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

    Neuronpedia

    INDEX
    Explanations

    fragmented or incomplete phrases indicating uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    참고
    -0.60
    出版年
    -0.60
     MNRAS
    -0.60
    also
    -0.55
    QMetaType
    -0.54
     发表于
    -0.53
    WriteLiteral
    -0.53
    taxia
    -0.53
     Ornith
    -0.53
     ulasan
    -0.52
    POSITIVE LOGITS
    CloseOperation
    0.86
     thousands
    0.86
     hundreds
    0.84
     typelib
    0.82
     millions
    0.79
    CHANT
    0.72
     Signalez
    0.69
     виправивши
    0.67
     hundred
    0.66
     million
    0.64
    Act Density 0.158%

    No Known Activations