014
 batteries+0.013
CA+0.013
 sailors+0.012
Neg logit contributions
 salon-0.046
aring-0.042
spe-0.041
Instead-0.040
ho-0.039
Token The
Token ID383
Feature activation-2.68e-01

Pos logit contributions
 salon+0.010
aring+0.009
spe+0.008
Instead+0.008
ho+0.008
Neg logit contributions
CA-0.008
 emergencies-0.008
 steam-0.007
 sailors-0.007
 lava-0.007
Token owl
Token ID39610
Feature activation-2.63e-01

Pos logit contributions
 salon+0.019
aring+0.017
Instead+0.016
spe+0.016
ho+0.015
Neg logit contributions
CA-0.012
 emergencies-0.012
 steam-0.011
 lava-0.011
 sailors-0.011
Token smiled
Token ID13541
Feature activation+6.52e-01

Pos logit contributions
 salon+0.019
aring+0.017
Instead+0.015
spe+0.015
ashing+0.014
Neg logit contributions
CA-0.012
 steam-0.011
kins-0.010
 sailors-0.010
ull-0.010
Token and
Token ID290
Feature activation+2.07e-01

Pos logit contributions
CA+0.033
 sailors+0.032
 steam+0.031
 emergencies+0.030
 lava+0.030
Neg logit contributions
 salon-0.044
aring-0.037
spe-0.034
Instead-0.034
ho-0.033
Token said
Token ID531
Feature activation+1.47e-01

Pos logit contributions
CA+0.012
 emergencies+0.011
 steam+0.011
agons+0.010
 batteries+0.010
Neg logit contributions
 salon-0.012
aring-0.011
Instead-0.010
spe-0.010
ho-0.010
Token,
Token ID11
Feature activation-5.67e-01

Pos logit contributions
CA+0.007
 emergencies+0.007
 sailors+0.007
 lava+0.007
 steam+0.007
Neg logit contributions
 salon-0.010
aring-0.008
Instead-0.007
spe-0.007
 pad-0.007
Token "
Token ID366
Feature activation+3.09e-01

Pos logit contributions
 salon+0.034
aring+0.030
spe+0.027
Instead+0.026
ho+0.025
Neg logit contributions
CA-0.032
 emergencies-0.030
 steam-0.030
 sailors-0.029
 lava-0.029
TokenYou
Token ID1639
Feature activation+4.80e-01

Pos logit contributions
CA+0.014
 emergencies+0.014
 steam+0.013
 sailors+0.013
 lava+0.013
Neg logit contributions
 salon-0.022
aring-0.020
spe-0.018
Instead-0.017
ho-0.017
Token're
Token ID821
Feature activation-8.23e-01

Pos logit contributions
CA+0.037
 emergencies+0.036
 steam+0.035
 sailors+0.034
 lava+0.034
Neg logit contributions
 salon-0.019
aring-0.016
spe-0.013
Instead-0.013
ho-0.012
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
 steam+0.005
 emergencies+0.005
CA+0.005
 sailors+0.005
 lava+0.005
Neg logit contributions
 salon-0.020
spe-0.017
aring-0.017
Instead-0.017
ho-0.016
Token The
Token ID383
Feature activation+1.19e-01

Pos logit contributions
CA+0.015
 emergencies+0.015
 steam+0.014
 sailors+0.014
 lava+0.014
Neg logit contributions
 salon-0.018
aring-0.016
spe-0.014
Instead-0.014
ho-0.014
Token little
Token ID1310
Feature activation-9.16e-01

Pos logit contributions
 steam+0.005
 emergencies+0.005
CA+0.005
 lava+0.005
 sailors+0.005
Neg logit contributions
 salon-0.008
aring-0.008
Instead-0.007
spe-0.007
ared-0.007
Token girl
Token ID2576
Feature activation-7.20e-01

Pos logit contributions
 salon+0.060
aring+0.058
Instead+0.051
spe+0.047
itating+0.047
Neg logit contributions
 steam-0.046
CA-0.044
 sailors-0.044
 lava-0.044
 batteries-0.043
Token was
Token ID373
Feature activation+2.30e-02

Pos logit contributions
 salon+0.052
aring+0.050
 perspective+0.046
Instead+0.045
 glimpse+0.045
Neg logit contributions
 steam-0.026
CA-0.026
 sparks-0.022
pa-0.022
 happened-0.021
Token very
Token ID845
Feature activation+1.54e-01

Pos logit contributions
 steam+0.001
 emergencies+0.001
CA+0.001
 sailors+0.001
 lava+0.001
Neg logit contributions
 salon-0.002
aring-0.001
ho-0.001
 perspective-0.001
spe-0.001
Token sad
Token ID6507
Feature activation-9.45e-01

Pos logit contributions
CA+0.007
 steam+0.007
kins+0.007
 pans+0.007
 emergencies+0.007
Neg logit contributions
 salon-0.010
 pad-0.009
aring-0.009
 perspective-0.009
Instead-0.008
Token and
Token ID290
Feature activation+1.39e-01

Pos logit contributions
 salon+0.081
spe+0.071
aring+0.070
Instead+0.069
ho+0.066
Neg logit contributions
 emergencies-0.027
 steam-0.027
 batteries-0.025
 lava-0.025
 sailors-0.023
Token cried
Token ID16896
Feature activation+5.60e-01

Pos logit contributions
 steam+0.007
CA+0.007
 emergencies+0.006
 lava+0.006
 sailors+0.006
Neg logit contributions
 salon-0.009
aring-0.009
 perspective-0.007
Instead-0.007
spe-0.007
Token a
Token ID257
Feature activation-5.84e-01

Pos logit contributions
 emergencies+0.019
CA+0.018
 steam+0.018
 lava+0.017
 sailors+0.017
Neg logit contributions
 salon-0.047
aring-0.041
spe-0.039
Instead-0.038
ho-0.037
Token lot
Token ID1256
Feature activation-9.06e-01

Pos logit contributions
 salon+0.040
aring+0.034
ared+0.032
spe+0.032
ress+0.031
Neg logit contributions
 steam-0.029
CA-0.027
 emergencies-0.027
 fire-0.026
 pans-0.026
Token
Token ID198
Feature activation+9.67e-02

Pos logit contributions
 salon+0.065
aring+0.060
Instead+0.053
spe+0.052
 Even+0.050
Neg logit contributions
CA-0.063
 emergencies-0.060
 steam-0.060
 sailors-0.058
 lava-0.058
Token
Token ID198
Feature activation+3.79e-01

Pos logit contributions
CA+0.005
 emergencies+0.004
 steam+0.004
 sailors+0.004
 lava+0.004
Neg logit contributions
 salon-0.007
aring-0.006
spe-0.006
ho-0.005
Instead-0.005
TokenFrom
Token ID4863
Feature activation-8.01e-01

Pos logit contributions
CA+0.018
 emergencies+0.016
 steam+0.016
 sailors+0.016
ull+0.015
Neg logit contributions
 salon-0.027
aring-0.023
ho-0.021
ared-0.021
spe-0.021
Token that
Token ID326
Feature activation+3.05e-02

Pos logit contributions
 salon+0.039
aring+0.034
Instead+0.030
ho+0.029
spe+0.029
Neg logit contributions
CA-0.054
 emergencies-0.052
 lava-0.049
 batteries-0.049
 steam-0.049
Token day
Token ID1110
Feature activation+2.08e-01

Pos logit contributions
 steam+0.001
 emergencies+0.001
CA+0.001
 lava+0.001
 Bert+0.001
Neg logit contributions
 salon-0.003
aring-0.002
ared-0.002
aney-0.002
Instead-0.002
Token forward
Token ID2651
Feature activation-1.52e+00

Pos logit contributions
CA+0.011
 emergencies+0.011
 steam+0.010
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.013
aring-0.012
Instead-0.011
spe-0.011
ho-0.010
Token,
Token ID11
Feature activation-1.53e-01

Pos logit contributions
 salon+0.107
aring+0.092
Instead+0.088
spe+0.085
itating+0.083
Neg logit contributions
CA-0.068
 emergencies-0.068
 sailors-0.066
 aliens-0.065
 steam-0.065
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
 salon+0.013
aring+0.012
Instead+0.011
spe+0.011
ho+0.011
Neg logit contributions
CA-0.004
 emergencies-0.004
 steam-0.004
 sailors-0.004
 lava-0.004
Token cel
Token ID18725
Feature activation-1.69e-01

Pos logit contributions
CA+0.005
 emergencies+0.005
 steam+0.005
 sailors+0.005
 lava+0.005
Neg logit contributions
 salon-0.007
aring-0.007
spe-0.006
Instead-0.006
ho-0.006
Tokenery
Token ID1924
Feature activation+1.07e+00

Pos logit contributions
 salon+0.014
aring+0.013
Instead+0.012
ho+0.012
spe+0.012
Neg logit contributions
CA-0.005
 emergencies-0.005
 steam-0.004
 sailors-0.004
 batteries-0.004
Token always
Token ID1464
Feature activation+7.72e-01

Pos logit contributions
CA+0.053
 steam+0.053
kins+0.052
 sailors+0.052
 emergencies+0.050
Neg logit contributions
 salon-0.069
aring-0.061
Instead-0.054
spe-0.052
ared-0.050
Token boat
Token ID8848
Feature activation-2.89e-01

Pos logit contributions
CA+0.009
 emergencies+0.008
kins+0.008
 lava+0.008
 steam+0.008
Neg logit contributions
 salon-0.014
aring-0.013
spe-0.012
Instead-0.011
ho-0.011
Token d
Token ID288
Feature activation+5.10e-01

Pos logit contributions
 salon+0.018
aring+0.016
Instead+0.014
spe+0.014
ho+0.014
Neg logit contributions
CA-0.016
 emergencies-0.015
 steam-0.015
 sailors-0.014
 lava-0.014
Tokenocked
Token ID3543
Feature activation+3.99e-01

Pos logit contributions
CA+0.031
 emergencies+0.029
 steam+0.029
 lava+0.028
agons+0.028
Neg logit contributions
 salon-0.029
aring-0.024
spe-0.023
Instead-0.021
ho-0.021
Token at
Token ID379
Feature activation-6.06e-01

Pos logit contributions
 steam+0.016
CA+0.016
 sailors+0.015
 lava+0.015
 emergencies+0.015
Neg logit contributions
 salon-0.031
aring-0.027
Instead-0.024
spe-0.023
ho-0.023
Token a
Token ID257
Feature activation-1.74e-01

Pos logit contributions
 salon+0.044
ho+0.037
aring+0.037
 pad+0.037
Instead+0.036
Neg logit contributions
CA-0.026
 emergencies-0.023
 pans-0.022
agons-0.022
kins-0.021
Token harbor
Token ID25451
Feature activation-1.40e+00

Pos logit contributions
 salon+0.013
aring+0.012
ared+0.011
ouncing+0.011
Instead+0.011
Neg logit contributions
 steam-0.008
 emergencies-0.007
CA-0.007
 lava-0.007
 sailors-0.007
Token far
Token ID1290
Feature activation-1.92e-01

Pos logit contributions
 salon+0.131
aring+0.119
Instead+0.115
 While+0.112
Of+0.112
Neg logit contributions
 steam-0.025
 sailors-0.022
 emergencies-0.021
 lava-0.020
kins-0.020
Token away
Token ID1497
Feature activation+6.77e-01

Pos logit contributions
 salon+0.013
aring+0.011
Instead+0.010
spe+0.009
aney+0.009
Neg logit contributions
 steam-0.009
CA-0.009
 sailors-0.009
 lava-0.009
 emergencies-0.009
Token.
Token ID13
Feature activation+2.71e-01

Pos logit contributions
 emergencies+0.018
CA+0.018
 steam+0.017
 sailors+0.017
 lava+0.017
Neg logit contributions
 salon-0.060
aring-0.055
Instead-0.051
spe-0.050
ho-0.049
Token The
Token ID383
Feature activation-1.21e-03

Pos logit contributions
CA+0.014
 emergencies+0.013
 steam+0.013
 lava+0.012
 sailors+0.012
Neg logit contributions
 salon-0.018
aring-0.016
spe-0.015
ho-0.014
Instead-0.014
Token cat
Token ID3797
Feature activation+3.29e-01

Pos logit contributions
 salon+0.000
aring+0.000
spe+0.000
Instead+0.000
ho+0.000
Neg logit contributions
CA-0.000
 emergencies-0.000
 steam-0.000
 lava-0.000
 sailors-0.000
Token forgive
Token ID20927
Feature activation-3.45e-01

Pos logit contributions
 salon+0.020
Instead+0.016
aring+0.016
bars+0.015
ress+0.015
Neg logit contributions
 steam-0.015
CA-0.015
 happened-0.014
 batteries-0.014
 sailors-0.013
Token you
Token ID345
Feature activation-6.20e-01

Pos logit contributions
 salon+0.023
aring+0.021
ho+0.018
Instead+0.018
 Even+0.017
Neg logit contributions
CA-0.018
 emergencies-0.015
 steam-0.015
 lava-0.015
 sailors-0.015
Token.
Token ID13
Feature activation-3.76e-02

Pos logit contributions
 salon+0.059
spe+0.052
aring+0.052
ho+0.051
Instead+0.051
Neg logit contributions
 emergencies-0.011
 sailors-0.011
 steam-0.010
 batteries-0.010
kins-0.009
Token You
Token ID921
Feature activation-1.02e+00

Pos logit contributions
 salon+0.002
aring+0.002
Instead+0.002
spe+0.002
ho+0.002
Neg logit contributions
CA-0.002
 emergencies-0.002
 steam-0.002
 sailors-0.002
 lava-0.002
Token're
Token ID821
Feature activation-1.31e+00

Pos logit contributions
 salon+0.058
aring+0.050
spe+0.046
Instead+0.044
ho+0.044
Neg logit contributions
CA-0.060
 emergencies-0.058
 steam-0.057
 sailors-0.057
 batteries-0.056
Token my
Token ID616
Feature activation-1.45e+00

Pos logit contributions
 salon+0.057
aring+0.051
 sad+0.041
Instead+0.041
 nine+0.039
Neg logit contributions
CA-0.094
rob-0.090
agons-0.085
unks-0.084
agles-0.084
Token brother
Token ID3956
Feature activation-8.40e-01

Pos logit contributions
 salon+0.096
aring+0.086
spe+0.081
Instead+0.081
 Sadly+0.076
Neg logit contributions
 steam-0.070
 emergencies-0.068
 sailors-0.068
 batteries-0.066
CA-0.064
Token and
Token ID290
Feature activation-4.14e-01

Pos logit contributions
 salon+0.064
aring+0.057
spe+0.053
Instead+0.052
ho+0.052
Neg logit contributions
CA-0.034
 emergencies-0.032
 steam-0.031
 sailors-0.030
 batteries-0.030
Token I
Token ID314
Feature activation-7.14e-01

Pos logit contributions
 salon+0.029
aring+0.026
spe+0.024
Instead+0.023
ho+0.023
Neg logit contributions
CA-0.019
 emergencies-0.018
 steam-0.018
 sailors-0.017
 lava-0.017
Token love
Token ID1842
Feature activation+8.28e-02

Pos logit contributions
 salon+0.043
aring+0.033
Instead+0.033
spe+0.031
ress+0.030
Neg logit contributions
 steam-0.038
CA-0.038
 emergencies-0.036
 sailors-0.036
 batteries-0.036
Token you
Token ID345
Feature activation-7.86e-01

Pos logit contributions
CA+0.004
 emergencies+0.003
 sailors+0.003
 steam+0.003
agons+0.003
Neg logit contributions
 salon-0.006
aring-0.005
ho-0.005
Instead-0.005
spe-0.005
Token okay
Token ID8788
Feature activation+1.28e-01

Pos logit contributions
 salon+0.027
aring+0.025
spe+0.022
Instead+0.022
ho+0.022
Neg logit contributions
CA-0.019
 emergencies-0.018
 steam-0.018
 lava-0.017
 sailors-0.017
Token."
Token ID526
Feature activation+4.88e-01

Pos logit contributions
CA+0.005
 emergencies+0.005
 steam+0.005
 lava+0.004
 sailors+0.004
Neg logit contributions
 salon-0.010
aring-0.009
spe-0.008
Instead-0.008
ho-0.008
Token
Token ID198
Feature activation+1.86e-01

Pos logit contributions
CA+0.028
 emergencies+0.027
 steam+0.026
 sailors+0.026
 lava+0.026
Neg logit contributions
 salon-0.028
aring-0.025
spe-0.022
Instead-0.022
ho-0.022
Token
Token ID198
Feature activation+4.63e-01

Pos logit contributions
 emergencies+0.012
CA+0.012
 lava+0.012
 sailors+0.012
 steam+0.012
Neg logit contributions
 salon-0.009
aring-0.008
Instead-0.008
 Even-0.007
 Sadly-0.007
TokenM
Token ID44
Feature activation+3.34e-01

Pos logit contributions
CA+0.023
 emergencies+0.022
 steam+0.021
 pans+0.020
 sailors+0.020
Neg logit contributions
 salon-0.031
aring-0.028
spe-0.025
ho-0.025
 pad-0.024
Tokenummy
Token ID13513
Feature activation-1.48e+00

Pos logit contributions
CA+0.017
 emergencies+0.016
 steam+0.016
 sailors+0.015
 lava+0.015
Neg logit contributions
 salon-0.022
aring-0.020
spe-0.018
Instead-0.018
ho-0.017
Token and
Token ID290
Feature activation+7.90e-02

Pos logit contributions
 salon+0.097
aring+0.088
spe+0.079
Instead+0.079
ho+0.075
Neg logit contributions
CA-0.073
 steam-0.072
 sailors-0.067
 lava-0.066
 emergencies-0.066
Token Daddy
Token ID26926
Feature activation-2.17e-01

Pos logit contributions
CA+0.003
 steam+0.002
 emergencies+0.002
 sailors+0.002
 lava+0.002
Neg logit contributions
 salon-0.007
aring-0.006
spe-0.006
Instead-0.006
ho-0.005
Token laughed
Token ID13818
Feature activation+5.16e-01

Pos logit contributions
 salon+0.015
aring+0.015
Instead+0.013
spe+0.013
 virtue+0.012
Neg logit contributions
 steam-0.009
 sailors-0.009
CA-0.008
pa-0.008
kins-0.008
Token and
Token ID290
Feature activation+2.25e-01

Pos logit contributions
CA+0.024
 emergencies+0.023
 steam+0.022
 sailors+0.021
 lava+0.021
Neg logit contributions
 salon-0.036
aring-0.033
spe-0.030
Instead-0.030
ho-0.029
Token hugged
Token ID41130
Feature activation+6.96e-01

Pos logit contributions
CA+0.011
 steam+0.011
 emergencies+0.010
 sailors+0.010
 lava+0.010
Neg logit contributions
 salon-0.015
aring-0.014
Instead-0.012
spe-0.012
ho-0.012
Token be
Token ID307
Feature activation-3.74e-01

Pos logit contributions
 salon+0.033
aring+0.031
spe+0.028
Instead+0.027
ho+0.026
Neg logit contributions
CA-0.030
 emergencies-0.029
 steam-0.029
 sailors-0.029
 batteries-0.027
Token his
Token ID465
Feature activation-7.08e-01

Pos logit contributions
 salon+0.021
aring+0.018
spe+0.016
 pad+0.015
Instead+0.015
Neg logit contributions
CA-0.023
 emergencies-0.021
rob-0.021
 lava-0.020
agons-0.020
Token wife
Token ID3656
Feature activation-1.32e+00

Pos logit contributions
 salon+0.043
aring+0.040
Instead+0.037
spe+0.036
ho+0.034
Neg logit contributions
 emergencies-0.037
 steam-0.036
 sailors-0.035
CA-0.035
 batteries-0.035
Token and
Token ID290
Feature activation-5.79e-01

Pos logit contributions
 salon+0.109
aring+0.103
ho+0.098
Instead+0.098
spe+0.095
Neg logit contributions
 sailors-0.037
kins-0.036
 emergencies-0.033
 batteries-0.033
 steam-0.033
Token Ben
Token ID3932
Feature activation-7.29e-01

Pos logit contributions
 salon+0.041
aring+0.039
Instead+0.035
spe+0.035
ho+0.034
Neg logit contributions
 emergencies-0.024
CA-0.024
 sailors-0.024
 steam-0.023
 batteries-0.023
Token's
Token ID338
Feature activation-1.48e+00

Pos logit contributions
 salon+0.067
aring+0.061
Instead+0.058
spe+0.058
ho+0.057
Neg logit contributions
 sailors-0.014
kins-0.014
 batteries-0.013
 emergencies-0.013
 steam-0.013
Token mom
Token ID1995
Feature activation-8.84e-01

Pos logit contributions
 salon+0.103
aring+0.097
Instead+0.091
spe+0.090
 Even+0.085
Neg logit contributions
 emergencies-0.063
CA-0.061
 steam-0.061
 sailors-0.060
 batteries-0.058
Token.
Token ID13
Feature activation-4.49e-01

Pos logit contributions
 salon+0.079
aring+0.073
Instead+0.070
spe+0.068
ho+0.067
Neg logit contributions
 sailors-0.019
kins-0.019
 steam-0.018
 emergencies-0.018
 batteries-0.018
Token He
Token ID679
Feature activation-4.64e-01

Pos logit contributions
 salon+0.030
aring+0.027
spe+0.025
ho+0.024
Instead+0.024
Neg logit contributions
CA-0.022
 emergencies-0.021
 steam-0.020
 sailors-0.020
 batteries-0.020
Token asked
Token ID1965
Feature activation-1.62e-01

Pos logit contributions
 salon+0.030
aring+0.027
spe+0.024
Instead+0.024
ho+0.024
Neg logit contributions
CA-0.024
 emergencies-0.023
 steam-0.022
 sailors-0.022
 batteries-0.021
Token Ben
Token ID3932
Feature activation-2.28e-01

Pos logit contributions
 salon+0.013
aring+0.012
spe+0.011
Instead+0.011
ho+0.011
Neg logit contributions
 emergencies-0.005
CA-0.005
 sailors-0.005
 steam-0.005
 batteries-0.005