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

    Neuronpedia

    INDEX
    Explanations

    actions related to existence and consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimés
    -0.59
    TypedDataSet
    -0.59
    moine
    -0.56
    multirow
    -0.53
    +#+#
    -0.51
     Empieza
    -0.51
    脚注の使い方
    -0.51
     ويكيپيديا
    -0.50
    riae
    -0.48
    Publica
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.58
    おり
    0.56
     nahilalakip
    0.56
    しまう
    0.55
    rawDesc
    0.55
    しまい
    0.54
     GenerationType
    0.54
    以来
    0.51
    からは
    0.51
    DockStyle
    0.50
    Act Density 0.139%

    No Known Activations