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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases that require verification or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.89
     ویکی‌پدیای
    -0.81
    AsUp
    -0.80
     ||=
    -0.72
    críbete
    -0.67
     beginnetje
    -0.66
     بيها
    -0.66
    sizeCache
    -0.65
    haustible
    -0.65
    SharedDtor
    -0.64
    POSITIVE LOGITS
    Confirm
    1.02
     Confirm
    0.99
    confirm
    0.92
    Accept
    0.86
     confirm
    0.81
    accept
    0.80
    ="#"
    0.71
     Accept
    0.68
    CONFIRM
    0.68
     confirming
    0.67
    Act Density 0.146%

    No Known Activations