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

    Neuronpedia

    INDEX
    Explanations

    phrases and instances that indicate a command or request

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¢ĭ
    -0.16
    ifi
    -0.15
    anou
    -0.15
    .tp
    -0.15
    chl
    -0.14
    оÑĢаз
    -0.14
    groundColor
    -0.14
    GROUND
    -0.14
    qh
    -0.14
    Ī¬
    -0.14
    POSITIVE LOGITS
    ushima
    0.16
     ActionTypes
    0.15
    giene
    0.14
    ÑĢад
    0.14
    ÑĢÑı
    0.14
    adge
    0.14
    ÑĢади
    0.14
    odon
    0.14
     punch
    0.14
    ÄĽt
    0.14
    Act Density 0.003%

    No Known Activations