TOP ACTIVATIONS
MAX = 4.570

They burst open in a million different colours and he was
v ase broke into a million pieces and they were very
pocket and broke into a million pieces . Tim my 's
. It broke into a million pieces . Tim
v ase shattered into a million pieces and the elderly lady
and it broke into a million pieces . L
The ornament broke into a million pieces and Lily felt really
and it broke into a million pieces . L
tooth had broken into a million pieces , and each piece
and it shattered into a million pieces . Lily 's mom
he found a rabbit qu arre lling with a squirrel .
and it broke into a million pieces . Her mom my
and it broke into a million pieces . Lily was very
and it broke into a million pieces . His mom my
She grabbed onto its handle bars and put her feet onto
and it broke into a million pieces . Tim my was
hive . Suddenly , a swarm of bees flew out of
. He grabbed the handle bars and he quickly pushed on
walked in on us qu arre ling and heard us .
and it shattered into a million pieces . Lily was so

MIN ACTIVATIONS
MIN = -5.473

much fun . " Whe e !" he shouted . From
happy and shouts " Whe e !" Uncle Tom laughs and
as the best joke - te ller around . <|endoftext|> Once
then said , " Whe e !" Tim my slid down
and shouts . " Whe e ! This is fun !"
down the slide . Whe e ! It was so much
and said , " Whe e ! This is fun !
and slide down . Whe e !" Tim slid
went to get more ice - cream . Spot was worried
was now happy and well - fed . From then on
She shouts , " Whe e !" Sam watches
and shouted , " Whe e !" L ily
he said , " Whe e !" The subway went under
on the grass . Whe e !" L ily
and slides down . Whe e ! They do
and slides down . Whe e ! " Wow
and Jack was the happiest oct opus in the whole ocean
and shouts , " Whe e ! This is fun !
and shouts , " Whe e ! That was fun !"
slides down . " Whe e !" she says . She

INTERVAL 2.060 - 4.570
CONTAINS 0.061%

how to polish the tw igs until they spark led like
The twins smiled in amaz ement . What an exciting
a time , in a small house , there lived a
a time , in an ordinary little town , there lived
the box wouldn 't bud ge . Just when he was

INTERVAL -0.451 - 2.060
CONTAINS 80.447%

I look at it ? â € Su zy asked .
so happy to find that the kitten was un har med
deaf and couldn 't hear very well . Lily was sad
to find a chocolate bar waiting for her ! The little
old scale . It weighed things from near and far ,

INTERVAL -2.962 - -0.451
CONTAINS 19.470%

the forest . As they were walking through the woods ,
He ran faster and faster and felt very powerful . He
proud of himself for using his sword . From then on
end , he was happy he did . The sunshine felt
it was so sm elly ! One day , someone had

INTERVAL -5.473 - -2.962
CONTAINS 0.023%

all kind of fun things - they ran , jumped and
play a game of tug - o - war .
calm and listen to grown - ups . The end .
She loved to play hide - and - seek with her
ara loves to play dress - up with her costumes .
Token They
Token ID1119
Feature activation-8.55e-01

Pos logit contributions
 Twe+0.007
 ot+0.007
 Nem+0.007
 le+0.006
Twe+0.006
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
rum-0.005
Token burst
Token ID11173
Feature activation+4.33e-01

Pos logit contributions
 Twe+0.022
 ot+0.022
 Nem+0.020
 le+0.020
Twe+0.020
Neg logit contributions
 outage-0.032
ouncing-0.031
hole-0.031
ying-0.030
 ma-0.029
Token open
Token ID1280
Feature activation+1.71e-01

Pos logit contributions
 outage+0.012
hole+0.012
ouncing+0.011
lessly+0.011
ying+0.011
Neg logit contributions
 Twe-0.015
Twe-0.015
 ot-0.014
 le-0.014
 Nem-0.014
Token in
Token ID287
Feature activation+1.22e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
ying+0.005
hole+0.005
 ma+0.004
Neg logit contributions
 Twe-0.006
 ot-0.006
 Nem-0.006
 le-0.005
Twe-0.005
Token a
Token ID257
Feature activation+4.08e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
 le-0.004
Twe-0.004
Token million
Token ID1510
Feature activation+4.57e+00

Pos logit contributions
ouncing+0.015
 outage+0.015
ying+0.014
hole+0.014
rum+0.014
Neg logit contributions
 Twe-0.011
 ot-0.011
 le-0.010
 Nem-0.010
Twe-0.010
Token different
Token ID1180
Feature activation+7.33e-01

Pos logit contributions
 outage+0.133
hole+0.128
ying+0.120
ouncing+0.119
lessly+0.119
Neg logit contributions
 Twe-0.161
Twe-0.153
 ot-0.152
 Nem-0.148
 le-0.143
Token colours
Token ID18915
Feature activation-5.67e-02

Pos logit contributions
 outage+0.023
hole+0.022
ouncing+0.022
ying+0.022
 ma+0.021
Neg logit contributions
 Twe-0.024
 ot-0.022
Twe-0.022
 Nem-0.022
 le-0.021
Token and
Token ID290
Feature activation-8.31e-01

Pos logit contributions
 Twe+0.002
 ot+0.002
 le+0.002
 Nem+0.002
Twe+0.001
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
ying-0.002
 ma-0.002
Token he
Token ID339
Feature activation-5.07e-01

Pos logit contributions
 Twe+0.024
 ot+0.023
Twe+0.022
 Nem+0.022
 le+0.021
Neg logit contributions
 outage-0.029
ouncing-0.028
hole-0.028
ying-0.027
 ma-0.027
Token was
Token ID373
Feature activation-9.58e-02

Pos logit contributions
 Twe+0.015
Twe+0.014
 ot+0.014
 Nem+0.014
 jew+0.013
Neg logit contributions
 outage-0.017
hole-0.016
ouncing-0.016
lessly-0.015
ows-0.015
Token v
Token ID410
Feature activation-1.30e+00

Pos logit contributions
 Twe+0.003
 Nem+0.003
Twe+0.003
 ot+0.003
 Bub+0.003
Neg logit contributions
 outage-0.004
 ma-0.004
hole-0.004
 click-0.004
ouncing-0.004
Tokenase
Token ID589
Feature activation+2.10e-01

Pos logit contributions
 Nem+0.056
 ot+0.055
 Twe+0.055
 jew+0.051
 Bub+0.051
Neg logit contributions
ouncing-0.031
 outage-0.028
ying-0.027
ows-0.026
hole-0.025
Token broke
Token ID6265
Feature activation+4.35e-01

Pos logit contributions
 outage+0.008
ouncing+0.008
hole+0.008
ying+0.008
 ma+0.008
Neg logit contributions
 Twe-0.005
 ot-0.005
 Nem-0.005
Twe-0.004
 le-0.004
Token into
Token ID656
Feature activation+3.18e-02

Pos logit contributions
 outage+0.012
ouncing+0.011
hole+0.011
ying+0.011
lessly+0.010
Neg logit contributions
 Twe-0.016
 ot-0.015
 Nem-0.015
Twe-0.015
 le-0.014
Token a
Token ID257
Feature activation+6.91e-01

Pos logit contributions
 outage+0.001
hole+0.001
ouncing+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
Twe-0.001
 le-0.001
Token million
Token ID1510
Feature activation+4.40e+00

Pos logit contributions
ouncing+0.019
ying+0.019
 outage+0.017
ows+0.017
hole+0.017
Neg logit contributions
 Twe-0.026
 ot-0.026
 le-0.025
 jew-0.024
Twe-0.024
Token pieces
Token ID5207
Feature activation+1.67e+00

Pos logit contributions
hole+0.111
 outage+0.106
rum+0.096
 instant+0.096
lessly+0.094
Neg logit contributions
 Twe-0.166
Twe-0.163
 Nem-0.161
 ot-0.161
 Bub-0.149
Token and
Token ID290
Feature activation-2.15e-01

Pos logit contributions
ouncing+0.062
 Deal+0.061
 outage+0.061
 Today+0.059
 ma+0.058
Neg logit contributions
 Twe-0.042
 ot-0.041
 le-0.039
 Nem-0.038
 se-0.037
Token they
Token ID484
Feature activation-4.07e-01

Pos logit contributions
 ot+0.006
 Twe+0.006
Twe+0.006
 Nem+0.006
 le+0.006
Neg logit contributions
 outage-0.007
hole-0.007
ouncing-0.007
 ma-0.006
lessly-0.006
Token were
Token ID547
Feature activation+3.03e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
Twe+0.011
 le+0.010
Neg logit contributions
 outage-0.014
hole-0.014
ouncing-0.014
ying-0.013
lessly-0.013
Token very
Token ID845
Feature activation-3.20e-01

Pos logit contributions
 outage+0.009
ouncing+0.009
ying+0.009
hole+0.009
 Today+0.008
Neg logit contributions
 Twe-0.011
 ot-0.010
 le-0.010
 Nem-0.009
Twe-0.009
Token pocket
Token ID10000
Feature activation+4.32e-01

Pos logit contributions
 outage+0.023
hole+0.022
ouncing+0.021
ying+0.020
 ma+0.020
Neg logit contributions
 Twe-0.041
 ot-0.039
Twe-0.038
 Nem-0.038
 le-0.038
Token and
Token ID290
Feature activation-2.27e-03

Pos logit contributions
 outage+0.015
ouncing+0.014
hole+0.014
ying+0.014
 ma+0.013
Neg logit contributions
 Twe-0.013
 ot-0.012
 Nem-0.012
 le-0.012
Twe-0.011
Token broke
Token ID6265
Feature activation+1.70e-01

Pos logit contributions
Twe+0.000
 Twe+0.000
 ot+0.000
 le+0.000
 Nem+0.000
Neg logit contributions
 outage-0.000
hole-0.000
 ma-0.000
ouncing-0.000
 click-0.000
Token into
Token ID656
Feature activation-1.22e-01

Pos logit contributions
hole+0.005
 outage+0.005
ying+0.005
rum+0.005
ouncing+0.004
Neg logit contributions
Twe-0.006
 ot-0.005
 Twe-0.005
 le-0.005
 jew-0.005
Token a
Token ID257
Feature activation+3.93e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.003
hole-0.003
rum-0.003
ouncing-0.003
lessly-0.003
Token million
Token ID1510
Feature activation+4.28e+00

Pos logit contributions
ouncing+0.012
ying+0.012
 outage+0.011
ows+0.011
hole+0.011
Neg logit contributions
 Twe-0.013
 ot-0.013
 le-0.013
 jew-0.013
 Nem-0.012
Token pieces
Token ID5207
Feature activation+1.23e+00

Pos logit contributions
hole+0.108
 outage+0.104
rum+0.099
ying+0.096
lessly+0.095
Neg logit contributions
 Twe-0.165
Twe-0.159
 ot-0.156
 Nem-0.151
 le-0.146
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
 outage+0.049
ouncing+0.049
hole+0.047
ying+0.047
 ma+0.047
Neg logit contributions
 Twe-0.028
 ot-0.027
 Nem-0.025
 le-0.025
Twe-0.024
Token Tim
Token ID5045
Feature activation+6.21e-01

Pos logit contributions
 Today+0.013
ouncing+0.013
 outage+0.013
 ma+0.013
 about+0.013
Neg logit contributions
 ot-0.011
 jew-0.011
 se-0.011
 le-0.010
 Twe-0.010
Tokenmy
Token ID1820
Feature activation+5.94e-01

Pos logit contributions
 outage+0.020
ying+0.018
ouncing+0.017
 ma+0.017
 Today+0.017
Neg logit contributions
 Twe-0.020
 ot-0.020
 le-0.019
 Nem-0.019
Twe-0.019
Token's
Token ID338
Feature activation+1.91e+00

Pos logit contributions
 outage+0.025
ouncing+0.024
hole+0.024
ying+0.024
 ma+0.023
Neg logit contributions
 Twe-0.013
 ot-0.013
 Nem-0.012
 le-0.012
Twe-0.011
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
 outage+0.007
ouncing+0.007
ying+0.007
hole+0.007
 ma+0.007
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.003
 le-0.003
Twe-0.003
Token It
Token ID632
Feature activation-1.38e+00

Pos logit contributions
 Twe+0.008
 ot+0.008
 Nem+0.007
 le+0.007
Twe+0.007
Neg logit contributions
 outage-0.007
ouncing-0.006
hole-0.006
ying-0.006
 ma-0.006
Token broke
Token ID6265
Feature activation+1.29e-01

Pos logit contributions
 ot+0.039
 Twe+0.039
 Nem+0.038
Twe+0.038
 jew+0.037
Neg logit contributions
 outage-0.046
hole-0.044
lessly-0.042
ouncing-0.042
 click-0.041
Token into
Token ID656
Feature activation-1.37e-01

Pos logit contributions
 outage+0.004
hole+0.004
ouncing+0.004
ying+0.004
lessly+0.004
Neg logit contributions
 Twe-0.004
 ot-0.004
Twe-0.004
 Nem-0.004
 le-0.004
Token a
Token ID257
Feature activation+6.40e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
Twe+0.004
 le+0.004
Neg logit contributions
 outage-0.004
ouncing-0.004
hole-0.004
ying-0.004
 ma-0.004
Token million
Token ID1510
Feature activation+4.23e+00

Pos logit contributions
ouncing+0.021
ying+0.021
ows+0.019
 outage+0.018
ems+0.018
Neg logit contributions
 le-0.022
 Twe-0.022
 ot-0.021
 se-0.021
 jew-0.020
Token pieces
Token ID5207
Feature activation+1.56e+00

Pos logit contributions
 outage+0.123
hole+0.121
ouncing+0.115
ying+0.115
rum+0.113
Neg logit contributions
 Twe-0.144
 ot-0.139
Twe-0.137
 Nem-0.134
 le-0.129
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
 Deal+0.070
ouncing+0.070
 ma+0.068
 outage+0.068
 Today+0.068
Neg logit contributions
 Twe-0.026
 ot-0.025
 le-0.025
 se-0.023
 Nem-0.022
Token
Token ID198
Feature activation-1.30e-02

Pos logit contributions
 Twe+0.003
 ot+0.003
 Nem+0.003
Twe+0.003
 le+0.003
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
Twe+0.000
 le+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
TokenTim
Token ID14967
Feature activation-6.61e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
 jew+0.000
Neg logit contributions
 outage-0.001
ouncing-0.001
hole-0.001
ying-0.001
rum-0.001
Token v
Token ID410
Feature activation-1.20e+00

Pos logit contributions
 Nem+0.001
 Twe+0.001
Twe+0.001
 ot+0.001
 Bub+0.001
Neg logit contributions
 outage-0.001
 ma-0.001
hole-0.001
 click-0.001
ouncing-0.001
Tokenase
Token ID589
Feature activation+2.61e-01

Pos logit contributions
 Nem+0.052
 ot+0.051
 Twe+0.051
 Bub+0.048
 le+0.046
Neg logit contributions
ouncing-0.029
 outage-0.026
ying-0.025
ows-0.024
apping-0.024
Token shattered
Token ID23273
Feature activation+1.01e+00

Pos logit contributions
 outage+0.010
ouncing+0.010
hole+0.010
ying+0.010
 ma+0.010
Neg logit contributions
 Twe-0.006
 ot-0.006
 Nem-0.006
Twe-0.006
 le-0.005
Token into
Token ID656
Feature activation-3.76e-01

Pos logit contributions
 outage+0.029
hole+0.029
ouncing+0.028
ying+0.028
lessly+0.027
Neg logit contributions
 Twe-0.034
 ot-0.033
Twe-0.032
 Nem-0.032
 le-0.031
Token a
Token ID257
Feature activation+3.76e-01

Pos logit contributions
 Twe+0.011
 ot+0.011
 Nem+0.011
Twe+0.010
 le+0.010
Neg logit contributions
 outage-0.012
hole-0.012
ouncing-0.012
 ma-0.011
ying-0.011
Token million
Token ID1510
Feature activation+4.13e+00

Pos logit contributions
ouncing+0.011
ying+0.011
 outage+0.010
ows+0.009
hole+0.009
Neg logit contributions
 le-0.014
 ot-0.014
 Twe-0.014
 se-0.013
 jew-0.013
Token pieces
Token ID5207
Feature activation+1.37e+00

Pos logit contributions
hole+0.112
 outage+0.110
lessly+0.101
 instant+0.099
rum+0.098
Neg logit contributions
 Twe-0.151
Twe-0.144
 ot-0.144
 Nem-0.142
 le-0.130
Token and
Token ID290
Feature activation-1.44e-01

Pos logit contributions
 Deal+0.048
ouncing+0.048
 outage+0.047
 ma+0.046
 Today+0.046
Neg logit contributions
 Twe-0.037
 ot-0.036
 le-0.036
 se-0.034
 Nem-0.034
Token the
Token ID262
Feature activation-6.95e-01

Pos logit contributions
 ot+0.004
Twe+0.004
 Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.005
 ma-0.004
hole-0.004
ouncing-0.004
lessly-0.004
Token elderly
Token ID13830
Feature activation-1.80e+00

Pos logit contributions
 Twe+0.021
 Nem+0.021
Twe+0.020
 ot+0.020
 Bub+0.018
Neg logit contributions
 ma-0.022
hole-0.021
 outage-0.021
 click-0.021
ouncing-0.020
Token lady
Token ID10846
Feature activation-8.57e-01

Pos logit contributions
 Nem+0.070
 ot+0.068
 Twe+0.068
Twe+0.067
 Bub+0.067
Neg logit contributions
 ma-0.042
ouncing-0.040
 outage-0.039
ying-0.037
 about-0.037
Token and
Token ID290
Feature activation-1.92e-01

Pos logit contributions
 outage+0.029
ouncing+0.028
ying+0.027
 ma+0.027
rum+0.027
Neg logit contributions
 Twe-0.032
 ot-0.031
 le-0.030
 Nem-0.028
Twe-0.028
Token it
Token ID340
Feature activation-1.20e-01

Pos logit contributions
 Twe+0.005
 ot+0.005
Twe+0.005
 Nem+0.005
 le+0.005
Neg logit contributions
 outage-0.006
ouncing-0.006
hole-0.006
 ma-0.006
ying-0.006
Token broke
Token ID6265
Feature activation-2.77e-03

Pos logit contributions
Twe+0.004
 ot+0.004
 Twe+0.004
 Nem+0.004
 jew+0.004
Neg logit contributions
 outage-0.003
hole-0.003
ouncing-0.003
lessly-0.003
ows-0.003
Token into
Token ID656
Feature activation-2.78e-01

Pos logit contributions
 ot+0.000
 Twe+0.000
Twe+0.000
 Nem+0.000
 le+0.000
Neg logit contributions
hole-0.000
 outage-0.000
ouncing-0.000
ying-0.000
lessly-0.000
Token a
Token ID257
Feature activation+4.27e-01

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.008
Twe+0.008
 le+0.008
Neg logit contributions
 outage-0.009
ouncing-0.009
hole-0.008
ying-0.008
 ma-0.008
Token million
Token ID1510
Feature activation+4.07e+00

Pos logit contributions
ying+0.014
ouncing+0.014
ows+0.012
 outage+0.012
ems+0.012
Neg logit contributions
 Twe-0.014
 ot-0.014
 le-0.014
 se-0.014
 jew-0.013
Token pieces
Token ID5207
Feature activation+1.19e+00

Pos logit contributions
hole+0.102
 outage+0.101
rum+0.094
lessly+0.091
ying+0.089
Neg logit contributions
 Twe-0.158
Twe-0.153
 ot-0.150
 Nem-0.147
 le-0.140
Token.
Token ID13
Feature activation+9.90e-02

Pos logit contributions
ouncing+0.053
 outage+0.052
 ma+0.051
 Deal+0.051
 Today+0.051
Neg logit contributions
 Twe-0.021
 ot-0.021
 le-0.019
 Nem-0.018
 se-0.017
Token
Token ID198
Feature activation+6.93e-02

Pos logit contributions
 outage+0.004
ouncing+0.004
hole+0.004
ying+0.003
rum+0.003
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.002
 le-0.002
Twe-0.002
Token
Token ID198
Feature activation+9.15e-02

Pos logit contributions
 outage+0.002
hole+0.002
ouncing+0.002
ying+0.002
 ma+0.002
Neg logit contributions
 Twe-0.002
Twe-0.002
 Nem-0.002
 ot-0.002
 le-0.002
TokenL
Token ID43
Feature activation+9.70e-02

Pos logit contributions
 outage+0.004
hole+0.004
ouncing+0.004
ying+0.004
ows+0.004
Neg logit contributions
 Twe-0.002
 ot-0.001
Twe-0.001
 le-0.001
 Nem-0.001
Token The
Token ID383
Feature activation+1.97e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
Twe+0.000
 le+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
Token ornament
Token ID45618
Feature activation+5.28e-01

Pos logit contributions
 outage+0.007
ouncing+0.007
ying+0.006
hole+0.006
ows+0.006
Neg logit contributions
 Twe-0.006
 ot-0.006
 le-0.005
 Nem-0.005
Twe-0.005
Token broke
Token ID6265
Feature activation+2.87e-01

Pos logit contributions
 outage+0.018
hole+0.018
ouncing+0.017
ying+0.017
lessly+0.016
Neg logit contributions
 Twe-0.015
 ot-0.015
 Nem-0.015
Twe-0.015
 jew-0.014
Token into
Token ID656
Feature activation-7.31e-02

Pos logit contributions
 outage+0.008
ouncing+0.008
hole+0.008
ying+0.008
 ma+0.007
Neg logit contributions
 Twe-0.010
 ot-0.010
 Nem-0.009
Twe-0.009
 le-0.009
Token a
Token ID257
Feature activation+7.42e-01

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
Twe+0.002
 le+0.002
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
ying-0.002
 ma-0.002
Token million
Token ID1510
Feature activation+4.07e+00

Pos logit contributions
ouncing+0.025
ying+0.024
ows+0.022
ems+0.022
 outage+0.022
Neg logit contributions
 Twe-0.025
 le-0.025
 ot-0.025
 se-0.024
 jew-0.024
Token pieces
Token ID5207
Feature activation+1.52e+00

Pos logit contributions
 outage+0.116
hole+0.115
ouncing+0.109
ying+0.108
rum+0.107
Neg logit contributions
 Twe-0.140
 ot-0.137
Twe-0.132
 Nem-0.131
 le-0.127
Token and
Token ID290
Feature activation-7.32e-02

Pos logit contributions
 Deal+0.055
ouncing+0.055
 outage+0.054
 ma+0.053
 Today+0.053
Neg logit contributions
 Twe-0.039
 ot-0.038
 le-0.038
 se-0.036
 Nem-0.035
Token Lily
Token ID20037
Feature activation-2.19e-01

Pos logit contributions
Twe+0.002
 ot+0.002
 Twe+0.002
 Nem+0.002
 jew+0.002
Neg logit contributions
 outage-0.002
hole-0.002
ouncing-0.002
 ma-0.002
lessly-0.002
Token felt
Token ID2936
Feature activation-2.37e-01

Pos logit contributions
 Twe+0.006
 ot+0.005
 Nem+0.005
 le+0.005
Twe+0.005
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.008
 ma-0.008
Token really
Token ID1107
Feature activation-5.77e-01

Pos logit contributions
 Twe+0.010
 ot+0.010
Twe+0.010
 Nem+0.009
 le+0.009
Neg logit contributions
 outage-0.005
lessly-0.004
 about-0.004
hole-0.004
ying-0.004
Token and
Token ID290
Feature activation-2.66e-01

Pos logit contributions
ouncing+0.023
 Deal+0.023
 outage+0.022
 ma+0.022
ying+0.022
Neg logit contributions
 Twe-0.018
 le-0.018
 ot-0.017
 se-0.017
 pl-0.015
Token it
Token ID340
Feature activation-3.06e-01

Pos logit contributions
 ot+0.009
Twe+0.009
 Twe+0.008
 Nem+0.008
 le+0.008
Neg logit contributions
 outage-0.007
hole-0.007
 ma-0.007
 click-0.007
ouncing-0.007
Token broke
Token ID6265
Feature activation-8.33e-02

Pos logit contributions
 ot+0.010
 Twe+0.010
Twe+0.010
 Nem+0.010
 jew+0.010
Neg logit contributions
 outage-0.009
hole-0.008
ouncing-0.008
lessly-0.008
ows-0.008
Token into
Token ID656
Feature activation-3.53e-01

Pos logit contributions
 ot+0.003
Twe+0.003
 Twe+0.003
 Nem+0.003
 le+0.003
Neg logit contributions
hole-0.002
 outage-0.002
lessly-0.002
ouncing-0.002
ying-0.002
Token a
Token ID257
Feature activation+3.22e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
Twe+0.011
 le+0.011
Neg logit contributions
 outage-0.011
hole-0.010
ouncing-0.010
ying-0.010
 ma-0.010
Token million
Token ID1510
Feature activation+4.06e+00

Pos logit contributions
ouncing+0.009
ying+0.008
 outage+0.008
ows+0.007
hole+0.007
Neg logit contributions
 Twe-0.012
 ot-0.012
 le-0.012
 jew-0.012
 se-0.012
Token pieces
Token ID5207
Feature activation+1.13e+00

Pos logit contributions
 outage+0.101
hole+0.100
rum+0.093
lessly+0.091
 instant+0.090
Neg logit contributions
 Twe-0.156
Twe-0.152
 ot-0.149
 Nem-0.146
 le-0.138
Token.
Token ID13
Feature activation+8.84e-02

Pos logit contributions
ouncing+0.050
 outage+0.049
 ma+0.048
 Deal+0.048
 Today+0.048
Neg logit contributions
 Twe-0.020
 ot-0.020
 le-0.019
 Nem-0.018
 se-0.017
Token
Token ID198
Feature activation-1.08e-02

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.002
ying+0.002
 ma+0.002
Neg logit contributions
 ot-0.003
 Twe-0.003
 Nem-0.003
 le-0.003
Twe-0.003
Token
Token ID198
Feature activation+5.55e-02

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
Twe+0.000
 le+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
TokenL
Token ID43
Feature activation+5.46e-02

Pos logit contributions
 outage+0.002
ouncing+0.002
hole+0.002
ying+0.002
 ma+0.002
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
 le-0.001
Twe-0.001
Token tooth
Token ID16162
Feature activation-8.23e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 le+0.003
 jew+0.003
 Nem+0.003
Neg logit contributions
 outage-0.004
ouncing-0.004
ying-0.004
hole-0.004
rum-0.004
Token had
Token ID550
Feature activation+1.57e-01

Pos logit contributions
 Twe+0.020
 ot+0.020
 le+0.019
 se+0.018
 Nem+0.018
Neg logit contributions
 outage-0.031
ouncing-0.031
ying-0.030
 Today-0.030
hole-0.030
Token broken
Token ID5445
Feature activation+5.67e-01

Pos logit contributions
 outage+0.005
hole+0.005
 ma+0.005
 about+0.005
lessly+0.005
Neg logit contributions
 Twe-0.005
 ot-0.005
Twe-0.005
 Nem-0.004
 le-0.004
Token into
Token ID656
Feature activation-4.49e-01

Pos logit contributions
 outage+0.019
ouncing+0.018
hole+0.018
ying+0.017
 ma+0.017
Neg logit contributions
 Twe-0.017
 ot-0.017
 Nem-0.016
Twe-0.016
 le-0.016
Token a
Token ID257
Feature activation+2.74e-01

Pos logit contributions
 Twe+0.013
 ot+0.013
Twe+0.012
 Nem+0.012
 le+0.012
Neg logit contributions
 outage-0.015
hole-0.015
ouncing-0.014
ying-0.014
rum-0.014
Token million
Token ID1510
Feature activation+3.92e+00

Pos logit contributions
ying+0.010
ouncing+0.010
ows+0.009
 outage+0.009
rum+0.009
Neg logit contributions
 Twe-0.008
 ot-0.008
 le-0.008
 se-0.007
 jew-0.007
Token pieces
Token ID5207
Feature activation+1.21e+00

Pos logit contributions
hole+0.108
 outage+0.108
rum+0.099
lessly+0.097
ouncing+0.097
Neg logit contributions
 Twe-0.141
 ot-0.135
Twe-0.135
 Nem-0.132
 le-0.123
Token,
Token ID11
Feature activation-3.32e-01

Pos logit contributions
ouncing+0.046
 Deal+0.045
 outage+0.045
 ma+0.045
 Today+0.044
Neg logit contributions
 ot-0.029
 Twe-0.028
 le-0.027
 Nem-0.026
 se-0.025
Token and
Token ID290
Feature activation+5.73e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 le+0.011
 Nem+0.010
 se+0.010
Neg logit contributions
 outage-0.010
ying-0.010
ouncing-0.010
rum-0.009
 Today-0.009
Token each
Token ID1123
Feature activation-9.08e-01

Pos logit contributions
 outage+0.021
ouncing+0.021
hole+0.020
ying+0.020
rum+0.019
Neg logit contributions
 Twe-0.016
 ot-0.015
 Nem-0.014
 le-0.014
Twe-0.014
Token piece
Token ID3704
Feature activation-7.80e-01

Pos logit contributions
 Twe+0.025
 ot+0.024
 le+0.023
 Nem+0.023
Twe+0.022
Neg logit contributions
ouncing-0.033
 outage-0.032
ying-0.031
hole-0.031
 ma-0.030
Token and
Token ID290
Feature activation-2.12e-01

Pos logit contributions
ouncing+0.020
 outage+0.020
 Deal+0.020
 ma+0.019
ying+0.019
Neg logit contributions
 Twe-0.016
 le-0.015
 ot-0.015
 se-0.014
Twe-0.013
Token it
Token ID340
Feature activation-2.06e-01

Pos logit contributions
 ot+0.007
Twe+0.007
 Twe+0.006
 jew+0.006
 Nem+0.006
Neg logit contributions
 outage-0.006
 ma-0.006
 click-0.006
ouncing-0.005
lessly-0.005
Token shattered
Token ID23273
Feature activation+4.87e-01

Pos logit contributions
 ot+0.007
 Nem+0.007
Twe+0.007
 Twe+0.007
 jew+0.007
Neg logit contributions
hole-0.005
 outage-0.005
ouncing-0.005
lessly-0.005
 click-0.005
Token into
Token ID656
Feature activation-7.86e-01

Pos logit contributions
hole+0.013
 outage+0.012
lessly+0.012
ouncing+0.012
ying+0.011
Neg logit contributions
Twe-0.018
 Twe-0.017
 ot-0.017
 Nem-0.017
 jew-0.016
Token a
Token ID257
Feature activation+2.16e-01

Pos logit contributions
 Twe+0.024
 ot+0.023
Twe+0.022
 Nem+0.022
 le+0.021
Neg logit contributions
 outage-0.026
hole-0.025
ouncing-0.024
 ma-0.024
rum-0.024
Token million
Token ID1510
Feature activation+3.89e+00

Pos logit contributions
ouncing+0.006
ying+0.006
 outage+0.005
ows+0.005
ems+0.005
Neg logit contributions
 Twe-0.008
 le-0.008
 ot-0.008
 se-0.008
 jew-0.008
Token pieces
Token ID5207
Feature activation+1.01e+00

Pos logit contributions
hole+0.094
 outage+0.094
rum+0.087
 instant+0.084
lessly+0.082
Neg logit contributions
 Twe-0.148
Twe-0.146
 Nem-0.144
 ot-0.143
 Bub-0.135
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
ouncing+0.043
 outage+0.042
 ma+0.042
 Deal+0.042
 Today+0.041
Neg logit contributions
 Twe-0.019
 ot-0.019
 le-0.018
 Nem-0.017
 se-0.016
Token Lily
Token ID20037
Feature activation+3.53e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
Twe+0.000
Neg logit contributions
 outage-0.001
hole-0.001
ouncing-0.001
ying-0.000
rum-0.000
Token's
Token ID338
Feature activation+1.79e+00

Pos logit contributions
 outage+0.016
ying+0.015
ouncing+0.015
hole+0.015
 Today+0.014
Neg logit contributions
 Twe-0.007
 ot-0.007
 le-0.007
Twe-0.006
 Nem-0.006
Token mom
Token ID1995
Feature activation-1.20e-01

Pos logit contributions
ouncing+0.049
 outage+0.049
hole+0.048
 ma+0.046
ows+0.046
Neg logit contributions
 Nem-0.061
 Twe-0.060
Twe-0.057
 ot-0.057
 jew-0.055
Token he
Token ID339
Feature activation-7.49e-03

Pos logit contributions
 outage+0.007
hole+0.006
ying+0.006
ouncing+0.006
 Today+0.006
Neg logit contributions
Twe-0.009
 Twe-0.009
 ot-0.009
 le-0.009
 jew-0.009
Token found
Token ID1043
Feature activation-3.63e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
Twe+0.000
 Nem+0.000
 jew+0.000
Neg logit contributions
hole-0.000
ouncing-0.000
 ma-0.000
 outage-0.000
 about-0.000
Token a
Token ID257
Feature activation+1.76e-01

Pos logit contributions
Twe+0.012
 Twe+0.011
 ot+0.010
 arom+0.010
 Nem+0.010
Neg logit contributions
 about-0.011
hole-0.011
lessly-0.010
ying-0.010
 outage-0.010
Token rabbit
Token ID22746
Feature activation+7.50e-01

Pos logit contributions
ouncing+0.007
 outage+0.006
ying+0.006
hole+0.006
rum+0.006
Neg logit contributions
 Twe-0.005
 ot-0.005
 le-0.004
 Nem-0.004
Twe-0.004
Token qu
Token ID627
Feature activation-2.18e-01

Pos logit contributions
 outage+0.024
ouncing+0.023
hole+0.023
ying+0.022
 ma+0.021
Neg logit contributions
 Twe-0.024
 ot-0.023
 Nem-0.022
Twe-0.022
 le-0.022
Tokenarre
Token ID9624
Feature activation+3.85e+00

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.009
 le+0.009
Twe+0.008
Neg logit contributions
ouncing-0.005
 outage-0.005
hole-0.004
ying-0.004
lessly-0.004
Tokenlling
Token ID2680
Feature activation+1.11e+00

Pos logit contributions
ouncing+0.119
 ma+0.118
 Deal+0.118
 outage+0.118
 Today+0.117
Neg logit contributions
 ot-0.124
 Twe-0.118
 Nem-0.112
 le-0.112
 se-0.111
Token with
Token ID351
Feature activation-1.15e+00

Pos logit contributions
 outage+0.036
ouncing+0.035
hole+0.034
ying+0.034
 ma+0.033
Neg logit contributions
 Twe-0.034
 ot-0.034
 Nem-0.032
 le-0.032
Twe-0.030
Token a
Token ID257
Feature activation-4.25e-01

Pos logit contributions
Twe+0.038
 Twe+0.034
 ot+0.034
pre+0.033
 host+0.031
Neg logit contributions
 about-0.030
 click-0.030
lessly-0.029
 grin-0.029
 instant-0.029
Token squirrel
Token ID33039
Feature activation+4.09e-01

Pos logit contributions
 Twe+0.012
 ot+0.012
 le+0.011
 Nem+0.011
Twe+0.010
Neg logit contributions
ying-0.016
ouncing-0.015
 outage-0.015
hole-0.015
rum-0.014
Token.
Token ID13
Feature activation+8.18e-02

Pos logit contributions
 outage+0.014
ouncing+0.014
hole+0.014
ying+0.013
rum+0.013
Neg logit contributions
 Twe-0.012
 ot-0.011
 Nem-0.011
Twe-0.011
 jew-0.010
Token and
Token ID290
Feature activation-2.45e-01

Pos logit contributions
 ot+0.016
 Twe+0.015
 le+0.015
 se+0.015
 Nem+0.015
Neg logit contributions
ouncing-0.016
 outage-0.015
 Today-0.014
 ma-0.014
rum-0.014
Token it
Token ID340
Feature activation-1.76e-01

Pos logit contributions
 ot+0.008
Twe+0.007
 Twe+0.007
 Nem+0.007
 le+0.007
Neg logit contributions
 outage-0.007
hole-0.007
ouncing-0.007
 ma-0.007
ying-0.007
Token broke
Token ID6265
Feature activation-1.13e-01

Pos logit contributions
Twe+0.006
 Twe+0.006
 ot+0.006
 Nem+0.006
 jew+0.006
Neg logit contributions
 outage-0.005
hole-0.005
ouncing-0.005
lessly-0.004
ying-0.004
Token into
Token ID656
Feature activation-3.72e-01

Pos logit contributions
 ot+0.004
 Twe+0.004
Twe+0.004
 Nem+0.003
 le+0.003
Neg logit contributions
hole-0.003
 outage-0.003
lessly-0.003
ouncing-0.003
ying-0.003
Token a
Token ID257
Feature activation+3.80e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
Twe+0.011
 le+0.010
Neg logit contributions
 outage-0.012
ouncing-0.011
hole-0.011
ying-0.011
 ma-0.011
Token million
Token ID1510
Feature activation+3.83e+00

Pos logit contributions
ouncing+0.011
ying+0.011
 outage+0.010
hole+0.010
ows+0.010
Neg logit contributions
 ot-0.014
 Twe-0.013
 le-0.013
 se-0.013
 Nem-0.013
Token pieces
Token ID5207
Feature activation+1.06e+00

Pos logit contributions
 outage+0.097
hole+0.094
rum+0.091
lessly+0.090
ying+0.090
Neg logit contributions
 Twe-0.147
Twe-0.144
 ot-0.136
 Nem-0.130
 le-0.128
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
ouncing+0.046
 outage+0.045
 ma+0.044
 Deal+0.044
 Today+0.044
Neg logit contributions
 Twe-0.020
 ot-0.020
 le-0.019
 Nem-0.018
 se-0.017
Token Her
Token ID2332
Feature activation+5.82e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 ot-0.005
 Twe-0.005
 Nem-0.004
Twe-0.004
 le-0.004
Token mom
Token ID1995
Feature activation+9.25e-03

Pos logit contributions
 outage+0.017
ouncing+0.016
 ma+0.016
hole+0.015
ying+0.015
Neg logit contributions
 Twe-0.020
Twe-0.020
 ot-0.018
 Nem-0.018
 Bub-0.017
Tokenmy
Token ID1820
Feature activation+6.81e-01

Pos logit contributions
 outage+0.000
 Today+0.000
ying+0.000
 ma+0.000
ouncing+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 le-0.000
 se-0.000
Twe-0.000
Token and
Token ID290
Feature activation+1.66e-01

Pos logit contributions
 outage+0.032
hole+0.032
ying+0.030
 ma+0.030
ouncing+0.029
Neg logit contributions
 ot-0.038
Twe-0.037
 Twe-0.037
 Nem-0.035
 le-0.034
Token it
Token ID340
Feature activation+1.72e-01

Pos logit contributions
 outage+0.006
ouncing+0.006
hole+0.005
ying+0.005
 ma+0.005
Neg logit contributions
 Twe-0.005
 ot-0.005
 Nem-0.004
 le-0.004
Twe-0.004
Token broke
Token ID6265
Feature activation-6.16e-02

Pos logit contributions
 outage+0.005
hole+0.005
ouncing+0.005
ows+0.005
lessly+0.005
Neg logit contributions
 ot-0.006
 Twe-0.005
 Nem-0.005
Twe-0.005
 jew-0.005
Token into
Token ID656
Feature activation-3.94e-01

Pos logit contributions
 ot+0.002
 Twe+0.002
Twe+0.002
 Nem+0.002
 le+0.002
Neg logit contributions
hole-0.002
 outage-0.002
ouncing-0.002
lessly-0.002
ying-0.002
Token a
Token ID257
Feature activation+4.46e-01

Pos logit contributions
 Twe+0.013
 ot+0.012
 Nem+0.012
Twe+0.012
 le+0.011
Neg logit contributions
 outage-0.012
hole-0.012
ouncing-0.012
ying-0.011
 ma-0.011
Token million
Token ID1510
Feature activation+3.81e+00

Pos logit contributions
ouncing+0.013
ying+0.012
ows+0.011
ems+0.011
 outage+0.010
Neg logit contributions
 Twe-0.017
 ot-0.017
 le-0.017
 se-0.016
 jew-0.016
Token pieces
Token ID5207
Feature activation+1.11e+00

Pos logit contributions
 outage+0.109
hole+0.105
ouncing+0.099
ying+0.099
rum+0.098
Neg logit contributions
 Twe-0.135
 ot-0.131
Twe-0.129
 Nem-0.127
 le-0.122
Token.
Token ID13
Feature activation+1.34e-01

Pos logit contributions
ouncing+0.048
 outage+0.047
 ma+0.046
 Today+0.046
 Deal+0.045
Neg logit contributions
 Twe-0.022
 ot-0.021
 le-0.020
 Nem-0.019
 se-0.018
Token Lily
Token ID20037
Feature activation+4.21e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
hole+0.004
ying+0.004
rum+0.004
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
Twe-0.004
 le-0.004
Token was
Token ID373
Feature activation+7.34e-01

Pos logit contributions
 outage+0.019
ying+0.019
ouncing+0.019
 Today+0.018
hole+0.018
Neg logit contributions
 Twe-0.008
 ot-0.007
 le-0.007
 Nem-0.006
Twe-0.006
Token very
Token ID845
Feature activation+8.58e-01

Pos logit contributions
ouncing+0.026
ems+0.025
 outage+0.025
ying+0.024
 Today+0.024
Neg logit contributions
 Twe-0.023
 ot-0.021
 le-0.021
 Nem-0.020
 se-0.019
Token and
Token ID290
Feature activation-9.22e-02

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.008
ying+0.008
 ma+0.008
Neg logit contributions
 Twe-0.008
 ot-0.008
 Nem-0.008
 le-0.007
Twe-0.007
Token it
Token ID340
Feature activation-5.00e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 Nem+0.002
Twe+0.002
 le+0.002
Neg logit contributions
 outage-0.003
ouncing-0.003
hole-0.003
ying-0.003
 ma-0.003
Token broke
Token ID6265
Feature activation-2.14e-03

Pos logit contributions
Twe+0.015
 Twe+0.015
 ot+0.015
 Nem+0.014
 jew+0.014
Neg logit contributions
 outage-0.015
hole-0.015
ouncing-0.015
 about-0.014
ows-0.014
Token into
Token ID656
Feature activation-2.98e-01

Pos logit contributions
 ot+0.000
Twe+0.000
 Twe+0.000
 Nem+0.000
 le+0.000
Neg logit contributions
hole-0.000
 outage-0.000
lessly-0.000
rum-0.000
ouncing-0.000
Token a
Token ID257
Feature activation+2.93e-01

Pos logit contributions
 Twe+0.010
 ot+0.010
 Nem+0.009
Twe+0.009
 le+0.009
Neg logit contributions
 outage-0.009
hole-0.009
ouncing-0.008
rum-0.008
ying-0.008
Token million
Token ID1510
Feature activation+3.77e+00

Pos logit contributions
ouncing+0.009
ying+0.009
 outage+0.008
ows+0.008
hole+0.008
Neg logit contributions
 Twe-0.010
 ot-0.010
 le-0.010
 jew-0.010
Twe-0.010
Token pieces
Token ID5207
Feature activation+1.02e+00

Pos logit contributions
hole+0.094
 outage+0.088
 instant+0.084
rum+0.084
lessly+0.081
Neg logit contributions
 Twe-0.145
Twe-0.140
 ot-0.139
 Nem-0.136
 Bub-0.129
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
 outage+0.041
ouncing+0.041
ying+0.040
hole+0.039
 ma+0.039
Neg logit contributions
 Twe-0.022
 ot-0.022
 Nem-0.020
 le-0.020
Twe-0.019
Token His
Token ID2399
Feature activation+1.67e-01

Pos logit contributions
ouncing+0.006
 Today+0.005
 outage+0.005
 ma+0.005
hole+0.005
Neg logit contributions
 ot-0.007
 Twe-0.006
 le-0.006
 jew-0.006
Twe-0.006
Token mom
Token ID1995
Feature activation-7.78e-02

Pos logit contributions
ouncing+0.005
 outage+0.005
 ma+0.005
hole+0.005
 grin+0.005
Neg logit contributions
 Twe-0.005
Twe-0.005
 ot-0.005
 Nem-0.005
 le-0.005
Tokenmy
Token ID1820
Feature activation+6.54e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 le+0.003
Twe+0.003
 se+0.003
Neg logit contributions
 outage-0.002
ying-0.002
 Today-0.002
ouncing-0.002
 ma-0.002
Token She
Token ID1375
Feature activation-4.55e-01

Pos logit contributions
 Twe+0.006
 ot+0.005
 Nem+0.005
 le+0.005
Twe+0.005
Neg logit contributions
 outage-0.003
hole-0.003
ying-0.003
ouncing-0.002
rum-0.002
Token grabbed
Token ID13176
Feature activation+1.66e-01

Pos logit contributions
 Twe+0.014
 ot+0.014
Twe+0.013
 Nem+0.013
 jew+0.012
Neg logit contributions
ouncing-0.014
hole-0.014
 outage-0.014
 ma-0.014
ying-0.013
Token onto
Token ID4291
Feature activation+4.88e-01

Pos logit contributions
hole+0.005
 onwards+0.005
 about+0.005
ying+0.005
 click+0.005
Neg logit contributions
Twe-0.005
 ot-0.005
 Twe-0.005
 Nem-0.005
 jew-0.004
Token its
Token ID663
Feature activation-3.89e-01

Pos logit contributions
 click+0.012
hole+0.011
 about+0.011
 ma+0.011
 Today+0.011
Neg logit contributions
 ot-0.017
Twe-0.017
 Nem-0.016
 jew-0.015
mer-0.015
Token handle
Token ID5412
Feature activation+1.15e+00

Pos logit contributions
 Twe+0.013
 ot+0.012
 Nem+0.012
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.012
ouncing-0.012
hole-0.011
ying-0.011
 ma-0.011
Tokenbars
Token ID34046
Feature activation+3.69e+00

Pos logit contributions
 outage+0.037
 Deal+0.037
rum+0.036
ouncing+0.035
 Promise+0.035
Neg logit contributions
 Twe-0.034
 le-0.032
 ot-0.032
 se-0.030
 Nem-0.029
Token and
Token ID290
Feature activation-2.07e-01

Pos logit contributions
 outage+0.121
 Deal+0.116
ouncing+0.115
ying+0.114
 ma+0.114
Neg logit contributions
 Twe-0.114
 ot-0.103
 le-0.101
Twe-0.097
 se-0.095
Token put
Token ID1234
Feature activation-3.70e-02

Pos logit contributions
 Twe+0.005
 ot+0.005
Twe+0.005
 Nem+0.005
 le+0.005
Neg logit contributions
 outage-0.008
hole-0.008
ouncing-0.008
ying-0.007
 ma-0.007
Token her
Token ID607
Feature activation-1.10e-01

Pos logit contributions
 ot+0.002
 Twe+0.002
Twe+0.002
 Nem+0.002
 le+0.002
Neg logit contributions
hole-0.001
 outage-0.001
ouncing-0.001
ying-0.001
lessly-0.001
Token feet
Token ID3625
Feature activation-5.43e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
 le+0.004
Twe+0.003
Neg logit contributions
 outage-0.003
ouncing-0.003
ying-0.003
hole-0.003
 ma-0.003
Token onto
Token ID4291
Feature activation+5.80e-02

Pos logit contributions
 Twe+0.022
 ot+0.021
 Nem+0.021
 le+0.021
Twe+0.020
Neg logit contributions
 outage-0.012
ouncing-0.012
ying-0.011
hole-0.011
 ma-0.011
Token and
Token ID290
Feature activation-1.67e-01

Pos logit contributions
ouncing+0.044
 outage+0.043
 ma+0.042
ying+0.042
 Deal+0.041
Neg logit contributions
 Twe-0.024
 ot-0.024
 le-0.023
 Nem-0.021
 se-0.020
Token it
Token ID340
Feature activation-4.17e-02

Pos logit contributions
 Twe+0.005
 ot+0.005
Twe+0.005
 Nem+0.005
 le+0.005
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token broke
Token ID6265
Feature activation-1.15e-01

Pos logit contributions
 ot+0.001
Twe+0.001
 Twe+0.001
 Nem+0.001
 jew+0.001
Neg logit contributions
hole-0.001
 outage-0.001
lessly-0.001
 falls-0.001
ouncing-0.001
Token into
Token ID656
Feature activation-4.27e-01

Pos logit contributions
 ot+0.004
Twe+0.004
 Twe+0.004
 Nem+0.003
 jew+0.003
Neg logit contributions
hole-0.004
 outage-0.003
lessly-0.003
rum-0.003
ouncing-0.003
Token a
Token ID257
Feature activation+3.79e-01

Pos logit contributions
 Twe+0.014
 ot+0.014
Twe+0.014
 Nem+0.013
 le+0.013
Neg logit contributions
 outage-0.012
hole-0.012
rum-0.012
ouncing-0.012
 ma-0.011
Token million
Token ID1510
Feature activation+3.69e+00

Pos logit contributions
ouncing+0.011
ying+0.010
ows+0.009
 outage+0.009
ems+0.009
Neg logit contributions
 Twe-0.014
 le-0.014
 ot-0.014
 se-0.014
 jew-0.013
Token pieces
Token ID5207
Feature activation+9.15e-01

Pos logit contributions
 outage+0.095
hole+0.094
rum+0.089
ying+0.086
lessly+0.085
Neg logit contributions
 Twe-0.139
Twe-0.135
 ot-0.134
 Nem-0.130
 le-0.124
Token.
Token ID13
Feature activation-3.39e-02

Pos logit contributions
ouncing+0.040
 outage+0.039
 ma+0.038
 Today+0.038
ying+0.038
Neg logit contributions
 Twe-0.017
 ot-0.017
 le-0.016
 Nem-0.015
Twe-0.014
Token Tim
Token ID5045
Feature activation+5.52e-01

Pos logit contributions
 ot+0.001
 Twe+0.001
 jew+0.001
 le+0.001
Twe+0.001
Neg logit contributions
 outage-0.001
ouncing-0.001
 Today-0.001
hole-0.001
 ma-0.001
Tokenmy
Token ID1820
Feature activation+5.49e-01

Pos logit contributions
 outage+0.020
 ma+0.018
ying+0.018
 click+0.018
 onwards+0.018
Neg logit contributions
 Twe-0.015
 ot-0.015
 le-0.014
B-0.014
 Nem-0.013
Token was
Token ID373
Feature activation+5.40e-01

Pos logit contributions
 outage+0.025
ouncing+0.024
ying+0.024
hole+0.024
 Today+0.023
Neg logit contributions
 Twe-0.011
 ot-0.010
 le-0.010
 Nem-0.009
Twe-0.009
Token hive
Token ID35881
Feature activation+1.19e+00

Pos logit contributions
 outage+0.015
ouncing+0.015
hole+0.014
ying+0.014
 ma+0.013
Neg logit contributions
 Twe-0.020
 ot-0.019
 Nem-0.018
 le-0.018
Twe-0.018
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
 outage+0.052
ouncing+0.052
ying+0.050
hole+0.050
rum+0.049
Neg logit contributions
 Twe-0.022
 ot-0.021
 le-0.020
 Nem-0.019
 jew-0.018
Token Suddenly
Token ID24975
Feature activation+1.40e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
 le+0.004
Twe+0.004
Neg logit contributions
 outage-0.005
hole-0.004
ouncing-0.004
ying-0.004
rum-0.004
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
ying+0.004
hole+0.004
 ma+0.004
Neg logit contributions
 Twe-0.005
 ot-0.005
Twe-0.005
 Nem-0.005
 le-0.004
Token a
Token ID257
Feature activation-1.95e-01

Pos logit contributions
 outage+0.003
ying+0.003
ouncing+0.003
 ma+0.003
hole+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
Twe-0.004
 le-0.003
 Nem-0.003
Token swarm
Token ID30077
Feature activation+3.66e+00

Pos logit contributions
 Twe+0.006
 ot+0.005
 le+0.005
 Nem+0.005
Twe+0.005
Neg logit contributions
 outage-0.007
ouncing-0.007
hole-0.007
ying-0.007
rum-0.006
Token of
Token ID286
Feature activation-8.08e-01

Pos logit contributions
ouncing+0.114
 outage+0.113
hole+0.106
 ma+0.104
rum+0.103
Neg logit contributions
 ot-0.122
 Twe-0.116
 le-0.115
 Nem-0.110
 se-0.109
Token bees
Token ID17002
Feature activation+1.00e+00

Pos logit contributions
 Twe+0.028
 ot+0.026
 Nem+0.026
Twe+0.025
 le+0.025
Neg logit contributions
 outage-0.024
ouncing-0.023
ying-0.022
hole-0.022
 ma-0.021
Token flew
Token ID13112
Feature activation+8.04e-01

Pos logit contributions
 outage+0.037
ouncing+0.036
hole+0.035
ying+0.035
 ma+0.034
Neg logit contributions
 Twe-0.027
 ot-0.026
 Nem-0.024
 le-0.024
Twe-0.024
Token out
Token ID503
Feature activation-1.73e-01

Pos logit contributions
 outage+0.019
ouncing+0.019
hole+0.018
ying+0.018
lessly+0.017
Neg logit contributions
 Twe-0.031
 ot-0.030
 Nem-0.030
Twe-0.030
 jew-0.029
Token of
Token ID286
Feature activation-7.88e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
 le+0.005
 Nem+0.005
 se+0.005
Neg logit contributions
ouncing-0.005
 outage-0.005
hole-0.005
ying-0.005
 ma-0.005
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
 outage+0.026
ouncing+0.026
ying+0.025
hole+0.025
 ma+0.025
Neg logit contributions
 Twe-0.015
 ot-0.014
 le-0.013
 Nem-0.013
Twe-0.013
Token He
Token ID679
Feature activation-5.87e-01

Pos logit contributions
 Nem+0.010
 Twe+0.010
 ot+0.010
 le+0.009
 Bub+0.009
Neg logit contributions
 outage-0.009
hole-0.009
ouncing-0.009
ying-0.008
rum-0.008
Token grabbed
Token ID13176
Feature activation+2.70e-01

Pos logit contributions
 Twe+0.016
 ot+0.016
Twe+0.014
 Nem+0.014
 le+0.014
Neg logit contributions
 outage-0.021
ouncing-0.021
hole-0.021
ying-0.020
 ma-0.020
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
 outage+0.010
hole+0.009
ouncing+0.009
ying+0.009
 ma+0.009
Neg logit contributions
 Twe-0.007
 ot-0.007
Twe-0.007
 Nem-0.007
 le-0.006
Token handle
Token ID5412
Feature activation+7.91e-01

Pos logit contributions
 outage+0.030
ouncing+0.030
ying+0.029
rum+0.027
ows+0.027
Neg logit contributions
 Twe-0.042
 ot-0.041
 le-0.040
 Nem-0.038
 jew-0.038
Tokenbars
Token ID34046
Feature activation+3.66e+00

Pos logit contributions
 outage+0.023
 Deal+0.023
ouncing+0.022
rum+0.022
ems+0.022
Neg logit contributions
 Twe-0.026
 ot-0.025
 le-0.025
 se-0.023
 Nem-0.023
Token and
Token ID290
Feature activation-1.43e-01

Pos logit contributions
 outage+0.114
ouncing+0.109
ying+0.107
 Deal+0.107
 ma+0.105
Neg logit contributions
 Twe-0.119
 ot-0.113
 le-0.111
 Nem-0.105
 se-0.104
Token he
Token ID339
Feature activation-3.73e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
Twe+0.004
 le+0.003
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token quickly
Token ID2952
Feature activation-5.10e-01

Pos logit contributions
 Twe+0.011
 ot+0.011
Twe+0.010
 Nem+0.010
 le+0.010
Neg logit contributions
hole-0.012
 outage-0.012
ouncing-0.012
ying-0.011
 ma-0.011
Token pushed
Token ID7121
Feature activation+7.46e-02

Pos logit contributions
 Twe+0.016
 ot+0.015
Twe+0.015
 Nem+0.015
 le+0.014
Neg logit contributions
hole-0.016
 outage-0.016
ouncing-0.016
 ma-0.015
lessly-0.015
Token on
Token ID319
Feature activation+7.37e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.002
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002
Token walked
Token ID6807
Feature activation-4.26e-02

Pos logit contributions
 outage+0.015
ouncing+0.015
ying+0.015
hole+0.015
 ma+0.014
Neg logit contributions
 Twe-0.012
 ot-0.012
 Nem-0.011
 le-0.011
Twe-0.011
Token in
Token ID287
Feature activation-7.44e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
 le+0.001
Twe+0.001
Neg logit contributions
 outage-0.001
ouncing-0.001
hole-0.001
ying-0.001
 ma-0.001
Token on
Token ID319
Feature activation+9.42e-01

Pos logit contributions
 Twe+0.016
 ot+0.014
 le+0.014
 Nem+0.014
 jew+0.013
Neg logit contributions
ouncing-0.034
ying-0.032
 outage-0.030
itates-0.030
ows-0.030
Token us
Token ID514
Feature activation+8.76e-02

Pos logit contributions
 outage+0.034
hole+0.033
ouncing+0.032
 ma+0.032
ying+0.032
Neg logit contributions
 Twe-0.025
 ot-0.024
Twe-0.023
 Nem-0.023
 le-0.022
Token qu
Token ID627
Feature activation-9.10e-02

Pos logit contributions
ouncing+0.004
 outage+0.004
ying+0.004
 ma+0.003
irk+0.003
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
 Bub-0.001
Tokenarre
Token ID9624
Feature activation+3.61e+00

Pos logit contributions
 Twe+0.005
 ot+0.005
 Nem+0.005
 le+0.005
Twe+0.004
Neg logit contributions
 outage-0.001
ouncing-0.001
hole-0.001
ying-0.001
 ma-0.001
Tokenling
Token ID1359
Feature activation+8.61e-01

Pos logit contributions
 Today+0.123
 outage+0.120
 ma+0.119
ouncing+0.119
 Deal+0.118
Neg logit contributions
 ot-0.102
 Twe-0.093
 Nem-0.092
 se-0.091
 le-0.089
Token and
Token ID290
Feature activation-5.38e-01

Pos logit contributions
 outage+0.030
ouncing+0.029
hole+0.028
ying+0.028
 ma+0.027
Neg logit contributions
 Twe-0.025
 ot-0.024
 Nem-0.023
 le-0.023
Twe-0.022
Token heard
Token ID2982
Feature activation+1.52e-01

Pos logit contributions
 Twe+0.017
 ot+0.017
 Nem+0.016
 le+0.016
Twe+0.015
Neg logit contributions
 outage-0.017
hole-0.017
ouncing-0.017
ying-0.017
ows-0.016
Token us
Token ID514
Feature activation-2.15e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
ying+0.005
hole+0.005
 ma+0.005
Neg logit contributions
 Twe-0.004
 ot-0.004
Twe-0.004
 Nem-0.004
 le-0.004
Token.
Token ID13
Feature activation-5.87e-02

Pos logit contributions
 Twe+0.005
 ot+0.005
 Nem+0.004
 le+0.004
Twe+0.004
Neg logit contributions
 outage-0.009
ouncing-0.008
hole-0.008
ying-0.008
 ma-0.008
Token and
Token ID290
Feature activation-8.82e-03

Pos logit contributions
 outage+0.063
ouncing+0.062
rum+0.060
ying+0.059
 Today+0.058
Neg logit contributions
 Twe-0.055
 ot-0.051
 le-0.050
 Nem-0.049
Twe-0.047
Token it
Token ID340
Feature activation-1.84e-02

Pos logit contributions
 Twe+0.000
 ot+0.000
Twe+0.000
 Nem+0.000
 le+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
Token shattered
Token ID23273
Feature activation+4.68e-01

Pos logit contributions
 ot+0.001
 Twe+0.001
Twe+0.001
 Nem+0.001
 jew+0.001
Neg logit contributions
 outage-0.001
hole-0.001
ouncing-0.001
lessly-0.001
ying-0.001
Token into
Token ID656
Feature activation-7.12e-01

Pos logit contributions
 outage+0.014
hole+0.014
ouncing+0.013
ying+0.013
lessly+0.013
Neg logit contributions
 Twe-0.015
 ot-0.015
Twe-0.015
 Nem-0.015
 le-0.014
Token a
Token ID257
Feature activation+2.49e-01

Pos logit contributions
 Twe+0.022
 ot+0.021
Twe+0.021
 Nem+0.020
 le+0.019
Neg logit contributions
 outage-0.023
hole-0.022
 ma-0.021
lessly-0.021
ouncing-0.021
Token million
Token ID1510
Feature activation+3.58e+00

Pos logit contributions
ouncing+0.006
ying+0.006
 outage+0.006
hole+0.006
ows+0.005
Neg logit contributions
 Twe-0.010
 ot-0.010
 le-0.009
 jew-0.009
 se-0.009
Token pieces
Token ID5207
Feature activation+8.58e-01

Pos logit contributions
 outage+0.091
hole+0.090
lessly+0.084
 instant+0.082
rum+0.081
Neg logit contributions
 Twe-0.137
Twe-0.132
 ot-0.132
 Nem-0.127
 le-0.121
Token.
Token ID13
Feature activation+8.86e-02

Pos logit contributions
ouncing+0.035
 outage+0.034
 Today+0.033
 ma+0.033
 Deal+0.033
Neg logit contributions
 Twe-0.019
 ot-0.018
 le-0.017
 Nem-0.017
 se-0.016
Token Lily
Token ID20037
Feature activation+3.10e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.002
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
Twe-0.003
 le-0.003
Token was
Token ID373
Feature activation+6.66e-01

Pos logit contributions
 outage+0.014
ying+0.014
ouncing+0.014
 Today+0.014
hole+0.014
Neg logit contributions
 Twe-0.005
 ot-0.005
 le-0.005
 Nem-0.005
 se-0.004
Token so
Token ID523
Feature activation+1.38e+00

Pos logit contributions
ouncing+0.020
 outage+0.020
ying+0.019
hole+0.019
ems+0.019
Neg logit contributions
 Twe-0.023
 ot-0.022
 le-0.021
 Nem-0.021
 se-0.020
Token much
Token ID881
Feature activation+1.04e+00

Pos logit contributions
 outage+0.021
hole+0.020
ouncing+0.020
ying+0.020
 ma+0.019
Neg logit contributions
 Twe-0.025
 ot-0.024
 le-0.023
 Nem-0.023
Twe-0.022
Token fun
Token ID1257
Feature activation-1.34e-01

Pos logit contributions
 outage+0.035
ouncing+0.034
hole+0.033
ying+0.033
 ma+0.032
Neg logit contributions
 Twe-0.031
 ot-0.030
 Nem-0.028
Twe-0.028
 le-0.028
Token.
Token ID13
Feature activation-2.11e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 Nem+0.003
 le+0.003
Twe+0.003
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token "
Token ID366
Feature activation-3.99e-01

Pos logit contributions
 Twe+0.008
 Nem+0.007
 ot+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.006
ying-0.006
ouncing-0.006
hole-0.006
rum-0.005
TokenWhe
Token ID10842
Feature activation-4.08e-01

Pos logit contributions
 Twe+0.012
 ot+0.012
 Nem+0.011
 le+0.011
Twe+0.011
Neg logit contributions
 outage-0.013
ouncing-0.012
hole-0.012
ying-0.012
 ma-0.012
Tokene
Token ID68
Feature activation-4.56e+00

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
 le+0.011
Twe+0.010
Neg logit contributions
 outage-0.014
ouncing-0.014
hole-0.014
ying-0.013
 ma-0.013
Token!"
Token ID2474
Feature activation-4.27e-01

Pos logit contributions
 Twe+0.170
 ot+0.169
 Nem+0.162
Twe+0.160
 le+0.158
Neg logit contributions
ouncing-0.113
 outage-0.112
hole-0.108
ying-0.104
 ma-0.103
Token he
Token ID339
Feature activation+3.61e-01

Pos logit contributions
 Twe+0.014
 ot+0.013
 Nem+0.013
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.014
ouncing-0.013
hole-0.013
ying-0.013
 ma-0.012
Token shouted
Token ID17293
Feature activation-2.80e-01

Pos logit contributions
 outage+0.011
ouncing+0.011
hole+0.011
ying+0.011
 ma+0.010
Neg logit contributions
 Twe-0.011
 ot-0.011
 Nem-0.010
Twe-0.010
 le-0.010
Token.
Token ID13
Feature activation-7.60e-03

Pos logit contributions
 ot+0.008
 Twe+0.008
Twe+0.008
 le+0.008
 Nem+0.008
Neg logit contributions
 outage-0.009
ouncing-0.009
 about-0.008
hole-0.008
lessly-0.008
Token From
Token ID3574
Feature activation+6.55e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
Twe+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
Token happy
Token ID3772
Feature activation+2.54e-01

Pos logit contributions
 outage+0.018
hole+0.017
ouncing+0.017
ying+0.016
 Today+0.016
Neg logit contributions
 Twe-0.026
 ot-0.025
 le-0.024
 Nem-0.024
Twe-0.024
Token and
Token ID290
Feature activation-4.25e-01

Pos logit contributions
 outage+0.009
hole+0.009
ouncing+0.009
ying+0.009
rum+0.008
Neg logit contributions
 Twe-0.007
 ot-0.007
 le-0.007
 Nem-0.006
 jew-0.006
Token shouts
Token ID34757
Feature activation-1.58e-01

Pos logit contributions
 Twe+0.015
 ot+0.014
 le+0.014
 Nem+0.014
Twe+0.013
Neg logit contributions
 outage-0.013
hole-0.012
ying-0.012
ouncing-0.012
rum-0.011
Token "
Token ID366
Feature activation-1.11e+00

Pos logit contributions
 Twe+0.005
 ot+0.005
 Nem+0.005
Twe+0.005
 le+0.005
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
TokenWhe
Token ID10842
Feature activation-1.36e-01

Pos logit contributions
 Twe+0.034
 ot+0.034
 Nem+0.032
 le+0.031
Twe+0.031
Neg logit contributions
 outage-0.036
ouncing-0.035
hole-0.035
ying-0.033
 ma-0.033
Tokene
Token ID68
Feature activation-4.51e+00

Pos logit contributions
 Twe+0.003
 ot+0.003
 Nem+0.003
 le+0.003
Twe+0.003
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token!"
Token ID2474
Feature activation-4.52e-01

Pos logit contributions
 Twe+0.163
 ot+0.160
 Nem+0.154
Twe+0.152
 le+0.149
Neg logit contributions
ouncing-0.119
 outage-0.118
hole-0.113
ying-0.111
 ma-0.110
Token Uncle
Token ID23169
Feature activation-2.52e-01

Pos logit contributions
 Twe+0.012
 le+0.011
 Nem+0.010
Twe+0.010
 ot+0.010
Neg logit contributions
 outage-0.019
ying-0.018
rum-0.017
hole-0.017
ouncing-0.016
Token Tom
Token ID4186
Feature activation+4.59e-01

Pos logit contributions
 Twe+0.009
 ot+0.009
 le+0.009
 Nem+0.009
Twe+0.008
Neg logit contributions
 outage-0.007
hole-0.007
ouncing-0.006
ying-0.006
lessly-0.006
Token laughs
Token ID22051
Feature activation+7.71e-02

Pos logit contributions
 outage+0.013
hole+0.012
ying+0.012
ouncing+0.012
lessly+0.011
Neg logit contributions
 Twe-0.016
 ot-0.016
 le-0.016
 Nem-0.015
 Bub-0.014
Token and
Token ID290
Feature activation-5.59e-02

Pos logit contributions
 outage+0.003
hole+0.003
ouncing+0.003
ying+0.003
rum+0.002
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
 se-0.002
Token as
Token ID355
Feature activation-1.81e-01

Pos logit contributions
 outage+0.016
ouncing+0.016
ying+0.016
hole+0.016
lessly+0.016
Neg logit contributions
 Twe-0.016
 ot-0.016
Twe-0.015
 le-0.015
 Nem-0.015
Token the
Token ID262
Feature activation-1.86e+00

Pos logit contributions
Twe+0.005
 ot+0.005
 Twe+0.005
 le+0.005
 Nem+0.005
Neg logit contributions
 ma-0.006
ying-0.006
 outage-0.006
lessly-0.005
ouncing-0.005
Token best
Token ID1266
Feature activation+7.28e-02

Pos logit contributions
 Twe+0.069
Twe+0.063
 Nem+0.062
 ot+0.061
 jew+0.057
Neg logit contributions
 ma-0.048
 outage-0.047
ouncing-0.045
 click-0.044
hole-0.044
Token joke
Token ID9707
Feature activation-1.44e+00

Pos logit contributions
 outage+0.002
ouncing+0.002
ying+0.002
hole+0.002
 ma+0.002
Neg logit contributions
 Twe-0.002
Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Token-
Token ID12
Feature activation-3.76e+00

Pos logit contributions
 Twe+0.043
 ot+0.042
 Nem+0.040
Twe+0.039
 le+0.039
Neg logit contributions
 outage-0.048
ouncing-0.047
hole-0.046
ying-0.045
 ma-0.043
Tokente
Token ID660
Feature activation-4.48e+00

Pos logit contributions
 ot+0.116
 Twe+0.114
 Nem+0.111
 jew+0.111
Twe+0.106
Neg logit contributions
ouncing-0.119
 outage-0.115
ying-0.114
lessly-0.111
rum-0.105
Tokenller
Token ID6051
Feature activation-8.62e-01

Pos logit contributions
 jew+0.172
 ot+0.168
Twe+0.167
 Twe+0.164
 Nem+0.162
Neg logit contributions
ouncing-0.110
 outage-0.097
ying-0.093
rum-0.091
hole-0.089
Token around
Token ID1088
Feature activation+5.35e-01

Pos logit contributions
 Twe+0.025
 ot+0.024
Twe+0.023
 Nem+0.023
 le+0.022
Neg logit contributions
 outage-0.030
ouncing-0.029
hole-0.028
ying-0.028
 ma-0.027
Token.
Token ID13
Feature activation-1.65e-01

Pos logit contributions
 outage+0.020
ying+0.020
hole+0.020
ouncing+0.019
lessly+0.019
Neg logit contributions
 Twe-0.013
 ot-0.012
Twe-0.012
 le-0.011
 Nem-0.011
Token<|endoftext|>
Token ID50256
Feature activation+2.49e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
 Nem+0.006
Twe+0.006
 le+0.006
Neg logit contributions
 outage-0.004
hole-0.004
ouncing-0.004
ying-0.004
ows-0.004
TokenOnce
Token ID7454
Feature activation+1.95e-01

Pos logit contributions
 outage+0.009
ouncing+0.008
hole+0.008
ying+0.008
 ma+0.008
Neg logit contributions
 Twe-0.007
 ot-0.007
 Nem-0.007
Twe-0.007
 le-0.006
Token then
Token ID788
Feature activation-1.26e+00

Pos logit contributions
 Twe+0.008
Twe+0.008
 ot+0.008
 Nem+0.008
 le+0.008
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.007
 ma-0.007
Token said
Token ID531
Feature activation-9.81e-02

Pos logit contributions
 Twe+0.037
 ot+0.036
 Nem+0.034
 le+0.033
Twe+0.033
Neg logit contributions
 outage-0.043
ouncing-0.042
hole-0.041
ying-0.041
rum-0.039
Token,
Token ID11
Feature activation+3.34e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 Nem+0.003
Twe+0.003
 le+0.003
Neg logit contributions
 outage-0.003
ouncing-0.003
hole-0.003
ying-0.003
 ma-0.003
Token "
Token ID366
Feature activation-7.57e-01

Pos logit contributions
 outage+0.010
hole+0.009
ouncing+0.009
ying+0.009
rum+0.009
Neg logit contributions
 Twe-0.012
 ot-0.011
 Nem-0.011
 le-0.011
Twe-0.010
TokenWhe
Token ID10842
Feature activation-5.37e-02

Pos logit contributions
 Twe+0.023
 ot+0.022
 Nem+0.021
 le+0.021
Twe+0.021
Neg logit contributions
 outage-0.025
ouncing-0.025
hole-0.024
ying-0.024
 ma-0.023
Tokene
Token ID68
Feature activation-4.45e+00

Pos logit contributions
 Twe+0.002
 ot+0.001
 Nem+0.001
 le+0.001
Twe+0.001
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
ying-0.002
 ma-0.002
Token!"
Token ID2474
Feature activation-6.05e-01

Pos logit contributions
 Twe+0.159
 ot+0.158
 Nem+0.152
Twe+0.150
 jew+0.146
Neg logit contributions
ouncing-0.119
 outage-0.114
hole-0.109
 ma-0.109
ows-0.109
Token Tim
Token ID5045
Feature activation-6.92e-02

Pos logit contributions
 Twe+0.020
 ot+0.019
 Nem+0.019
 le+0.018
Twe+0.018
Neg logit contributions
 outage-0.019
hole-0.018
ouncing-0.018
ying-0.018
 ma-0.017
Tokenmy
Token ID1820
Feature activation-4.41e-02

Pos logit contributions
 Twe+0.002
 ot+0.002
 le+0.002
 Nem+0.002
Twe+0.002
Neg logit contributions
 outage-0.002
ying-0.002
otion-0.002
ouncing-0.002
lessly-0.002
Token slid
Token ID27803
Feature activation+2.92e-02

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
 le+0.001
Twe+0.001
Neg logit contributions
 outage-0.002
ouncing-0.002
ying-0.002
hole-0.002
 ma-0.002
Token down
Token ID866
Feature activation+9.16e-01

Pos logit contributions
 outage+0.001
 Promise+0.001
rum+0.001
ouncing+0.001
ems+0.001
Neg logit contributions
 Twe-0.001
 le-0.001
 ot-0.001
 Nem-0.001
 Bub-0.001
Token and
Token ID290
Feature activation+1.27e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 le+0.001
 Nem+0.001
 Bub+0.001
Neg logit contributions
 outage-0.001
hole-0.001
ying-0.001
ouncing-0.001
 ma-0.001
Token shouts
Token ID34757
Feature activation-3.27e-02

Pos logit contributions
 outage+0.004
ying+0.004
hole+0.004
ouncing+0.003
rum+0.003
Neg logit contributions
 Twe-0.005
 ot-0.004
 le-0.004
 Nem-0.004
 Bub-0.004
Token.
Token ID13
Feature activation+7.28e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
Twe+0.001
 Nem+0.001
 le+0.001
Neg logit contributions
ouncing-0.001
 outage-0.001
ying-0.001
hole-0.001
 ma-0.001
Token "
Token ID366
Feature activation-3.36e-02

Pos logit contributions
 outage+0.022
ouncing+0.022
hole+0.021
ying+0.021
rum+0.020
Neg logit contributions
 Twe-0.025
 ot-0.024
 Nem-0.023
 le-0.022
Twe-0.022
TokenWhe
Token ID10842
Feature activation+2.99e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
Twe+0.001
 Nem+0.001
 le+0.001
Neg logit contributions
 outage-0.001
ouncing-0.001
ying-0.001
hole-0.001
ows-0.001
Tokene
Token ID68
Feature activation-4.43e+00

Pos logit contributions
 outage+0.013
ouncing+0.012
hole+0.012
ying+0.012
 ma+0.012
Neg logit contributions
 Twe-0.006
 ot-0.006
 le-0.006
 Nem-0.005
Twe-0.005
Token!
Token ID0
Feature activation-1.87e-01

Pos logit contributions
 Twe+0.162
 ot+0.159
 Nem+0.153
Twe+0.151
 le+0.149
Neg logit contributions
 outage-0.117
ouncing-0.115
hole-0.110
ying-0.108
 ma-0.105
Token This
Token ID770
Feature activation-3.80e-01

Pos logit contributions
 Twe+0.008
 ot+0.008
 Nem+0.008
 le+0.007
Twe+0.007
Neg logit contributions
 outage-0.004
ouncing-0.004
hole-0.004
ying-0.004
lessly-0.003
Token is
Token ID318
Feature activation+7.81e-01

Pos logit contributions
 Twe+0.012
 ot+0.012
 le+0.012
 Nem+0.011
Twe+0.011
Neg logit contributions
 outage-0.012
ouncing-0.011
ying-0.011
hole-0.011
rum-0.011
Token fun
Token ID1257
Feature activation+7.44e-01

Pos logit contributions
 outage+0.026
ouncing+0.026
hole+0.025
ying+0.025
rum+0.024
Neg logit contributions
 Twe-0.024
 ot-0.023
 Nem-0.022
 le-0.021
Twe-0.021
Token!"
Token ID2474
Feature activation-4.59e-01

Pos logit contributions
ouncing+0.026
 outage+0.026
hole+0.025
ying+0.025
 ma+0.024
Neg logit contributions
 Twe-0.021
 ot-0.020
 le-0.020
 Nem-0.019
Twe-0.017
Token down
Token ID866
Feature activation+5.35e-01

Pos logit contributions
 Twe+0.023
 le+0.021
 ot+0.021
 Nem+0.020
 Bub+0.019
Neg logit contributions
 outage-0.014
ying-0.012
ouncing-0.012
rum-0.011
 Promise-0.011
Token the
Token ID262
Feature activation-5.18e-01

Pos logit contributions
 outage+0.017
hole+0.017
ouncing+0.017
lessly+0.017
ying+0.016
Neg logit contributions
 ot-0.016
Twe-0.015
 Twe-0.015
 Nem-0.015
 jew-0.014
Token slide
Token ID10649
Feature activation-1.00e-01

Pos logit contributions
 Twe+0.018
 le+0.017
 ot+0.016
Twe+0.016
 Nem+0.015
Neg logit contributions
 outage-0.017
ems-0.016
rum-0.016
ouncing-0.016
 Deal-0.016
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
Twe+0.002
 le+0.002
Neg logit contributions
 outage-0.004
ouncing-0.004
hole-0.004
ying-0.004
lessly-0.004
Token Whe
Token ID5792
Feature activation+3.14e-01

Pos logit contributions
 Twe+0.007
 ot+0.006
 le+0.006
 Nem+0.006
Twe+0.006
Neg logit contributions
 outage-0.006
ying-0.006
hole-0.006
ouncing-0.005
rum-0.005
Tokene
Token ID68
Feature activation-4.41e+00

Pos logit contributions
 outage+0.011
ouncing+0.011
hole+0.010
ying+0.010
 ma+0.010
Neg logit contributions
 Twe-0.009
 ot-0.009
 Nem-0.008
 le-0.008
Twe-0.008
Token!
Token ID0
Feature activation-4.69e-01

Pos logit contributions
 ot+0.145
 Nem+0.139
 Twe+0.135
 jew+0.132
Twe+0.132
Neg logit contributions
ouncing-0.140
ows-0.128
hole-0.120
 ma-0.120
 outage-0.118
Token It
Token ID632
Feature activation-1.57e+00

Pos logit contributions
 Twe+0.017
 ot+0.016
 Nem+0.015
Twe+0.015
 le+0.015
Neg logit contributions
 outage-0.014
ouncing-0.013
hole-0.013
ying-0.013
rum-0.012
Token was
Token ID373
Feature activation+2.10e-01

Pos logit contributions
 Twe+0.031
 ot+0.030
 Nem+0.028
Twe+0.027
 le+0.027
Neg logit contributions
 outage-0.069
ouncing-0.067
hole-0.066
ying-0.066
 ma-0.064
Token so
Token ID523
Feature activation+7.03e-01

Pos logit contributions
 outage+0.007
ouncing+0.007
ying+0.007
hole+0.007
rum+0.007
Neg logit contributions
 Twe-0.007
 le-0.006
 ot-0.006
 Nem-0.006
Twe-0.006
Token much
Token ID881
Feature activation+1.37e+00

Pos logit contributions
 outage+0.023
hole+0.022
rum+0.021
ying+0.020
ouncing+0.020
Neg logit contributions
 Twe-0.024
 ot-0.021
 le-0.021
 Nem-0.021
Twe-0.021
Token and
Token ID290
Feature activation+2.04e-01

Pos logit contributions
 outage+0.006
ouncing+0.005
hole+0.005
ying+0.005
rum+0.005
Neg logit contributions
 Twe-0.006
 ot-0.006
 Nem-0.006
 le-0.006
 Bub-0.005
Token said
Token ID531
Feature activation+6.74e-04

Pos logit contributions
 outage+0.008
ying+0.007
hole+0.007
ouncing+0.007
rum+0.007
Neg logit contributions
 Twe-0.006
 ot-0.005
 Nem-0.005
 le-0.005
Twe-0.005
Token,
Token ID11
Feature activation+4.10e-01

Pos logit contributions
 outage+0.000
hole+0.000
ouncing+0.000
ying+0.000
rum+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 Nem-0.000
 le-0.000
 Bub-0.000
Token "
Token ID366
Feature activation-5.26e-01

Pos logit contributions
 outage+0.016
hole+0.015
ying+0.014
rum+0.014
ouncing+0.014
Neg logit contributions
 Twe-0.012
 le-0.011
 Nem-0.011
 ot-0.011
 Bub-0.011
TokenWhe
Token ID10842
Feature activation+1.30e-01

Pos logit contributions
 Twe+0.018
 ot+0.017
 Nem+0.017
Twe+0.016
 le+0.016
Neg logit contributions
 outage-0.016
ouncing-0.015
hole-0.015
ying-0.015
 ma-0.014
Tokene
Token ID68
Feature activation-4.39e+00

Pos logit contributions
 outage+0.005
ouncing+0.005
hole+0.005
ying+0.004
 ma+0.004
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
 le-0.003
Twe-0.003
Token!
Token ID0
Feature activation-1.91e-01

Pos logit contributions
 ot+0.157
 Twe+0.156
 Nem+0.151
Twe+0.149
 jew+0.146
Neg logit contributions
ouncing-0.117
 outage-0.109
 ma-0.106
hole-0.105
ows-0.105
Token This
Token ID770
Feature activation-3.85e-01

Pos logit contributions
 Twe+0.008
 ot+0.007
 Nem+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.005
ying-0.005
hole-0.005
ouncing-0.004
lessly-0.004
Token is
Token ID318
Feature activation+8.17e-01

Pos logit contributions
 Twe+0.013
 ot+0.012
 le+0.012
 Nem+0.012
Twe+0.011
Neg logit contributions
 outage-0.012
ouncing-0.011
ying-0.011
hole-0.011
rum-0.011
Token fun
Token ID1257
Feature activation+5.89e-01

Pos logit contributions
 outage+0.027
ouncing+0.027
ying+0.026
hole+0.026
rum+0.025
Neg logit contributions
 Twe-0.026
 ot-0.024
 Nem-0.024
 le-0.023
Twe-0.023
Token!
Token ID0
Feature activation-4.40e-01

Pos logit contributions
ouncing+0.020
 outage+0.020
hole+0.020
ying+0.020
 Deal+0.019
Neg logit contributions
 Twe-0.017
 ot-0.016
 le-0.016
 Nem-0.015
 se-0.014
Token and
Token ID290
Feature activation-3.21e-01

Pos logit contributions
 outage+0.037
rum+0.030
hole+0.030
ouncing+0.029
lessly+0.029
Neg logit contributions
 Twe-0.021
 le-0.019
 Nem-0.018
sp-0.018
--0.018
Token slide
Token ID10649
Feature activation-2.98e-01

Pos logit contributions
 Twe+0.010
 ot+0.009
 le+0.009
 Nem+0.009
Twe+0.009
Neg logit contributions
 outage-0.011
ouncing-0.010
ying-0.010
hole-0.010
rum-0.010
Token down
Token ID866
Feature activation+2.46e-01

Pos logit contributions
 Twe+0.010
 le+0.009
 Nem+0.009
 ot+0.009
Twe+0.008
Neg logit contributions
 outage-0.010
ouncing-0.009
 Promise-0.009
rum-0.008
ying-0.008
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
 outage+0.009
ouncing+0.008
hole+0.008
ying+0.008
rum+0.008
Neg logit contributions
 Twe-0.007
 ot-0.007
 le-0.007
 Nem-0.007
Twe-0.006
Token Whe
Token ID5792
Feature activation-5.18e-03

Pos logit contributions
ying+0.007
 outage+0.007
ouncing+0.006
hole+0.006
lessly+0.006
Neg logit contributions
 Twe-0.009
 ot-0.008
 Nem-0.008
Twe-0.008
 Bub-0.008
Tokene
Token ID68
Feature activation-4.39e+00

Pos logit contributions
 Twe+0.000
 ot+0.000
 le+0.000
 Nem+0.000
Twe+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
 ma-0.000
lessly-0.000
Token!"
Token ID2474
Feature activation-3.22e-01

Pos logit contributions
 Twe+0.170
 ot+0.169
 Nem+0.162
Twe+0.162
 jew+0.158
Neg logit contributions
ouncing-0.104
 outage-0.101
ows-0.097
hole-0.096
ying-0.095
Token
Token ID198
Feature activation+6.57e-03

Pos logit contributions
 Twe+0.009
 ot+0.007
Twe+0.007
 Nem+0.007
 le+0.007
Neg logit contributions
 outage-0.013
ying-0.013
ouncing-0.012
hole-0.012
rum-0.012
Token
Token ID198
Feature activation+1.14e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
hole+0.000
ying+0.000
 ma+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
Twe-0.000
 Nem-0.000
 le-0.000
TokenTim
Token ID14967
Feature activation-7.34e-01

Pos logit contributions
 outage+0.004
ying+0.003
ouncing+0.003
hole+0.003
ows+0.003
Neg logit contributions
 Twe-0.004
Twe-0.004
 ot-0.004
 le-0.003
 Nem-0.003
Token slid
Token ID27803
Feature activation-1.30e-01

Pos logit contributions
 Twe+0.020
 ot+0.019
 Nem+0.018
 le+0.018
Twe+0.018
Neg logit contributions
 outage-0.027
ouncing-0.026
hole-0.025
ying-0.025
 ma-0.024
Token went
Token ID1816
Feature activation-8.50e-02

Pos logit contributions
 ot+0.037
 jew+0.036
 Twe+0.036
Twe+0.036
 Nem+0.034
Neg logit contributions
ouncing-0.031
 does-0.028
 falls-0.027
ows-0.027
 about-0.027
Token to
Token ID284
Feature activation-8.50e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
Twe+0.003
 Nem+0.003
 jew+0.003
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
ying-0.002
 about-0.002
Token get
Token ID651
Feature activation-7.85e-02

Pos logit contributions
 Twe+0.025
 ot+0.024
Twe+0.023
 Nem+0.023
 le+0.022
Neg logit contributions
 outage-0.029
hole-0.027
ouncing-0.027
 ma-0.027
ying-0.027
Token more
Token ID517
Feature activation-2.65e-01

Pos logit contributions
Twe+0.003
 ot+0.003
 jew+0.003
ho+0.003
io+0.003
Neg logit contributions
 forth-0.001
 down-0.001
 onwards-0.001
 OK-0.001
 on-0.001
Token ice
Token ID4771
Feature activation-2.06e+00

Pos logit contributions
 Twe+0.007
Twe+0.007
 ot+0.007
 Nem+0.006
 Bub+0.006
Neg logit contributions
 outage-0.010
hole-0.009
ying-0.009
ouncing-0.009
rum-0.009
Token-
Token ID12
Feature activation-4.38e+00

Pos logit contributions
 Twe+0.049
 ot+0.048
Twe+0.048
 Nem+0.046
 Bub+0.045
Neg logit contributions
ying-0.079
 outage-0.079
hole-0.077
ouncing-0.076
ows-0.075
Tokencream
Token ID36277
Feature activation-2.19e+00

Pos logit contributions
 ot+0.133
 jew+0.129
 Nem+0.125
 Bub+0.120
 Twe+0.116
Neg logit contributions
aking-0.130
ying-0.126
ouncing-0.124
hole-0.123
lessly-0.119
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
 Twe+0.055
 ot+0.053
Twe+0.050
 Nem+0.050
 le+0.048
Neg logit contributions
 outage-0.084
ouncing-0.081
hole-0.081
ying-0.080
 ma-0.077
Token Spot
Token ID15899
Feature activation+2.41e-01

Pos logit contributions
 ot+0.005
 Twe+0.005
Twe+0.005
 jew+0.005
 Nem+0.005
Neg logit contributions
ouncing-0.005
 outage-0.005
 Today-0.005
 ma-0.005
hole-0.005
Token was
Token ID373
Feature activation+3.28e-01

Pos logit contributions
ouncing+0.008
 outage+0.007
 ma+0.007
hole+0.007
ying+0.007
Neg logit contributions
 Twe-0.007
 ot-0.007
Twe-0.007
 jew-0.007
 Nem-0.007
Token worried
Token ID7960
Feature activation+5.04e-01

Pos logit contributions
 outage+0.010
hole+0.010
ying+0.010
ouncing+0.010
ems+0.010
Neg logit contributions
 Twe-0.012
 le-0.011
 ot-0.011
 Nem-0.010
Twe-0.010
Token was
Token ID373
Feature activation-4.18e-01

Pos logit contributions
 Twe+0.026
 ot+0.025
Twe+0.024
 Nem+0.023
 le+0.022
Neg logit contributions
 outage-0.033
ouncing-0.033
hole-0.032
ying-0.032
lessly-0.031
Token now
Token ID783
Feature activation-1.28e+00

Pos logit contributions
 Twe+0.016
 ot+0.016
Twe+0.015
 Nem+0.015
 le+0.015
Neg logit contributions
 outage-0.010
ouncing-0.010
ying-0.010
hole-0.009
 ma-0.009
Token happy
Token ID3772
Feature activation-2.67e-01

Pos logit contributions
 Twe+0.043
 ot+0.041
 Nem+0.040
 le+0.039
Twe+0.038
Neg logit contributions
 outage-0.039
ouncing-0.038
hole-0.038
ying-0.037
 ma-0.035
Token and
Token ID290
Feature activation-7.93e-01

Pos logit contributions
 Twe+0.007
 ot+0.007
 Nem+0.006
 le+0.006
 jew+0.006
Neg logit contributions
 outage-0.010
hole-0.010
ouncing-0.010
ying-0.010
rum-0.009
Token well
Token ID880
Feature activation-1.95e+00

Pos logit contributions
 Twe+0.027
 ot+0.026
 Nem+0.025
 le+0.024
Twe+0.024
Neg logit contributions
 outage-0.024
ouncing-0.023
hole-0.023
ying-0.022
 ma-0.021
Token-
Token ID12
Feature activation-4.37e+00

Pos logit contributions
 Twe+0.053
 ot+0.051
Twe+0.050
 Nem+0.047
 le+0.046
Neg logit contributions
 outage-0.070
ouncing-0.069
ying-0.068
hole-0.067
lessly-0.066
Tokenfed
Token ID19082
Feature activation-1.68e-01

Pos logit contributions
 ot+0.132
 jew+0.121
 Nem+0.118
 Twe+0.117
 se+0.117
Neg logit contributions
ouncing-0.152
ying-0.140
aking-0.136
lessly-0.131
ows-0.129
Token.
Token ID13
Feature activation-5.93e-02

Pos logit contributions
 Twe+0.004
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.006
ouncing-0.006
hole-0.006
ying-0.006
 ma-0.006
Token From
Token ID3574
Feature activation+6.52e-01

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
 le+0.002
Twe+0.002
Neg logit contributions
 outage-0.001
hole-0.001
ying-0.001
ouncing-0.001
ows-0.001
Token then
Token ID788
Feature activation-3.10e-01

Pos logit contributions
 outage+0.021
ouncing+0.020
hole+0.020
ying+0.020
 ma+0.019
Neg logit contributions
 Twe-0.021
 ot-0.020
 Nem-0.019
 le-0.019
Twe-0.019
Token on
Token ID319
Feature activation+1.29e+00

Pos logit contributions
 le+0.009
 Twe+0.009
B+0.008
 ot+0.008
 B+0.008
Neg logit contributions
 outage-0.012
ows-0.011
hole-0.010
 fuss-0.010
ouncing-0.010
Token She
Token ID1375
Feature activation+3.95e-01

Pos logit contributions
 outage+0.014
ying+0.013
hole+0.013
rum+0.013
ouncing+0.013
Neg logit contributions
 Twe-0.015
 ot-0.013
Twe-0.013
 le-0.013
 Nem-0.013
Token shouts
Token ID34757
Feature activation+9.43e-02

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.008
ying+0.008
rum+0.008
Neg logit contributions
 Twe-0.016
 ot-0.016
 le-0.015
 Nem-0.015
Twe-0.015
Token,
Token ID11
Feature activation+1.99e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.002
ying+0.002
 ma+0.002
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
Twe-0.003
 le-0.003
Token "
Token ID366
Feature activation-3.17e-01

Pos logit contributions
 outage+0.008
hole+0.008
ying+0.008
rum+0.008
 instant+0.007
Neg logit contributions
 Twe-0.005
 le-0.005
 ot-0.005
 Nem-0.005
 Bub-0.005
TokenWhe
Token ID10842
Feature activation+3.23e-01

Pos logit contributions
 Twe+0.013
 ot+0.012
 Nem+0.012
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.008
ouncing-0.007
hole-0.007
ying-0.007
 ma-0.007
Tokene
Token ID68
Feature activation-4.36e+00

Pos logit contributions
 outage+0.013
ouncing+0.013
hole+0.012
ying+0.012
lessly+0.012
Neg logit contributions
 Twe-0.007
 ot-0.007
 le-0.007
 Nem-0.006
Twe-0.006
Token!"
Token ID2474
Feature activation-2.36e-01

Pos logit contributions
 Twe+0.152
 ot+0.151
 Nem+0.145
Twe+0.143
 jew+0.140
Neg logit contributions
ouncing-0.120
 outage-0.116
hole-0.112
ying-0.110
 ma-0.109
Token
Token ID198
Feature activation+1.00e-01

Pos logit contributions
 Twe+0.007
 ot+0.007
 Nem+0.007
 le+0.007
Twe+0.006
Neg logit contributions
 outage-0.008
hole-0.008
ying-0.008
ouncing-0.008
rum-0.007
Token
Token ID198
Feature activation+1.79e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
 le-0.003
Twe-0.003
TokenSam
Token ID16305
Feature activation-1.92e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
hole+0.005
ying+0.005
 ma+0.005
Neg logit contributions
 Twe-0.006
 ot-0.006
 Nem-0.006
 le-0.006
Twe-0.006
Token watches
Token ID16860
Feature activation+6.57e-02

Pos logit contributions
 le+0.007
 Twe+0.006
 ot+0.006
 Nem+0.006
 se+0.006
Neg logit contributions
 outage-0.006
ying-0.005
hole-0.005
lessly-0.005
ouncing-0.005
Token and
Token ID290
Feature activation-1.69e-02

Pos logit contributions
 outage+0.004
ouncing+0.004
hole+0.004
ying+0.004
rum+0.004
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002
Token shouted
Token ID17293
Feature activation-2.73e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
Twe+0.000
Neg logit contributions
 outage-0.001
ouncing-0.001
ying-0.001
hole-0.001
rum-0.001
Token,
Token ID11
Feature activation+1.58e-02

Pos logit contributions
 Twe+0.007
 ot+0.006
 Nem+0.006
 le+0.006
Twe+0.006
Neg logit contributions
 outage-0.011
ouncing-0.010
hole-0.010
ying-0.010
 ma-0.010
Token "
Token ID366
Feature activation-4.92e-01

Pos logit contributions
 outage+0.001
ying+0.001
hole+0.001
rum+0.001
 instant+0.001
Neg logit contributions
 Twe-0.000
 le-0.000
 ot-0.000
 Nem-0.000
 Bub-0.000
TokenWhe
Token ID10842
Feature activation+3.35e-01

Pos logit contributions
 Twe+0.019
 ot+0.019
 Nem+0.018
 le+0.018
 jew+0.017
Neg logit contributions
 outage-0.012
ouncing-0.012
hole-0.011
ying-0.011
 ma-0.011
Tokene
Token ID68
Feature activation-4.34e+00

Pos logit contributions
 outage+0.012
ouncing+0.012
hole+0.012
ying+0.012
 ma+0.011
Neg logit contributions
 Twe-0.009
 ot-0.009
 Nem-0.008
 le-0.008
Twe-0.008
Token!"
Token ID2474
Feature activation-5.59e-01

Pos logit contributions
 Twe+0.165
 ot+0.165
 Nem+0.160
Twe+0.158
 jew+0.156
Neg logit contributions
ouncing-0.106
 outage-0.098
ows-0.095
hole-0.095
 ma-0.094
Token
Token ID198
Feature activation-4.22e-03

Pos logit contributions
 Twe+0.016
 Nem+0.015
 ot+0.015
 le+0.015
Twe+0.014
Neg logit contributions
 outage-0.021
hole-0.020
ying-0.020
ouncing-0.020
rum-0.019
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
 jew+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
TokenL
Token ID43
Feature activation-1.74e-01

Pos logit contributions
 outage+0.003
ouncing+0.002
hole+0.002
ying+0.002
 ma+0.002
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
 le-0.004
 jew-0.004
Tokenily
Token ID813
Feature activation+1.08e-01

Pos logit contributions
 Twe+0.007
 ot+0.006
 Nem+0.006
 jew+0.006
Twe+0.006
Neg logit contributions
 outage-0.005
ying-0.005
ouncing-0.005
hole-0.005
ows-0.004
Token he
Token ID339
Feature activation-3.91e-01

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.008
ying+0.008
 ma+0.008
Neg logit contributions
 Twe-0.007
 ot-0.007
Twe-0.006
 Nem-0.006
 le-0.006
Token said
Token ID531
Feature activation-2.91e-01

Pos logit contributions
 Twe+0.012
 ot+0.012
Twe+0.011
 Nem+0.011
 jew+0.011
Neg logit contributions
ouncing-0.012
 outage-0.012
 ma-0.011
hole-0.011
lessly-0.011
Token,
Token ID11
Feature activation+3.68e-01

Pos logit contributions
 Twe+0.008
 ot+0.008
 Nem+0.008
 le+0.008
 jew+0.007
Neg logit contributions
 outage-0.011
hole-0.010
ouncing-0.010
ying-0.010
 Today-0.009
Token "
Token ID366
Feature activation-6.94e-01

Pos logit contributions
 outage+0.013
hole+0.013
ouncing+0.012
ying+0.012
rum+0.012
Neg logit contributions
 Twe-0.011
 Nem-0.011
 ot-0.010
 le-0.010
 Bub-0.010
TokenWhe
Token ID10842
Feature activation+3.16e-02

Pos logit contributions
 Twe+0.022
 ot+0.022
 le+0.021
 Nem+0.021
 jew+0.020
Neg logit contributions
ouncing-0.021
hole-0.021
 outage-0.020
 Today-0.020
lessly-0.019
Tokene
Token ID68
Feature activation-4.32e+00

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
 le-0.001
Twe-0.001
Token!"
Token ID2474
Feature activation-5.61e-01

Pos logit contributions
 Twe+0.150
 ot+0.150
 Nem+0.144
Twe+0.143
 jew+0.140
Neg logit contributions
ouncing-0.118
 outage-0.111
hole-0.107
 ma-0.107
ows-0.106
Token The
Token ID383
Feature activation-4.22e-01

Pos logit contributions
 Twe+0.019
 ot+0.017
 Nem+0.017
 le+0.016
Twe+0.016
Neg logit contributions
 outage-0.019
ying-0.018
hole-0.018
ouncing-0.018
rum-0.017
Token subway
Token ID19612
Feature activation-4.12e-01

Pos logit contributions
 Twe+0.013
 ot+0.012
 Nem+0.012
Twe+0.012
 le+0.011
Neg logit contributions
 outage-0.014
ouncing-0.013
hole-0.013
ying-0.013
 ma-0.013
Token went
Token ID1816
Feature activation+2.06e-01

Pos logit contributions
 Twe+0.010
 ot+0.010
 Nem+0.009
Twe+0.009
 le+0.009
Neg logit contributions
 outage-0.016
ouncing-0.016
hole-0.015
ying-0.015
 ma-0.015
Token under
Token ID739
Feature activation-7.95e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
hole+0.005
ying+0.005
lessly+0.004
Neg logit contributions
 Twe-0.008
 ot-0.008
 Nem-0.008
Twe-0.007
 le-0.007
Token on
Token ID319
Feature activation+5.42e-01

Pos logit contributions
 outage+0.008
ouncing+0.008
hole+0.007
ying+0.007
 Today+0.007
Neg logit contributions
 Twe-0.010
 ot-0.009
 le-0.009
 Nem-0.009
Twe-0.008
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
 outage+0.018
hole+0.018
ouncing+0.017
ying+0.017
 ma+0.017
Neg logit contributions
 ot-0.016
 Twe-0.016
Twe-0.015
 Nem-0.015
 le-0.014
Token grass
Token ID8701
Feature activation-2.13e-01

Pos logit contributions
 Twe+0.005
 ot+0.005
 le+0.005
 Nem+0.004
Twe+0.004
Neg logit contributions
 outage-0.004
ouncing-0.004
ying-0.004
hole-0.004
rum-0.004
Token.
Token ID13
Feature activation+3.23e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
 le+0.006
 Nem+0.005
Twe+0.005
Neg logit contributions
ouncing-0.007
 outage-0.007
ying-0.007
rum-0.007
 Deal-0.007
Token Whe
Token ID5792
Feature activation+3.55e-01

Pos logit contributions
ying+0.009
 outage+0.009
ouncing+0.008
hole+0.008
rum+0.008
Neg logit contributions
 Twe-0.012
 ot-0.012
 Nem-0.011
 le-0.011
Twe-0.011
Tokene
Token ID68
Feature activation-4.31e+00

Pos logit contributions
 outage+0.015
ouncing+0.014
hole+0.014
lessly+0.014
 Today+0.014
Neg logit contributions
 Twe-0.007
 le-0.007
 Nem-0.007
 ot-0.007
 se-0.006
Token!"
Token ID2474
Feature activation-5.68e-01

Pos logit contributions
 Twe+0.166
 ot+0.164
 Nem+0.158
Twe+0.156
 le+0.153
Neg logit contributions
ouncing-0.104
 outage-0.104
hole-0.098
ying-0.096
 ma-0.094
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
 Twe+0.014
 ot+0.013
 Nem+0.013
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.023
hole-0.023
ouncing-0.023
ying-0.022
rum-0.022
Token
Token ID198
Feature activation+5.46e-02

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
Twe+0.004
 le+0.004
Neg logit contributions
 outage-0.004
ouncing-0.004
hole-0.004
ying-0.004
 ma-0.004
TokenL
Token ID43
Feature activation-3.58e-01

Pos logit contributions
 outage+0.002
hole+0.002
ying+0.002
ouncing+0.002
rum+0.002
Neg logit contributions
 Twe-0.001
Twe-0.001
 le-0.001
 ot-0.001
 Nem-0.001
Tokenily
Token ID813
Feature activation-1.45e-02

Pos logit contributions
 Twe+0.012
 ot+0.012
 Nem+0.011
Twe+0.011
 le+0.011
Neg logit contributions
 outage-0.011
ouncing-0.011
ying-0.010
hole-0.010
 ma-0.010
Token and
Token ID290
Feature activation-5.73e-01

Pos logit contributions
ouncing+0.028
 Deal+0.027
 Promise+0.027
 outage+0.027
rum+0.027
Neg logit contributions
 le-0.020
 Twe-0.019
 ot-0.018
 se-0.018
 pl-0.017
Token slides
Token ID19392
Feature activation-7.85e-01

Pos logit contributions
 Twe+0.019
 le+0.018
 ot+0.017
 Nem+0.017
 pl+0.017
Neg logit contributions
 outage-0.019
rum-0.017
ying-0.017
ouncing-0.016
lessness-0.016
Token down
Token ID866
Feature activation+2.35e-01

Pos logit contributions
 Twe+0.035
 ot+0.033
 le+0.033
 Nem+0.032
Twe+0.031
Neg logit contributions
 outage-0.017
ouncing-0.015
hole-0.014
rum-0.014
ying-0.014
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
 outage+0.008
ouncing+0.008
hole+0.008
ying+0.008
lessly+0.008
Neg logit contributions
 ot-0.006
 Twe-0.006
Twe-0.006
 Nem-0.006
 jew-0.006
Token Whe
Token ID5792
Feature activation+2.56e-01

Pos logit contributions
 outage+0.006
hole+0.006
ying+0.006
rum+0.006
ouncing+0.005
Neg logit contributions
 Twe-0.005
 le-0.005
 Nem-0.005
Twe-0.005
 ot-0.005
Tokene
Token ID68
Feature activation-4.31e+00

Pos logit contributions
 outage+0.011
ouncing+0.010
hole+0.010
 ma+0.010
ying+0.010
Neg logit contributions
 Twe-0.006
 le-0.005
 Nem-0.005
 ot-0.005
Twe-0.005
Token!
Token ID0
Feature activation-1.61e-01

Pos logit contributions
 ot+0.144
 Twe+0.140
 Nem+0.136
Twe+0.135
 jew+0.131
Neg logit contributions
ouncing-0.129
ows-0.120
 outage-0.118
hole-0.116
 ma-0.115
Token
Token ID198
Feature activation+8.49e-02

Pos logit contributions
 Twe+0.004
 Nem+0.004
Twe+0.004
 le+0.004
 Bub+0.003
Neg logit contributions
 outage-0.007
hole-0.006
ying-0.006
rum-0.006
 forth-0.006
Token
Token ID198
Feature activation+1.10e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.002
 Nem-0.002
 ot-0.002
Twe-0.002
 le-0.002
TokenThey
Token ID2990
Feature activation-9.96e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
Twe-0.004
 le-0.004
Token do
Token ID466
Feature activation-5.45e-02

Pos logit contributions
 Twe+0.036
 ot+0.034
 Nem+0.033
 le+0.033
Twe+0.032
Neg logit contributions
 outage-0.029
ouncing-0.028
ying-0.027
hole-0.027
rum-0.026
Token and
Token ID290
Feature activation-5.90e-01

Pos logit contributions
ouncing+0.030
 outage+0.028
 Deal+0.028
 Promise+0.028
rum+0.028
Neg logit contributions
 le-0.020
 Twe-0.019
 ot-0.018
 se-0.017
 Nem-0.016
Token slides
Token ID19392
Feature activation-8.16e-01

Pos logit contributions
 Twe+0.020
 le+0.020
 ot+0.019
 Nem+0.019
 pl+0.018
Neg logit contributions
 outage-0.019
ying-0.017
rum-0.017
hole-0.016
ouncing-0.016
Token down
Token ID866
Feature activation+1.69e-01

Pos logit contributions
 Twe+0.037
 ot+0.035
 le+0.035
 Nem+0.035
Twe+0.033
Neg logit contributions
 outage-0.016
ouncing-0.014
hole-0.014
ying-0.014
rum-0.013
Token.
Token ID13
Feature activation+6.00e-02

Pos logit contributions
 outage+0.006
hole+0.006
ouncing+0.006
lessly+0.006
ying+0.006
Neg logit contributions
 ot-0.005
 Twe-0.004
Twe-0.004
 Nem-0.004
 jew-0.004
Token Whe
Token ID5792
Feature activation+1.75e-01

Pos logit contributions
 outage+0.002
hole+0.002
ying+0.002
ouncing+0.002
rum+0.002
Neg logit contributions
 Twe-0.002
 Nem-0.002
 ot-0.002
 le-0.002
 Bub-0.002
Tokene
Token ID68
Feature activation-4.31e+00

Pos logit contributions
 outage+0.007
ouncing+0.007
hole+0.007
 ma+0.007
lessly+0.006
Neg logit contributions
 Twe-0.004
 le-0.004
 Nem-0.004
 ot-0.004
Twe-0.003
Token!
Token ID0
Feature activation-2.63e-01

Pos logit contributions
 ot+0.149
 Twe+0.144
 Nem+0.141
Twe+0.139
 jew+0.137
Neg logit contributions
ouncing-0.124
ows-0.117
 outage-0.111
hole-0.110
 ma-0.110
Token
Token ID198
Feature activation+3.85e-02

Pos logit contributions
 Twe+0.008
 Nem+0.007
 ot+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.010
hole-0.010
ying-0.010
ouncing-0.009
rum-0.009
Token
Token ID198
Feature activation+3.35e-02

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 Nem-0.001
 ot-0.001
Twe-0.001
 le-0.001
Token"
Token ID1
Feature activation-5.43e-01

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
 le-0.001
Twe-0.001
TokenWow
Token ID22017
Feature activation+3.04e-01

Pos logit contributions
 Twe+0.018
 ot+0.018
 Nem+0.017
 le+0.017
Twe+0.017
Neg logit contributions
 outage-0.016
ouncing-0.015
hole-0.015
 ma-0.015
ying-0.014
Token and
Token ID290
Feature activation-6.34e-01

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
 le-0.001
 jew-0.001
Token Jack
Token ID3619
Feature activation+1.98e-01

Pos logit contributions
 Twe+0.018
 ot+0.018
Twe+0.017
 Nem+0.017
 le+0.017
Neg logit contributions
 outage-0.021
ouncing-0.021
ying-0.020
hole-0.020
 ma-0.020
Token was
Token ID373
Feature activation-2.92e-01

Pos logit contributions
ouncing+0.007
 outage+0.007
hole+0.007
ying+0.007
 ma+0.006
Neg logit contributions
 Twe-0.006
 ot-0.005
Twe-0.005
 Nem-0.005
 le-0.005
Token the
Token ID262
Feature activation-6.43e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
 le+0.011
Twe+0.011
Neg logit contributions
 outage-0.007
ouncing-0.007
hole-0.007
ying-0.006
 ma-0.006
Token happiest
Token ID49414
Feature activation-1.98e-01

Pos logit contributions
 Twe+0.028
Twe+0.026
 Nem+0.024
 le+0.024
 ot+0.024
Neg logit contributions
 ma-0.012
 instant-0.011
 outage-0.011
lessly-0.011
 grin-0.011
Token oct
Token ID19318
Feature activation-4.30e+00

Pos logit contributions
 Twe+0.006
Twe+0.006
 ot+0.005
 jew+0.005
 le+0.005
Neg logit contributions
 outage-0.006
ying-0.006
ouncing-0.006
 ma-0.006
lessly-0.006
Tokenopus
Token ID25790
Feature activation-2.30e+00

Pos logit contributions
 Twe+0.184
 jew+0.169
 ot+0.169
 Nem+0.166
 le+0.163
Neg logit contributions
ouncing-0.097
 outage-0.096
ying-0.090
apping-0.089
lessly-0.078
Token in
Token ID287
Feature activation-8.24e-01

Pos logit contributions
 Twe+0.072
 ot+0.069
Twe+0.069
 le+0.066
 Nem+0.065
Neg logit contributions
 outage-0.072
ying-0.069
ouncing-0.068
hole-0.067
lessly-0.066
Token the
Token ID262
Feature activation-3.81e-01

Pos logit contributions
 Twe+0.022
 ot+0.022
Twe+0.021
 le+0.020
 Nem+0.020
Neg logit contributions
 outage-0.029
ying-0.028
hole-0.028
ouncing-0.028
 ma-0.027
Token whole
Token ID2187
Feature activation-1.90e-01

Pos logit contributions
 Twe+0.016
Twe+0.015
 ot+0.014
 le+0.014
 Nem+0.014
Neg logit contributions
 Today-0.007
 outage-0.007
 instant-0.007
 ma-0.007
hole-0.007
Token ocean
Token ID9151
Feature activation-1.45e+00

Pos logit contributions
 Twe+0.008
Twe+0.008
 ot+0.008
 le+0.007
 Nem+0.007
Neg logit contributions
 outage-0.004
 Today-0.003
 instant-0.003
hole-0.003
 ma-0.003
Token and
Token ID290
Feature activation+1.50e-01

Pos logit contributions
 outage+0.005
hole+0.005
ying+0.005
ouncing+0.005
rum+0.005
Neg logit contributions
 Twe-0.005
 ot-0.004
 le-0.004
 Nem-0.004
 Bub-0.004
Token shouts
Token ID34757
Feature activation+9.19e-02

Pos logit contributions
 outage+0.004
ying+0.004
hole+0.004
ouncing+0.004
rum+0.004
Neg logit contributions
 Twe-0.006
 ot-0.005
 le-0.005
 Nem-0.005
 se-0.005
Token,
Token ID11
Feature activation+8.05e-02

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
Twe-0.003
 le-0.003
Token "
Token ID366
Feature activation-4.70e-01

Pos logit contributions
 outage+0.003
ying+0.003
hole+0.003
rum+0.003
ouncing+0.003
Neg logit contributions
 Twe-0.002
 le-0.002
 ot-0.002
 Nem-0.002
 Bub-0.002
TokenWhe
Token ID10842
Feature activation+2.28e-01

Pos logit contributions
 Twe+0.017
 ot+0.016
 Nem+0.016
 le+0.015
Twe+0.015
Neg logit contributions
 outage-0.013
ouncing-0.013
hole-0.012
ying-0.012
 ma-0.012
Tokene
Token ID68
Feature activation-4.29e+00

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.009
ying+0.009
lessly+0.009
Neg logit contributions
 Twe-0.005
 ot-0.005
 le-0.005
 Nem-0.004
Twe-0.004
Token!
Token ID0
Feature activation-9.50e-02

Pos logit contributions
 Twe+0.146
 ot+0.144
 Nem+0.138
Twe+0.136
 le+0.133
Neg logit contributions
ouncing-0.122
 outage-0.121
hole-0.115
ying-0.114
 ma-0.113
Token This
Token ID770
Feature activation-3.04e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.003
 le+0.003
Twe+0.003
Neg logit contributions
 outage-0.002
ying-0.002
hole-0.002
ouncing-0.002
lessly-0.002
Token is
Token ID318
Feature activation+8.40e-01

Pos logit contributions
 le+0.009
 Twe+0.009
 ot+0.009
 se+0.008
 pl+0.008
Neg logit contributions
ouncing-0.010
 outage-0.010
ying-0.010
rum-0.010
lessly-0.010
Token fun
Token ID1257
Feature activation+7.56e-01

Pos logit contributions
 outage+0.026
ouncing+0.025
hole+0.025
ying+0.024
rum+0.023
Neg logit contributions
 Twe-0.028
 ot-0.027
 Nem-0.026
 le-0.025
Twe-0.025
Token!
Token ID0
Feature activation-3.48e-01

Pos logit contributions
ouncing+0.028
 outage+0.028
hole+0.027
ying+0.027
itates+0.026
Neg logit contributions
 Twe-0.019
 ot-0.019
 le-0.018
 Nem-0.017
 jew-0.016
Token and
Token ID290
Feature activation+4.38e-02

Pos logit contributions
 Twe+0.002
 ot+0.002
 le+0.002
 Nem+0.002
 se+0.002
Neg logit contributions
 outage-0.002
ying-0.002
ouncing-0.002
hole-0.002
rum-0.002
Token shouts
Token ID34757
Feature activation+1.65e-01

Pos logit contributions
 outage+0.001
ying+0.001
hole+0.001
ouncing+0.001
rum+0.001
Neg logit contributions
 Twe-0.002
 ot-0.002
 le-0.002
 Nem-0.002
 jew-0.001
Token,
Token ID11
Feature activation+7.51e-02

Pos logit contributions
ouncing+0.005
 outage+0.005
ying+0.005
hole+0.005
 ma+0.005
Neg logit contributions
 Twe-0.005
 ot-0.005
Twe-0.005
 Nem-0.005
 le-0.005
Token "
Token ID366
Feature activation-5.00e-01

Pos logit contributions
 outage+0.003
ying+0.003
hole+0.003
rum+0.003
 instant+0.003
Neg logit contributions
 Twe-0.002
 le-0.002
 ot-0.002
 Nem-0.002
 Bub-0.002
TokenWhe
Token ID10842
Feature activation+2.31e-01

Pos logit contributions
 Twe+0.020
 ot+0.020
 Nem+0.019
 le+0.019
 jew+0.018
Neg logit contributions
ouncing-0.011
 outage-0.011
hole-0.011
 ma-0.010
ying-0.010
Tokene
Token ID68
Feature activation-4.29e+00

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.009
ying+0.009
 ma+0.009
Neg logit contributions
 Twe-0.005
 ot-0.005
 le-0.005
 Nem-0.005
Twe-0.005
Token!
Token ID0
Feature activation-1.05e-01

Pos logit contributions
 Twe+0.153
 ot+0.153
 Nem+0.147
Twe+0.146
 jew+0.143
Neg logit contributions
ouncing-0.114
 outage-0.107
hole-0.104
 ma-0.104
rum-0.102
Token That
Token ID1320
Feature activation-1.23e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
 le+0.004
Twe+0.004
Neg logit contributions
 outage-0.003
ying-0.002
hole-0.002
ouncing-0.002
lessly-0.002
Token was
Token ID373
Feature activation+1.46e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 le+0.004
 Nem+0.003
Twe+0.003
Neg logit contributions
 outage-0.004
ying-0.004
ouncing-0.004
rum-0.004
hole-0.004
Token fun
Token ID1257
Feature activation+3.63e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
hole+0.004
ying+0.004
 ma+0.004
Neg logit contributions
 Twe-0.005
 ot-0.004
 Nem-0.004
Twe-0.004
 le-0.004
Token!"
Token ID2474
Feature activation-5.52e-01

Pos logit contributions
 outage+0.013
ouncing+0.013
hole+0.012
ying+0.012
lessly+0.012
Neg logit contributions
 Twe-0.010
 ot-0.010
 le-0.010
 Nem-0.009
 se-0.008
Token slides
Token ID19392
Feature activation-9.97e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
ying+0.004
hole+0.004
rum+0.004
Neg logit contributions
 Twe-0.004
 ot-0.003
 Nem-0.003
 le-0.003
Twe-0.003
Token down
Token ID866
Feature activation-1.50e-01

Pos logit contributions
 Twe+0.037
 ot+0.035
 Nem+0.034
 le+0.034
Twe+0.033
Neg logit contributions
 outage-0.027
ouncing-0.026
ying-0.025
hole-0.025
rum-0.024
Token.
Token ID13
Feature activation+4.32e-01

Pos logit contributions
 ot+0.004
 Twe+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.005
hole-0.005
ouncing-0.005
ying-0.005
lessly-0.005
Token "
Token ID366
Feature activation-1.52e-01

Pos logit contributions
 outage+0.013
ying+0.012
hole+0.012
ouncing+0.012
rum+0.011
Neg logit contributions
 Twe-0.016
 ot-0.015
 Nem-0.015
Twe-0.014
 le-0.014
TokenWhe
Token ID10842
Feature activation-1.00e-01

Pos logit contributions
 Twe+0.005
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.005
ouncing-0.005
ying-0.005
hole-0.005
ows-0.005
Tokene
Token ID68
Feature activation-4.28e+00

Pos logit contributions
 Twe+0.002
 ot+0.002
 le+0.002
 Nem+0.002
Twe+0.002
Neg logit contributions
 outage-0.004
ouncing-0.004
hole-0.004
 ma-0.004
 click-0.004
Token!"
Token ID2474
Feature activation-2.59e-01

Pos logit contributions
 Twe+0.158
 ot+0.154
 Nem+0.148
 le+0.146
Twe+0.146
Neg logit contributions
 outage-0.113
ouncing-0.109
hole-0.107
ying-0.105
 ma-0.101
Token she
Token ID673
Feature activation+6.05e-01

Pos logit contributions
 Twe+0.009
 ot+0.008
 Nem+0.008
 le+0.008
Twe+0.008
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.008
rum-0.007
Token says
Token ID1139
Feature activation+6.48e-03

Pos logit contributions
 outage+0.019
ouncing+0.018
ying+0.018
hole+0.018
rum+0.017
Neg logit contributions
 Twe-0.020
 ot-0.019
 Nem-0.019
 le-0.018
Twe-0.018
Token.
Token ID13
Feature activation+3.16e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
ying+0.000
hole+0.000
ows+0.000
Neg logit contributions
 ot-0.000
 Twe-0.000
Twe-0.000
 Nem-0.000
 le-0.000
Token She
Token ID1375
Feature activation+4.47e-01

Pos logit contributions
 outage+0.010
ying+0.010
hole+0.010
ouncing+0.010
rum+0.009
Neg logit contributions
 Twe-0.011
 Nem-0.010
 ot-0.010
 le-0.009
Twe-0.009
Token how
Token ID703
Feature activation-3.39e-01

Pos logit contributions
 outage+0.010
ouncing+0.010
ying+0.010
hole+0.009
 ma+0.009
Neg logit contributions
 Twe-0.010
 ot-0.010
Twe-0.010
 Nem-0.010
 le-0.009
Token to
Token ID284
Feature activation+4.26e-01

Pos logit contributions
 Twe+0.010
 ot+0.010
Twe+0.010
 Nem+0.009
 le+0.009
Neg logit contributions
 outage-0.011
ouncing-0.011
ying-0.010
lessly-0.010
hole-0.010
Token polish
Token ID25245
Feature activation+3.92e-01

Pos logit contributions
 outage+0.014
ouncing+0.013
hole+0.013
ying+0.013
 ma+0.012
Neg logit contributions
 Twe-0.013
 ot-0.013
 Nem-0.012
 le-0.012
Twe-0.012
Token the
Token ID262
Feature activation+1.79e-01

Pos logit contributions
 outage+0.014
ouncing+0.013
hole+0.013
ying+0.013
 ma+0.013
Neg logit contributions
 Twe-0.011
 ot-0.011
 Nem-0.010
 le-0.010
Twe-0.010
Token tw
Token ID665
Feature activation+4.24e-01

Pos logit contributions
 outage+0.007
ouncing+0.007
ying+0.007
rum+0.007
hole+0.007
Neg logit contributions
 Twe-0.004
 ot-0.004
 le-0.004
 jew-0.004
Twe-0.004
Tokenigs
Token ID9235
Feature activation+2.69e+00

Pos logit contributions
 outage+0.009
ouncing+0.008
hole+0.008
ying+0.008
 ma+0.008
Neg logit contributions
 Twe-0.018
 ot-0.017
 le-0.017
Twe-0.017
 Nem-0.017
Token until
Token ID1566
Feature activation-5.30e-01

Pos logit contributions
 outage+0.091
ouncing+0.089
hole+0.084
 Deal+0.084
rum+0.084
Neg logit contributions
 Twe-0.080
 ot-0.079
 Nem-0.077
 le-0.073
 Bub-0.070
Token they
Token ID484
Feature activation-4.39e-01

Pos logit contributions
 Twe+0.017
Twe+0.017
 ot+0.016
 le+0.015
 Nem+0.015
Neg logit contributions
 outage-0.016
ying-0.016
ouncing-0.015
hole-0.015
 ma-0.015
Token spark
Token ID9009
Feature activation-7.48e-01

Pos logit contributions
 Twe+0.013
 ot+0.013
Twe+0.013
 le+0.012
 Nem+0.012
Neg logit contributions
 outage-0.014
hole-0.014
ying-0.014
ouncing-0.013
lessly-0.013
Tokenled
Token ID992
Feature activation-1.34e+00

Pos logit contributions
 Twe+0.026
Twe+0.025
 ot+0.024
 Nem+0.023
 le+0.023
Neg logit contributions
ying-0.022
ows-0.021
ouncing-0.021
lessly-0.021
hole-0.021
Token like
Token ID588
Feature activation-1.23e-01

Pos logit contributions
 Twe+0.046
 ot+0.045
Twe+0.044
 le+0.042
 Nem+0.042
Neg logit contributions
 outage-0.038
hole-0.037
ouncing-0.037
ying-0.036
lessly-0.035
Token
Token ID198
Feature activation+4.16e-02

Pos logit contributions
 outage+0.000
ouncing+0.000
hole+0.000
ying+0.000
 ma+0.000
Neg logit contributions
 Twe-0.000
 Nem-0.000
 ot-0.000
Twe-0.000
 le-0.000
TokenThe
Token ID464
Feature activation-1.25e-01

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
Twe-0.001
 Nem-0.001
 le-0.001
Token twins
Token ID20345
Feature activation-3.53e-01

Pos logit contributions
 Twe+0.004
Twe+0.004
 Nem+0.004
 ot+0.004
 jew+0.004
Neg logit contributions
 outage-0.004
 ma-0.004
ouncing-0.003
hole-0.003
 click-0.003
Token smiled
Token ID13541
Feature activation-1.22e-01

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.008
 le+0.008
Twe+0.008
Neg logit contributions
 outage-0.014
ouncing-0.013
ying-0.013
hole-0.013
rum-0.013
Token in
Token ID287
Feature activation+3.68e-02

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
 le+0.004
Twe+0.004
Neg logit contributions
 outage-0.003
ouncing-0.003
hole-0.003
ying-0.003
 ma-0.003
Token amaz
Token ID40642
Feature activation+2.22e+00

Pos logit contributions
 outage+0.001
ouncing+0.001
ying+0.001
hole+0.001
ows+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
 le-0.001
Twe-0.001
Tokenement
Token ID972
Feature activation+2.70e-01

Pos logit contributions
 outage+0.051
ying+0.051
hole+0.049
ouncing+0.048
lessly+0.046
Neg logit contributions
 Twe-0.090
 ot-0.088
 Nem-0.084
 le-0.084
Twe-0.084
Token.
Token ID13
Feature activation-4.98e-02

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.009
ying+0.009
 ma+0.009
Neg logit contributions
 Twe-0.008
 ot-0.007
 Nem-0.007
 le-0.007
Twe-0.007
Token What
Token ID1867
Feature activation-2.52e-01

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
 le+0.002
Twe+0.002
Neg logit contributions
 outage-0.001
ying-0.001
ouncing-0.001
hole-0.001
rum-0.001
Token an
Token ID281
Feature activation-2.11e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
Twe+0.006
 Nem+0.006
 le+0.006
Neg logit contributions
 outage-0.010
ouncing-0.009
hole-0.009
ying-0.009
 ma-0.009
Token exciting
Token ID7895
Feature activation+1.29e+00

Pos logit contributions
 Twe+0.007
 ot+0.006
 Nem+0.006
Twe+0.006
 le+0.006
Neg logit contributions
 outage-0.007
ying-0.006
hole-0.006
ouncing-0.006
rum-0.006
Token a
Token ID257
Feature activation-7.58e-01

Pos logit contributions
 ot+0.007
 Twe+0.007
 Nem+0.006
Twe+0.006
 le+0.006
Neg logit contributions
 outage-0.011
hole-0.010
ouncing-0.010
 about-0.010
 ma-0.010
Token time
Token ID640
Feature activation-1.23e-01

Pos logit contributions
 Twe+0.025
 ot+0.025
 Nem+0.024
Twe+0.023
 le+0.023
Neg logit contributions
 outage-0.023
ouncing-0.022
hole-0.021
ying-0.021
 ma-0.021
Token,
Token ID11
Feature activation-5.64e-02

Pos logit contributions
 ot+0.004
 Twe+0.004
Twe+0.004
 le+0.004
 Nem+0.004
Neg logit contributions
ouncing-0.003
 outage-0.003
ying-0.003
 Today-0.003
hole-0.003
Token in
Token ID287
Feature activation+6.45e-03

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
 le+0.002
 Bub+0.002
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
rum-0.002
ying-0.002
Token a
Token ID257
Feature activation+3.26e-02

Pos logit contributions
 outage+0.000
hole+0.000
 ma+0.000
 Today+0.000
 about+0.000
Neg logit contributions
 ot-0.000
 Twe-0.000
Twe-0.000
 Nem-0.000
 jew-0.000
Token small
Token ID1402
Feature activation+2.31e+00

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
 ma+0.001
 Today+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 Nem-0.001
Twe-0.001
 le-0.001
Token house
Token ID2156
Feature activation+1.72e-01

Pos logit contributions
 outage+0.068
ouncing+0.065
hole+0.064
ying+0.063
 ma+0.062
Neg logit contributions
 Twe-0.078
 ot-0.075
 Nem-0.073
Twe-0.072
 le-0.071
Token,
Token ID11
Feature activation-2.94e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
ying+0.005
hole+0.004
 ma+0.004
Neg logit contributions
 Twe-0.006
 ot-0.006
 Nem-0.006
Twe-0.006
 le-0.005
Token there
Token ID612
Feature activation+6.39e-01

Pos logit contributions
 Twe+0.011
 ot+0.011
 Nem+0.010
 le+0.010
Twe+0.010
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.007
rum-0.007
Token lived
Token ID5615
Feature activation-7.00e-01

Pos logit contributions
 outage+0.025
ouncing+0.025
ying+0.025
hole+0.025
 Today+0.024
Neg logit contributions
 Twe-0.014
 ot-0.014
Twe-0.013
 Nem-0.013
 le-0.013
Token a
Token ID257
Feature activation-3.44e-01

Pos logit contributions
 ot+0.022
 Twe+0.021
Twe+0.021
 arom+0.020
 Nem+0.020
Neg logit contributions
 about-0.021
 ma-0.021
aking-0.021
apping-0.020
 Today-0.020
Token a
Token ID257
Feature activation-8.13e-01

Pos logit contributions
 ot+0.008
 Twe+0.008
 Nem+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.012
hole-0.012
ouncing-0.012
 Today-0.012
 about-0.012
Token time
Token ID640
Feature activation-1.28e-01

Pos logit contributions
 Twe+0.027
 ot+0.026
 Nem+0.025
Twe+0.024
 le+0.024
Neg logit contributions
 outage-0.025
ouncing-0.024
hole-0.024
ying-0.023
 ma-0.022
Token,
Token ID11
Feature activation+7.70e-02

Pos logit contributions
 Twe+0.004
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.004
ouncing-0.004
ying-0.004
hole-0.003
 Today-0.003
Token in
Token ID287
Feature activation+1.62e-01

Pos logit contributions
 outage+0.003
ouncing+0.002
hole+0.002
rum+0.002
ems+0.002
Neg logit contributions
 Twe-0.003
 ot-0.002
 Nem-0.002
 le-0.002
 Bub-0.002
Token an
Token ID281
Feature activation+1.35e+00

Pos logit contributions
 outage+0.006
hole+0.006
 ma+0.006
ouncing+0.006
 Today+0.006
Neg logit contributions
 Twe-0.004
 ot-0.004
Twe-0.004
 Nem-0.004
 le-0.003
Token ordinary
Token ID8850
Feature activation+2.32e+00

Pos logit contributions
 outage+0.050
ouncing+0.050
hole+0.047
ows+0.047
ying+0.046
Neg logit contributions
 Twe-0.037
 ot-0.037
 Nem-0.034
 le-0.034
Twe-0.032
Token little
Token ID1310
Feature activation+1.34e+00

Pos logit contributions
 outage+0.063
ouncing+0.060
hole+0.059
 Today+0.059
 ma+0.058
Neg logit contributions
 Twe-0.082
 ot-0.078
Twe-0.077
 Nem-0.077
 le-0.073
Token town
Token ID3240
Feature activation-3.30e-01

Pos logit contributions
 outage+0.043
ouncing+0.042
hole+0.041
ying+0.040
 ma+0.039
Neg logit contributions
 Twe-0.043
 ot-0.041
 Nem-0.039
 le-0.039
Twe-0.039
Token,
Token ID11
Feature activation-2.81e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
Twe+0.011
 le+0.011
Neg logit contributions
 outage-0.009
ouncing-0.009
hole-0.009
ying-0.009
 ma-0.008
Token there
Token ID612
Feature activation+6.59e-01

Pos logit contributions
 Twe+0.011
 ot+0.010
 Nem+0.010
 le+0.009
Twe+0.009
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.007
ying-0.007
rum-0.007
Token lived
Token ID5615
Feature activation-6.92e-01

Pos logit contributions
 outage+0.029
ouncing+0.028
hole+0.028
ying+0.027
 ma+0.027
Neg logit contributions
 Twe-0.013
 ot-0.013
 Nem-0.012
Twe-0.011
 le-0.011
Token the
Token ID262
Feature activation-2.25e-01

Pos logit contributions
 outage+0.026
ouncing+0.025
hole+0.024
ows+0.024
rum+0.024
Neg logit contributions
 Twe-0.017
 Nem-0.016
 ot-0.016
 le-0.015
 Bub-0.014
Token box
Token ID3091
Feature activation-3.22e-01

Pos logit contributions
 Twe+0.007
Twe+0.007
 ot+0.006
 Nem+0.006
 jew+0.006
Neg logit contributions
 outage-0.007
hole-0.007
 ma-0.007
ouncing-0.006
ying-0.006
Token wouldn
Token ID3636
Feature activation+4.58e-01

Pos logit contributions
 Twe+0.008
 ot+0.007
 Nem+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.013
hole-0.013
ouncing-0.012
ying-0.012
ows-0.012
Token't
Token ID470
Feature activation+3.87e-01

Pos logit contributions
 outage+0.013
hole+0.012
ying+0.012
ouncing+0.012
lessly+0.012
Neg logit contributions
 ot-0.016
 Twe-0.015
 jew-0.015
 Nem-0.015
 le-0.015
Token bud
Token ID3600
Feature activation+8.20e-01

Pos logit contributions
ouncing+0.015
 outage+0.014
ying+0.013
hole+0.013
itates+0.013
Neg logit contributions
 Twe-0.011
 ot-0.010
 Nem-0.010
 le-0.009
 se-0.009
Tokenge
Token ID469
Feature activation+2.17e+00

Pos logit contributions
 outage+0.021
ouncing+0.020
ying+0.019
hole+0.019
 ma+0.019
Neg logit contributions
 Twe-0.031
 ot-0.030
 Nem-0.029
 le-0.029
Twe-0.029
Token.
Token ID13
Feature activation+4.43e-03

Pos logit contributions
 outage+0.084
hole+0.082
ouncing+0.081
ying+0.081
rum+0.078
Neg logit contributions
 Twe-0.054
 ot-0.052
Twe-0.049
 Nem-0.048
 le-0.047
Token Just
Token ID2329
Feature activation-4.04e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
ying+0.000
hole+0.000
rum+0.000
Neg logit contributions
 Twe-0.000
 Nem-0.000
 ot-0.000
 le-0.000
Twe-0.000
Token when
Token ID618
Feature activation+7.70e-01

Pos logit contributions
 Twe+0.012
 ot+0.011
 Nem+0.011
 le+0.010
 Bub+0.010
Neg logit contributions
 outage-0.015
ouncing-0.014
ying-0.014
hole-0.014
rum-0.013
Token he
Token ID339
Feature activation-1.14e-01

Pos logit contributions
 outage+0.025
ouncing+0.023
hole+0.023
 ma+0.023
ying+0.023
Neg logit contributions
 ot-0.023
 Twe-0.023
Twe-0.022
 le-0.021
 Nem-0.021
Token was
Token ID373
Feature activation-2.05e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
Twe+0.003
 Nem+0.003
 le+0.003
Neg logit contributions
hole-0.004
 outage-0.003
 ma-0.003
ying-0.003
ouncing-0.003
Token I
Token ID314
Feature activation+9.18e-02

Pos logit contributions
 ot+0.018
 Nem+0.018
 Twe+0.017
 jew+0.017
 le+0.016
Neg logit contributions
 outage-0.015
ouncing-0.014
 ma-0.014
hole-0.014
 Today-0.014
Token look
Token ID804
Feature activation-1.11e+00

Pos logit contributions
 outage+0.002
 Today+0.002
hole+0.002
 click+0.002
 ma+0.002
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
Twe-0.003
 le-0.003
Token at
Token ID379
Feature activation-1.67e-01

Pos logit contributions
 Twe+0.038
 ot+0.036
 Nem+0.036
 le+0.035
Twe+0.033
Neg logit contributions
 outage-0.035
ouncing-0.033
hole-0.032
ying-0.031
rum-0.030
Token it
Token ID340
Feature activation+2.85e-02

Pos logit contributions
 ot+0.005
 Twe+0.005
Twe+0.005
 Nem+0.005
 le+0.005
Neg logit contributions
hole-0.005
 outage-0.005
ying-0.005
ouncing-0.005
 ma-0.005
Token?
Token ID30
Feature activation-3.17e-01

Pos logit contributions
 outage+0.001
rum+0.001
ouncing+0.001
irk+0.001
lessly+0.001
Neg logit contributions
 Twe-0.001
 ot-0.001
 le-0.001
 Nem-0.001
 Bub-0.001
Tokenâ
Token ID22940
Feature activation+1.11e+00

Pos logit contributions
 Twe+0.012
 ot+0.011
Twe+0.011
 Nem+0.011
 le+0.011
Neg logit contributions
 outage-0.009
ouncing-0.008
ying-0.008
hole-0.008
rum-0.007
Token€
Token ID26391
Feature activation-1.47e+00

Pos logit contributions
 outage+0.032
ouncing+0.030
hole+0.029
ying+0.029
lessly+0.029
Neg logit contributions
 Twe-0.039
Twe-0.036
 ot-0.036
 le-0.035
 Nem-0.035
Token Su
Token ID1778
Feature activation+1.61e-02

Pos logit contributions
 Twe+0.048
Twe+0.043
 le+0.042
 ot+0.042
 Nem+0.041
Neg logit contributions
 outage-0.048
ying-0.046
lessly-0.045
rum-0.043
hole-0.043
Tokenzy
Token ID7357
Feature activation-4.84e-01

Pos logit contributions
 outage+0.001
ouncing+0.001
hole+0.001
ying+0.001
 ma+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 Nem-0.000
 le-0.000
Twe-0.000
Token asked
Token ID1965
Feature activation-5.86e-02

Pos logit contributions
 Twe+0.014
 ot+0.013
 Nem+0.012
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.017
ouncing-0.017
hole-0.016
ying-0.016
 ma-0.016
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
 ot+0.002
 Twe+0.002
Twe+0.002
 le+0.002
 Nem+0.002
Neg logit contributions
ying-0.002
ouncing-0.002
 outage-0.002
 ma-0.002
hole-0.002
Token so
Token ID523
Feature activation+1.00e+00

Pos logit contributions
 Twe+0.010
 ot+0.010
 le+0.010
 Nem+0.009
Twe+0.009
Neg logit contributions
 outage-0.010
ouncing-0.010
ying-0.010
hole-0.010
ems-0.010
Token happy
Token ID3772
Feature activation-2.69e-02

Pos logit contributions
 outage+0.031
hole+0.030
ems+0.028
ying+0.028
ouncing+0.028
Neg logit contributions
 Twe-0.036
 ot-0.033
 le-0.033
 Nem-0.033
Twe-0.031
Token to
Token ID284
Feature activation-3.62e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
 le+0.001
Twe+0.001
Neg logit contributions
 outage-0.001
ouncing-0.001
hole-0.001
ying-0.001
 ma-0.001
Token find
Token ID1064
Feature activation-4.41e-01

Pos logit contributions
 Twe+0.013
 ot+0.013
 Nem+0.013
Twe+0.012
 le+0.012
Neg logit contributions
ouncing-0.010
 outage-0.010
hole-0.010
ying-0.010
ows-0.009
Token that
Token ID326
Feature activation+2.74e-01

Pos logit contributions
Twe+0.014
 Twe+0.013
 ot+0.013
 le+0.012
 jew+0.012
Neg logit contributions
 about-0.013
ying-0.013
 outage-0.013
lessly-0.012
hole-0.012
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
 outage+0.009
ouncing+0.009
hole+0.009
ying+0.009
rum+0.009
Neg logit contributions
 Twe-0.008
 ot-0.008
 Nem-0.007
 le-0.007
Twe-0.007
Token kitten
Token ID42143
Feature activation-3.35e-01

Pos logit contributions
 Twe+0.005
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.006
ouncing-0.006
hole-0.006
ying-0.005
 ma-0.005
Token was
Token ID373
Feature activation-3.32e-01

Pos logit contributions
 Twe+0.009
 ot+0.008
Twe+0.008
 Nem+0.008
 le+0.008
Neg logit contributions
 outage-0.013
ouncing-0.012
hole-0.012
ying-0.012
 ma-0.012
Token un
Token ID555
Feature activation-8.66e-01

Pos logit contributions
 Twe+0.012
 ot+0.012
 Nem+0.011
 le+0.011
Twe+0.011
Neg logit contributions
 outage-0.009
ouncing-0.009
hole-0.009
ying-0.008
 ma-0.008
Tokenhar
Token ID9869
Feature activation-6.07e-01

Pos logit contributions
 Twe+0.028
 ot+0.028
 Nem+0.027
 le+0.026
 Bub+0.025
Neg logit contributions
ouncing-0.026
hole-0.026
 outage-0.026
aking-0.025
ying-0.025
Tokenmed
Token ID1150
Feature activation-2.05e+00

Pos logit contributions
 Twe+0.022
 Nem+0.022
 ot+0.021
Twe+0.020
 Bub+0.020
Neg logit contributions
hole-0.018
ouncing-0.017
 outage-0.016
ying-0.016
rum-0.015
Token deaf
Token ID21815
Feature activation+2.13e-01

Pos logit contributions
 Twe+0.003
 ot+0.003
 le+0.003
 Nem+0.003
Twe+0.003
Neg logit contributions
 outage-0.003
ouncing-0.003
hole-0.003
ying-0.003
rum-0.002
Token and
Token ID290
Feature activation+4.87e-01

Pos logit contributions
 outage+0.008
ouncing+0.007
ying+0.007
hole+0.007
 ma+0.007
Neg logit contributions
 Twe-0.006
 ot-0.006
 le-0.005
 Nem-0.005
 jew-0.005
Token couldn
Token ID3521
Feature activation-5.50e-01

Pos logit contributions
 outage+0.015
ouncing+0.015
hole+0.015
ying+0.015
rum+0.014
Neg logit contributions
 Twe-0.016
 ot-0.015
 Nem-0.014
 le-0.014
Twe-0.014
Token't
Token ID470
Feature activation+1.80e-01

Pos logit contributions
 ot+0.018
 Twe+0.018
 Nem+0.017
 jew+0.017
Twe+0.017
Neg logit contributions
 outage-0.016
ouncing-0.015
 Today-0.015
ying-0.015
hole-0.015
Token hear
Token ID3285
Feature activation+1.35e-01

Pos logit contributions
 outage+0.005
hole+0.004
ying+0.004
ouncing+0.004
 ma+0.004
Neg logit contributions
 Twe-0.007
 ot-0.007
 Nem-0.007
 le-0.006
Twe-0.006
Token very
Token ID845
Feature activation+4.67e-02

Pos logit contributions
 outage+0.005
ouncing+0.005
hole+0.005
ying+0.005
 ma+0.005
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.003
Twe-0.003
 le-0.003
Token well
Token ID880
Feature activation-1.24e+00

Pos logit contributions
ouncing+0.001
 outage+0.001
hole+0.001
ying+0.001
rum+0.001
Neg logit contributions
 Twe-0.002
 ot-0.001
 le-0.001
 Nem-0.001
 se-0.001
Token.
Token ID13
Feature activation+7.25e-02

Pos logit contributions
 Twe+0.025
 ot+0.024
 le+0.023
 Nem+0.022
 jew+0.019
Neg logit contributions
 outage-0.052
ouncing-0.052
hole-0.051
 ma-0.050
 Deal-0.050
Token Lily
Token ID20037
Feature activation+9.59e-02

Pos logit contributions
 outage+0.002
ouncing+0.002
ying+0.002
hole+0.002
rum+0.002
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
Twe-0.003
 le-0.002
Token was
Token ID373
Feature activation+1.83e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
hole+0.004
ying+0.004
rum+0.003
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002
Token sad
Token ID6507
Feature activation+1.01e+00

Pos logit contributions
ouncing+0.006
 outage+0.006
hole+0.006
ying+0.006
ems+0.005
Neg logit contributions
 Twe-0.006
 le-0.006
 ot-0.006
 Nem-0.005
 jew-0.005
Token to
Token ID284
Feature activation+3.13e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
Twe+0.004
 Nem+0.004
 le+0.004
Neg logit contributions
 outage-0.005
ouncing-0.005
hole-0.005
ying-0.005
 ma-0.005
Token find
Token ID1064
Feature activation-3.68e-01

Pos logit contributions
 outage+0.010
ouncing+0.010
hole+0.010
ying+0.009
 ma+0.009
Neg logit contributions
 Twe-0.009
 ot-0.009
 Nem-0.009
Twe-0.009
 le-0.009
Token a
Token ID257
Feature activation-3.72e-01

Pos logit contributions
Twe+0.011
 Twe+0.011
 ot+0.011
 le+0.010
 Nem+0.010
Neg logit contributions
 outage-0.012
hole-0.011
 about-0.011
ying-0.011
lessly-0.011
Token chocolate
Token ID11311
Feature activation-1.63e+00

Pos logit contributions
 Twe+0.011
 ot+0.010
 le+0.010
 Nem+0.010
Twe+0.010
Neg logit contributions
ouncing-0.013
 outage-0.013
ying-0.013
hole-0.012
rum-0.012
Token bar
Token ID2318
Feature activation-8.85e-01

Pos logit contributions
 Twe+0.047
 ot+0.046
 Nem+0.044
 le+0.043
Twe+0.043
Neg logit contributions
 outage-0.056
ouncing-0.054
hole-0.053
ying-0.053
 ma-0.051
Token waiting
Token ID4953
Feature activation+7.31e-02

Pos logit contributions
 Twe+0.025
 ot+0.025
 le+0.024
 Nem+0.024
 jew+0.023
Neg logit contributions
ouncing-0.029
 outage-0.029
ying-0.028
hole-0.027
 ma-0.027
Token for
Token ID329
Feature activation+1.18e-01

Pos logit contributions
 outage+0.002
ouncing+0.002
hole+0.002
ying+0.002
rum+0.002
Neg logit contributions
 Twe-0.003
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002
Token her
Token ID607
Feature activation-3.92e-01

Pos logit contributions
 ma+0.004
 about+0.004
rum+0.004
 Today+0.003
ying+0.003
Neg logit contributions
 ot-0.003
Twe-0.003
 Twe-0.003
 le-0.003
 se-0.003
Token!
Token ID0
Feature activation-2.58e-01

Pos logit contributions
 Twe+0.011
 ot+0.010
 Nem+0.010
 le+0.010
Twe+0.010
Neg logit contributions
 outage-0.014
ouncing-0.014
hole-0.014
ying-0.013
 ma-0.013
Token The
Token ID383
Feature activation+9.42e-03

Pos logit contributions
 Twe+0.010
 ot+0.009
 Nem+0.009
Twe+0.009
 le+0.009
Neg logit contributions
 outage-0.007
ouncing-0.007
ying-0.007
hole-0.007
rum-0.006
Token little
Token ID1310
Feature activation+1.87e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
hole+0.000
ying+0.000
 ma+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 Nem-0.000
Twe-0.000
 le-0.000
Token old
Token ID1468
Feature activation+2.26e-01

Pos logit contributions
 outage+0.013
ouncing+0.013
hole+0.013
ying+0.013
 ma+0.012
Neg logit contributions
 Twe-0.013
 ot-0.012
 Nem-0.012
Twe-0.012
 le-0.011
Token scale
Token ID5046
Feature activation-4.63e-02

Pos logit contributions
 outage+0.007
ouncing+0.007
hole+0.007
ying+0.007
rum+0.007
Neg logit contributions
 Twe-0.007
 ot-0.007
 le-0.006
 Nem-0.006
Twe-0.006
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
Twe+0.001
 le+0.001
Neg logit contributions
 outage-0.002
hole-0.002
ouncing-0.002
ying-0.002
 ma-0.002
Token It
Token ID632
Feature activation-1.25e+00

Pos logit contributions
 outage+0.003
ouncing+0.003
ying+0.003
hole+0.003
rum+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
Twe-0.004
 le-0.004
Token weighed
Token ID20261
Feature activation+7.21e-01

Pos logit contributions
 Twe+0.033
 ot+0.032
 Nem+0.031
Twe+0.031
 jew+0.029
Neg logit contributions
 outage-0.044
hole-0.042
ouncing-0.040
 about-0.040
lessly-0.040
Token things
Token ID1243
Feature activation+1.22e+00

Pos logit contributions
 outage+0.025
ouncing+0.024
ying+0.023
hole+0.023
 ma+0.023
Neg logit contributions
 Twe-0.021
 ot-0.020
 Nem-0.019
 le-0.019
Twe-0.019
Token from
Token ID422
Feature activation-6.90e-02

Pos logit contributions
ouncing+0.042
 outage+0.041
rum+0.039
ying+0.039
 Deal+0.039
Neg logit contributions
 Twe-0.036
 ot-0.034
 Nem-0.033
 le-0.032
Twe-0.030
Token near
Token ID1474
Feature activation-5.20e-04

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
Twe+0.002
 le+0.002
Neg logit contributions
 outage-0.003
ouncing-0.002
hole-0.002
ying-0.002
 ma-0.002
Token and
Token ID290
Feature activation+4.44e-01

Pos logit contributions
 Twe+0.000
 ot+0.000
 Nem+0.000
 le+0.000
Twe+0.000
Neg logit contributions
 outage-0.000
ouncing-0.000
ying-0.000
hole-0.000
 ma-0.000
Token far
Token ID1290
Feature activation+3.25e-01

Pos logit contributions
 outage+0.016
ouncing+0.015
hole+0.015
ying+0.015
rum+0.014
Neg logit contributions
 Twe-0.013
 ot-0.012
 Nem-0.012
 le-0.011
Twe-0.011
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
 outage+0.011
ouncing+0.011
 Deal+0.010
ying+0.010
 ma+0.010
Neg logit contributions
 Twe-0.010
 ot-0.009
 Nem-0.009
 le-0.009
Twe-0.008
Token the
Token ID262
Feature activation-2.77e-01

Pos logit contributions
 outage+0.031
hole+0.031
ying+0.030
 about+0.030
ouncing+0.029
Neg logit contributions
 ot-0.026
 Twe-0.026
Twe-0.025
 le-0.024
 Nem-0.023
Token forest
Token ID8222
Feature activation+4.58e-01

Pos logit contributions
 ot+0.007
 Twe+0.007
 le+0.007
 Nem+0.007
 jew+0.007
Neg logit contributions
 outage-0.010
ouncing-0.010
rum-0.010
hole-0.010
ying-0.010
Token.
Token ID13
Feature activation-3.35e-01

Pos logit contributions
 outage+0.018
ouncing+0.017
hole+0.017
ying+0.017
ows+0.017
Neg logit contributions
 Twe-0.011
 ot-0.011
 Nem-0.010
Twe-0.010
 le-0.010
Token As
Token ID1081
Feature activation-1.06e-01

Pos logit contributions
 Twe+0.011
 Nem+0.010
 ot+0.010
 le+0.010
Twe+0.009
Neg logit contributions
 outage-0.011
ying-0.011
ouncing-0.010
hole-0.010
rum-0.010
Token they
Token ID484
Feature activation-1.05e+00

Pos logit contributions
 Twe+0.003
 ot+0.003
Twe+0.003
 le+0.003
 Nem+0.003
Neg logit contributions
 outage-0.004
ouncing-0.003
hole-0.003
ying-0.003
 ma-0.003
Token were
Token ID547
Feature activation-9.17e-01

Pos logit contributions
 Twe+0.028
Twe+0.026
 ot+0.026
 Nem+0.024
 le+0.023
Neg logit contributions
hole-0.038
 outage-0.037
ouncing-0.037
ying-0.037
 ma-0.036
Token walking
Token ID6155
Feature activation-2.18e-01

Pos logit contributions
 Twe+0.021
 le+0.021
 Nem+0.020
 ot+0.020
 pl+0.018
Neg logit contributions
 outage-0.037
ouncing-0.035
hole-0.034
rum-0.034
ying-0.033
Token through
Token ID832
Feature activation-9.49e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
 Nem+0.006
 Bub+0.005
 le+0.005
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
rum-0.008
 Deal-0.008
Token the
Token ID262
Feature activation-2.23e-01

Pos logit contributions
Twe+0.028
 Twe+0.028
 ot+0.027
 Nem+0.026
 le+0.025
Neg logit contributions
 outage-0.030
hole-0.030
 ma-0.028
 Today-0.028
ying-0.028
Token woods
Token ID16479
Feature activation+6.63e-01

Pos logit contributions
 Twe+0.006
 ot+0.006
 Nem+0.005
 le+0.005
Twe+0.005
Neg logit contributions
 outage-0.009
ouncing-0.008
ying-0.008
hole-0.008
rum-0.008
Token,
Token ID11
Feature activation-2.60e-01

Pos logit contributions
 outage+0.022
ouncing+0.022
hole+0.021
ying+0.021
rum+0.020
Neg logit contributions
 Twe-0.020
 ot-0.019
 Nem-0.019
 le-0.018
Twe-0.018
Token He
Token ID679
Feature activation-3.87e-01

Pos logit contributions
 outage+0.001
ouncing+0.001
ying+0.001
hole+0.001
rum+0.001
Neg logit contributions
 Twe-0.001
 Nem-0.001
 ot-0.001
 le-0.001
 Bub-0.001
Token ran
Token ID4966
Feature activation+1.10e-01

Pos logit contributions
 Twe+0.010
 ot+0.009
 Nem+0.009
Twe+0.009
 le+0.009
Neg logit contributions
 outage-0.015
ouncing-0.014
hole-0.014
ying-0.014
 ma-0.014
Token faster
Token ID5443
Feature activation+7.79e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
rum+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
 le-0.004
 Bub-0.003
Token and
Token ID290
Feature activation-8.17e-01

Pos logit contributions
 outage+0.027
ouncing+0.025
 Deal+0.024
ying+0.024
 ma+0.024
Neg logit contributions
 Twe-0.023
 le-0.022
 ot-0.022
 Nem-0.021
 se-0.021
Token faster
Token ID5443
Feature activation+9.06e-02

Pos logit contributions
 Twe+0.032
 ot+0.031
 Nem+0.030
 le+0.030
Twe+0.029
Neg logit contributions
 outage-0.020
ouncing-0.019
ying-0.019
hole-0.019
rum-0.018
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
 outage+0.003
ouncing+0.003
ying+0.003
hole+0.003
 Deal+0.003
Neg logit contributions
 Twe-0.003
 ot-0.003
 le-0.003
 Nem-0.003
 jew-0.002
Token felt
Token ID2936
Feature activation-5.96e-01

Pos logit contributions
 Twe+0.043
 ot+0.041
 Nem+0.041
 le+0.040
Twe+0.039
Neg logit contributions
 outage-0.026
ouncing-0.025
ying-0.024
hole-0.024
rum-0.023
Token very
Token ID845
Feature activation-8.69e-01

Pos logit contributions
 Twe+0.019
 ot+0.019
Twe+0.018
 Nem+0.018
 le+0.018
Neg logit contributions
 outage-0.018
ouncing-0.018
hole-0.017
ying-0.017
lessly-0.017
Token powerful
Token ID3665
Feature activation-1.32e+00

Pos logit contributions
 Twe+0.032
 ot+0.031
 Nem+0.030
 le+0.029
Twe+0.029
Neg logit contributions
 outage-0.024
ouncing-0.023
hole-0.022
ying-0.022
 ma-0.021
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
 Twe+0.030
 ot+0.029
 Nem+0.027
 le+0.027
 jew+0.025
Neg logit contributions
 outage-0.054
ouncing-0.053
hole-0.051
ying-0.051
 ma-0.050
Token He
Token ID679
Feature activation-4.08e-01

Pos logit contributions
 Twe+0.006
 Nem+0.005
 ot+0.005
 le+0.005
 Bub+0.005
Neg logit contributions
 outage-0.005
ouncing-0.004
hole-0.004
ying-0.004
rum-0.004
Token proud
Token ID6613
Feature activation-5.78e-01

Pos logit contributions
 outage+0.031
hole+0.031
ouncing+0.030
ying+0.029
 Today+0.027
Neg logit contributions
 Twe-0.050
 ot-0.048
 Nem-0.047
 le-0.046
Twe-0.045
Token of
Token ID286
Feature activation-5.95e-01

Pos logit contributions
 Twe+0.021
 ot+0.020
 Nem+0.019
 le+0.019
Twe+0.019
Neg logit contributions
 outage-0.016
ouncing-0.016
hole-0.015
ying-0.015
 ma-0.015
Token himself
Token ID2241
Feature activation-5.50e-01

Pos logit contributions
 Twe+0.018
 ot+0.018
 Nem+0.017
Twe+0.017
 le+0.017
Neg logit contributions
 outage-0.019
ouncing-0.019
hole-0.019
ying-0.018
 ma-0.018
Token for
Token ID329
Feature activation+6.06e-01

Pos logit contributions
 Twe+0.015
 ot+0.015
 le+0.014
 Nem+0.014
 Bub+0.013
Neg logit contributions
 outage-0.020
ouncing-0.019
hole-0.018
ying-0.018
itates-0.018
Token using
Token ID1262
Feature activation+1.18e-01

Pos logit contributions
 outage+0.020
ouncing+0.020
hole+0.019
 Today+0.018
ows+0.018
Neg logit contributions
 Twe-0.020
 ot-0.019
 Nem-0.019
 le-0.018
 jew-0.018
Token his
Token ID465
Feature activation-8.00e-01

Pos logit contributions
 outage+0.005
ouncing+0.005
ying+0.004
hole+0.004
 ma+0.004
Neg logit contributions
 Twe-0.003
 ot-0.003
 Nem-0.003
 le-0.003
Twe-0.002
Token sword
Token ID8429
Feature activation+3.78e-01

Pos logit contributions
 Twe+0.030
 ot+0.030
 Nem+0.029
 le+0.028
Twe+0.028
Neg logit contributions
 outage-0.020
ouncing-0.020
hole-0.019
ying-0.019
 ma-0.018
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
 outage+0.014
ouncing+0.014
ying+0.014
hole+0.014
 ma+0.013
Neg logit contributions
 Twe-0.009
 ot-0.009
 Nem-0.008
 le-0.008
Twe-0.008
Token From
Token ID3574
Feature activation+7.95e-01

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.003
 ma+0.003
Neg logit contributions
 Twe-0.004
 ot-0.004
 Nem-0.004
 le-0.004
Twe-0.004
Token then
Token ID788
Feature activation-2.03e-01

Pos logit contributions
 outage+0.026
ouncing+0.025
hole+0.025
ying+0.024
 ma+0.023
Neg logit contributions
 Twe-0.025
 ot-0.024
 Nem-0.023
 le-0.023
Twe-0.023
Token on
Token ID319
Feature activation+1.19e+00

Pos logit contributions
 le+0.005
 Twe+0.005
B+0.005
 ot+0.005
 B+0.005
Neg logit contributions
 outage-0.008
ows-0.007
hole-0.007
 fuss-0.007
ouncing-0.007
Token end
Token ID886
Feature activation+5.45e-01

Pos logit contributions
 outage+0.033
ouncing+0.033
ying+0.032
hole+0.031
rum+0.030
Neg logit contributions
 ot-0.026
 Twe-0.025
 le-0.024
 Nem-0.024
 jew-0.023
Token,
Token ID11
Feature activation+7.83e-01

Pos logit contributions
 outage+0.018
ouncing+0.018
hole+0.018
ying+0.017
rum+0.017
Neg logit contributions
 Twe-0.016
 ot-0.016
 Nem-0.015
 le-0.015
Twe-0.014
Token he
Token ID339
Feature activation+2.10e-01

Pos logit contributions
ouncing+0.032
 outage+0.032
ows+0.031
hole+0.030
ying+0.029
Neg logit contributions
 Twe-0.019
 Nem-0.017
 ot-0.017
 jew-0.016
 le-0.016
Token was
Token ID373
Feature activation+2.57e-01

Pos logit contributions
 outage+0.007
ouncing+0.006
hole+0.006
ying+0.006
 ma+0.006
Neg logit contributions
 Twe-0.007
 ot-0.006
Twe-0.006
 Nem-0.006
 jew-0.006
Token happy
Token ID3772
Feature activation+5.24e-01

Pos logit contributions
 outage+0.008
ouncing+0.008
hole+0.008
ying+0.008
 Today+0.008
Neg logit contributions
 Twe-0.008
 ot-0.008
 le-0.008
 Nem-0.008
 se-0.007
Token he
Token ID339
Feature activation-5.04e-01

Pos logit contributions
 outage+0.021
ouncing+0.021
hole+0.021
ying+0.021
ows+0.020
Neg logit contributions
 Twe-0.012
 ot-0.011
 Nem-0.011
 le-0.011
 jew-0.010
Token did
Token ID750
Feature activation-8.23e-01

Pos logit contributions
 Twe+0.018
 ot+0.018
Twe+0.016
 Nem+0.016
 le+0.016
Neg logit contributions
 outage-0.014
ouncing-0.014
hole-0.013
ying-0.013
lessly-0.013
Token.
Token ID13
Feature activation-7.04e-02

Pos logit contributions
 Twe+0.021
 ot+0.020
 le+0.019
 Nem+0.019
 jew+0.019
Neg logit contributions
 outage-0.031
ouncing-0.031
hole-0.030
ying-0.029
 Today-0.029
Token The
Token ID383
Feature activation+1.79e-03

Pos logit contributions
 Twe+0.002
 Nem+0.002
Twe+0.002
 ot+0.002
 le+0.002
Neg logit contributions
 outage-0.002
ouncing-0.002
ying-0.002
ems-0.002
hole-0.002
Token sunshine
Token ID34488
Feature activation-4.67e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
hole+0.000
ying+0.000
 ma+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 Nem-0.000
 le-0.000
Twe-0.000
Token felt
Token ID2936
Feature activation-8.79e-02

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.008
Twe+0.008
 le+0.008
Neg logit contributions
 outage-0.020
ouncing-0.020
hole-0.019
ying-0.019
 ma-0.019
Token it
Token ID340
Feature activation-3.77e-01

Pos logit contributions
 Twe+0.011
 ot+0.011
 Nem+0.010
 le+0.010
 se+0.009
Neg logit contributions
hole-0.011
ouncing-0.011
 outage-0.011
ying-0.011
 Today-0.011
Token was
Token ID373
Feature activation-2.76e-01

Pos logit contributions
 Twe+0.012
Twe+0.011
 ot+0.011
 jew+0.011
 Nem+0.011
Neg logit contributions
 outage-0.012
ouncing-0.011
ying-0.011
lessly-0.011
ows-0.011
Token so
Token ID523
Feature activation+6.90e-02

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.009
Twe+0.009
 le+0.009
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.007
 ma-0.007
Token sm
Token ID895
Feature activation-1.61e+00

Pos logit contributions
 outage+0.002
lessly+0.002
ouncing+0.002
 ma+0.002
ying+0.002
Neg logit contributions
 Twe-0.003
Twe-0.003
 ot-0.003
 jew-0.002
 Nem-0.002
Tokenelly
Token ID6148
Feature activation-1.21e+00

Pos logit contributions
 Twe+0.069
 ot+0.067
 Nem+0.065
 le+0.064
Twe+0.064
Neg logit contributions
 outage-0.034
ouncing-0.032
hole-0.031
ying-0.031
 ma-0.029
Token!
Token ID0
Feature activation-8.18e-01

Pos logit contributions
 Twe+0.028
 ot+0.027
 Nem+0.025
 le+0.025
Twe+0.025
Neg logit contributions
 outage-0.049
ouncing-0.048
hole-0.047
ying-0.047
 ma-0.045
Token One
Token ID1881
Feature activation+8.86e-01

Pos logit contributions
 ot+0.027
 Twe+0.027
 le+0.026
Twe+0.025
 jew+0.025
Neg logit contributions
 outage-0.023
 Today-0.022
ouncing-0.022
hole-0.022
 ma-0.022
Token day
Token ID1110
Feature activation-3.27e-01

Pos logit contributions
 outage+0.028
ouncing+0.027
hole+0.027
ying+0.026
 ma+0.025
Neg logit contributions
 Twe-0.029
 ot-0.028
 Nem-0.026
Twe-0.026
 le-0.026
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
Twe+0.013
 ot+0.013
 Twe+0.013
 jew+0.012
 Nem+0.012
Neg logit contributions
ouncing-0.007
 Today-0.007
 outage-0.007
 ma-0.007
 about-0.007
Token someone
Token ID2130
Feature activation+1.01e-01

Pos logit contributions
Twe+0.003
 ot+0.003
 Twe+0.003
 jew+0.003
 Nem+0.003
Neg logit contributions
 ma-0.004
 outage-0.004
 click-0.004
 Today-0.004
hole-0.003
Token had
Token ID550
Feature activation-1.78e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
ying+0.004
hole+0.003
 ma+0.003
Neg logit contributions
 Twe-0.003
 ot-0.003
Twe-0.002
 Nem-0.002
 le-0.002
Token all
Token ID477
Feature activation+4.93e-01

Pos logit contributions
 Twe+0.005
 ot+0.005
 Nem+0.005
 le+0.005
Twe+0.004
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.008
rum-0.007
Token kind
Token ID1611
Feature activation-1.52e-01

Pos logit contributions
 outage+0.021
hole+0.020
ouncing+0.020
 Deal+0.020
itates+0.020
Neg logit contributions
 ot-0.011
 Twe-0.011
 le-0.010
 Nem-0.010
 se-0.009
Token of
Token ID286
Feature activation-7.67e-01

Pos logit contributions
 Twe+0.006
Twe+0.006
 ot+0.005
 Nem+0.005
 Bub+0.005
Neg logit contributions
 outage-0.004
ouncing-0.004
 about-0.004
ying-0.004
hole-0.004
Token fun
Token ID1257
Feature activation+1.26e-01

Pos logit contributions
 Twe+0.019
 ot+0.019
 Nem+0.017
 le+0.017
Twe+0.017
Neg logit contributions
 outage-0.030
ouncing-0.029
hole-0.029
ying-0.028
 ma-0.027
Token things
Token ID1243
Feature activation+7.29e-02

Pos logit contributions
 outage+0.004
hole+0.004
ouncing+0.004
ying+0.004
 ma+0.004
Neg logit contributions
 Twe-0.004
 ot-0.004
 le-0.004
 Nem-0.004
Twe-0.003
Token-
Token ID12
Feature activation-3.68e+00

Pos logit contributions
 outage+0.003
ouncing+0.003
hole+0.003
ying+0.002
 ma+0.002
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002
Token they
Token ID484
Feature activation-5.18e-01

Pos logit contributions
 ot+0.102
 jew+0.102
 Twe+0.098
 Nem+0.098
 Bub+0.092
Neg logit contributions
ouncing-0.131
ying-0.128
 outage-0.125
lessly-0.118
ows-0.118
Token ran
Token ID4966
Feature activation-3.66e-01

Pos logit contributions
 Twe+0.017
 ot+0.017
Twe+0.016
 le+0.016
 Nem+0.016
Neg logit contributions
 outage-0.015
ouncing-0.014
hole-0.014
lessly-0.014
ying-0.014
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
 Twe+0.013
 ot+0.012
 Nem+0.012
 le+0.012
Twe+0.012
Neg logit contributions
 outage-0.011
ouncing-0.010
hole-0.010
ying-0.010
 ma-0.010
Token jumped
Token ID11687
Feature activation-1.78e-02

Pos logit contributions
 Twe+0.007
 ot+0.006
 le+0.006
 Nem+0.006
Twe+0.006
Neg logit contributions
 outage-0.007
ying-0.006
rum-0.006
hole-0.006
ouncing-0.006
Token and
Token ID290
Feature activation-1.93e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
Twe+0.001
 le+0.001
Neg logit contributions
 outage-0.000
ouncing-0.000
hole-0.000
ying-0.000
 ma-0.000
Token play
Token ID711
Feature activation-3.72e-01

Pos logit contributions
 outage+0.000
ouncing+0.000
hole+0.000
ying+0.000
 ma+0.000
Neg logit contributions
 Twe-0.000
 ot-0.000
 Nem-0.000
Twe-0.000
 le-0.000
Token a
Token ID257
Feature activation-1.17e+00

Pos logit contributions
 Twe+0.011
 ot+0.011
 Nem+0.010
 le+0.010
Twe+0.010
Neg logit contributions
 outage-0.013
ouncing-0.012
hole-0.012
ying-0.012
 ma-0.012
Token game
Token ID983
Feature activation+4.33e-01

Pos logit contributions
 Twe+0.042
 ot+0.041
 Nem+0.040
Twe+0.038
 jew+0.037
Neg logit contributions
 outage-0.032
hole-0.029
ouncing-0.028
 ma-0.028
 click-0.027
Token of
Token ID286
Feature activation-5.65e-01

Pos logit contributions
 outage+0.014
ouncing+0.014
hole+0.014
ying+0.014
 ma+0.013
Neg logit contributions
 Twe-0.013
 ot-0.013
 Nem-0.012
Twe-0.012
 le-0.012
Token tug
Token ID27762
Feature activation-2.71e-01

Pos logit contributions
 Twe+0.017
 ot+0.017
 Nem+0.016
 le+0.016
Twe+0.016
Neg logit contributions
 outage-0.019
ouncing-0.018
hole-0.018
ying-0.018
 ma-0.017
Token-
Token ID12
Feature activation-3.12e+00

Pos logit contributions
 Twe+0.010
 ot+0.010
 le+0.009
 Nem+0.009
Twe+0.009
Neg logit contributions
 outage-0.008
ouncing-0.007
hole-0.007
 ma-0.007
 Today-0.007
Tokeno
Token ID78
Feature activation-6.79e-01

Pos logit contributions
 ot+0.140
 Twe+0.136
 Nem+0.133
 jew+0.130
Twe+0.125
Neg logit contributions
ouncing-0.060
 outage-0.059
hole-0.058
ying-0.058
lessly-0.055
Token-
Token ID12
Feature activation-3.06e+00

Pos logit contributions
 Twe+0.021
 ot+0.021
 le+0.020
 Nem+0.020
Twe+0.019
Neg logit contributions
 outage-0.022
ouncing-0.021
hole-0.020
ying-0.020
 ma-0.020
Tokenwar
Token ID5767
Feature activation-2.25e-02

Pos logit contributions
 ot+0.137
 Twe+0.131
 Nem+0.128
 jew+0.127
 Bub+0.120
Neg logit contributions
ouncing-0.059
hole-0.056
 outage-0.056
lessly-0.055
ying-0.054
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 Twe+0.001
 ot+0.001
 Nem+0.001
Twe+0.001
 le+0.001
Neg logit contributions
 outage-0.001
ouncing-0.001
hole-0.001
ying-0.001
ows-0.001
Token
Token ID198
Feature activation-3.25e-01

Pos logit contributions
 Twe+0.011
 ot+0.011
 Nem+0.011
Twe+0.010
 le+0.010
Neg logit contributions
 outage-0.009
ouncing-0.009
hole-0.009
ying-0.009
 ma-0.008
Token calm
Token ID9480
Feature activation-1.91e-01

Pos logit contributions
 outage+0.015
ouncing+0.014
 ma+0.013
hole+0.013
ying+0.013
Neg logit contributions
 ot-0.014
 Twe-0.014
 Nem-0.013
 le-0.013
Twe-0.013
Token and
Token ID290
Feature activation-1.03e+00

Pos logit contributions
 Twe+0.006
 ot+0.006
 Nem+0.005
 le+0.005
 jew+0.005
Neg logit contributions
 outage-0.007
ouncing-0.006
 ma-0.006
hole-0.006
ying-0.006
Token listen
Token ID6004
Feature activation-9.58e-01

Pos logit contributions
 Twe+0.032
 ot+0.031
 le+0.029
 Nem+0.029
 se+0.028
Neg logit contributions
 outage-0.033
ouncing-0.033
hole-0.033
ying-0.033
rum-0.032
Token to
Token ID284
Feature activation-3.38e-01

Pos logit contributions
 Twe+0.025
 ot+0.024
 Nem+0.023
 le+0.022
Twe+0.022
Neg logit contributions
 outage-0.036
ouncing-0.035
hole-0.034
ying-0.034
 ma-0.033
Token grown
Token ID7334
Feature activation-4.31e-01

Pos logit contributions
 Twe+0.009
 ot+0.009
 Nem+0.008
 le+0.008
Twe+0.008
Neg logit contributions
 outage-0.013
ouncing-0.012
hole-0.012
ying-0.012
 ma-0.012
Token-
Token ID12
Feature activation-3.24e+00

Pos logit contributions
 Twe+0.012
 ot+0.012
 Nem+0.011
Twe+0.011
 le+0.010
Neg logit contributions
 outage-0.016
ying-0.015
ouncing-0.015
hole-0.015
rum-0.015
Tokenups
Token ID4739
Feature activation+7.30e-01

Pos logit contributions
 Twe+0.110
 ot+0.109
 Nem+0.105
 jew+0.102
 Bub+0.100
Neg logit contributions
ouncing-0.098
ying-0.097
 outage-0.093
aking-0.089
hole-0.085
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
 outage+0.028
ouncing+0.027
 ma+0.026
hole+0.026
rum+0.026
Neg logit contributions
 Twe-0.017
 ot-0.017
 Nem-0.016
 le-0.016
 jew-0.014
Token The
Token ID383
Feature activation-2.55e-01

Pos logit contributions
 Twe+0.008
 ot+0.007
 Nem+0.007
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.008
ouncing-0.007
hole-0.007
ying-0.007
 ma-0.007
Token end
Token ID886
Feature activation+8.63e-02

Pos logit contributions
 Twe+0.008
 ot+0.008
 Nem+0.008
Twe+0.007
 le+0.007
Neg logit contributions
 outage-0.008
ouncing-0.008
hole-0.008
ying-0.008
 ma-0.007
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
ouncing+0.004
hole+0.004
ying+0.004
 ma+0.004
 outage+0.004
Neg logit contributions
 Twe-0.001
 le-0.001
 ot-0.001
 Nem-0.001
Twe-0.001
Token She
Token ID1375
Feature activation-1.84e-01

Pos logit contributions
 outage+0.004
ying+0.004
hole+0.004
rum+0.004
ouncing+0.004
Neg logit contributions
 Twe-0.005
 Nem-0.004
 Bub-0.004
 ot-0.004
Twe-0.004
Token loved
Token ID6151
Feature activation+1.38e-01

Pos logit contributions
 ot+0.007
 Twe+0.006
 Nem+0.006
 jew+0.006
Twe+0.006
Neg logit contributions
 about-0.005
ouncing-0.004
 outage-0.004
itates-0.004
 has-0.004
Token to
Token ID284
Feature activation+8.46e-01

Pos logit contributions
 outage+0.004
ouncing+0.004
ying+0.004
 about+0.004
 ma+0.004
Neg logit contributions
 Twe-0.004
Twe-0.004
 ot-0.004
 Nem-0.004
 Bub-0.004
Token play
Token ID711
Feature activation-1.31e-01

Pos logit contributions
 outage+0.027
 ma+0.026
 Today+0.026
ouncing+0.025
 click+0.025
Neg logit contributions
 Twe-0.026
 ot-0.025
 Nem-0.024
Twe-0.024
 le-0.022
Token hide
Token ID7808
Feature activation+9.53e-01

Pos logit contributions
 Twe+0.004
 ot+0.004
 Nem+0.004
Twe+0.004
 le+0.004
Neg logit contributions
 outage-0.004
ouncing-0.004
ying-0.004
hole-0.004
 ma-0.004
Token-
Token ID12
Feature activation-2.99e+00

Pos logit contributions
ying+0.023
ows+0.023
ouncing+0.023
 about+0.022
lessly+0.021
Neg logit contributions
 Twe-0.034
 ot-0.034
 Nem-0.033
Twe-0.033
 Bub-0.032
Tokenand
Token ID392
Feature activation+8.07e-01

Pos logit contributions
 ot+0.165
 Twe+0.162
 Nem+0.162
 le+0.152
 jew+0.152
Neg logit contributions
ouncing-0.024
 outage-0.024
aking-0.021
ying-0.019
ows-0.018
Token-
Token ID12
Feature activation-3.37e+00

Pos logit contributions
ouncing+0.032
ying+0.031
ows+0.030
 outage+0.030
hole+0.029
Neg logit contributions
 ot-0.019
 Twe-0.018
 Nem-0.018
Twe-0.016
 Bub-0.015
Tokenseek
Token ID36163
Feature activation-6.38e-01

Pos logit contributions
 ot+0.124
 Nem+0.117
 Twe+0.116
 jew+0.107
 le+0.107
Neg logit contributions
ouncing-0.095
 outage-0.094
ows-0.087
ying-0.087
aking-0.085
Token with
Token ID351
Feature activation-1.41e+00

Pos logit contributions
 Twe+0.022
 ot+0.021
 Nem+0.020
Twe+0.020
 le+0.020
Neg logit contributions
 outage-0.019
ouncing-0.018
ying-0.018
hole-0.018
 about-0.017
Token her
Token ID607
Feature activation-2.76e-01

Pos logit contributions
pre+0.055
Twe+0.053
 ot+0.053
 Twe+0.052
 Nem+0.050
Neg logit contributions
 about-0.031
 mat-0.026
 ma-0.025
 Today-0.025
 Lisa-0.025
Tokenara
Token ID3301
Feature activation-7.95e-01

Pos logit contributions
 Twe+0.053
 ot+0.052
Twe+0.049
 Nem+0.048
 le+0.047
Neg logit contributions
hole-0.031
ouncing-0.031
ying-0.030
 ma-0.030
 outage-0.030
Token loves
Token ID10408
Feature activation-1.12e+00

Pos logit contributions
 Twe+0.032
 ot+0.031
 Nem+0.030
Twe+0.030
 le+0.030
Neg logit contributions
 outage-0.018
ouncing-0.018
hole-0.017
ying-0.017
 ma-0.016
Token to
Token ID284
Feature activation+6.01e-01

Pos logit contributions
Twe+0.037
 Twe+0.035
 jew+0.033
 ot+0.033
 Bub+0.032
Neg logit contributions
 ma-0.030
ying-0.029
ouncing-0.029
 about-0.028
 outage-0.028
Token play
Token ID711
Feature activation-3.54e-01

Pos logit contributions
 outage+0.020
ouncing+0.019
 Today+0.019
 ma+0.018
hole+0.018
Neg logit contributions
 Twe-0.018
 ot-0.017
Twe-0.017
 Nem-0.016
 le-0.016
Token dress
Token ID6576
Feature activation-2.35e-01

Pos logit contributions
 Twe+0.013
Twe+0.012
 ot+0.012
 Nem+0.012
 le+0.012
Neg logit contributions
ying-0.008
 about-0.008
 ma-0.007
 Today-0.007
iving-0.007
Token-
Token ID12
Feature activation-3.50e+00

Pos logit contributions
 Nem+0.006
 Twe+0.006
 ot+0.006
 Bub+0.006
Twe+0.006
Neg logit contributions
ying-0.009
ouncing-0.009
ows-0.008
 about-0.008
hole-0.008
Tokenup
Token ID929
Feature activation-5.85e-02

Pos logit contributions
 ot+0.101
 Nem+0.097
 Twe+0.090
 jew+0.087
 cuc+0.085
Neg logit contributions
 outage-0.120
ouncing-0.116
ying-0.114
ows-0.113
aking-0.111
Token with
Token ID351
Feature activation-1.07e+00

Pos logit contributions
 Twe+0.002
 ot+0.002
 Nem+0.002
Twe+0.002
 le+0.001
Neg logit contributions
 outage-0.002
ouncing-0.002
hole-0.002
ying-0.002
ows-0.002
Token her
Token ID607
Feature activation+9.95e-02

Pos logit contributions
pre+0.044
Twe+0.042
ho+0.042
 ot+0.042
mer+0.041
Neg logit contributions
 about-0.019
 Lisa-0.013
 ma-0.013
aps-0.013
 Today-0.013
Token costumes
Token ID24138
Feature activation+1.09e-01

Pos logit contributions
 outage+0.003
hole+0.002
 ma+0.002
ouncing+0.002
 Today+0.002
Neg logit contributions
 Twe-0.004
Twe-0.004
 Nem-0.003
 ot-0.003
 le-0.003
Token.
Token ID13
Feature activation+5.16e-02

Pos logit contributions
 outage+0.005
ouncing+0.004
hole+0.004
ying+0.004
 ma+0.004
Neg logit contributions
 Twe-0.002
 ot-0.002
 Nem-0.002
 le-0.002
Twe-0.002