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

    Neuronpedia

    INDEX
    Explanations

    the characteristics and specifications of various templates and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -piece
    -0.17
    unic
    -0.17
    ohl
    -0.16
    ourd
    -0.15
    untas
    -0.15
     Vladim
    -0.15
     piece
    -0.15
    GIN
    -0.15
     Piece
    -0.14
    à¸Ĺาà¸ĩ
    -0.14
    POSITIVE LOGITS
     format
    0.23
     formats
    0.23
     formato
    0.21
     form
    0.20
    formats
    0.17
     style
    0.17
    ahoma
    0.17
    amu
    0.16
     forma
    0.16
     styles
    0.16
    Act Density 0.187%

    No Known Activations