Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions indicating the passage of time or continuous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingt
    -0.21
    ãģĬãĤĬ
    -0.16
    shot
    -0.16
    elerik
    -0.15
    олн
    -0.14
    role
    -0.14
     AccessToken
    -0.14
     немÑĥ
    -0.14
     вдÑĢÑĥг
    -0.13
    ossible
    -0.13
    POSITIVE LOGITS
     then
    0.31
     childhood
    0.28
     they
    0.26
     we
    0.25
     there
    0.25
     inception
    0.23
     it
    0.23
     its
    0.23
    forth
    0.22
     nobody
    0.22
    Act Density 0.045%

    No Known Activations