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

    Neuronpedia

    INDEX
    Explanations

    actions and physical responses associated with surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sass
    -0.16
    878
    -0.14
    133
    -0.14
     chuck
    -0.14
    bw
    -0.14
    ICODE
    -0.14
    arel
    -0.14
    ury
    -0.14
    flag
    -0.14
     æ°
    -0.14
    POSITIVE LOGITS
    WSC
    0.16
    ripp
    0.15
    stanov
    0.15
    noch
    0.14
     pornstar
    0.14
     buffs
    0.14
     offen
    0.14
    ovnÄĽ
    0.14
    صÙģ
    0.14
    FTA
    0.14
    Act Density 0.361%

    No Known Activations