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

    Neuronpedia

    INDEX
    Explanations

    expressions related to evidence, analysis, and documentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.83
     ویکی‌پدیا
    -0.76
    rungsseite
    -0.73
    !*\
    -0.73
     Efq
    -0.72
     Signalez
    -0.71
     "..\..\..\
    -0.68
     GoogleFonts
    -0.68
     '\\;'
    -0.66
    脚注の使い方
    -0.64
    POSITIVE LOGITS
     Alembic
    0.49
     aisladas
    0.47
     configuração
    0.47
     disponíveis
    0.46
    elsa
    0.44
    isticated
    0.43
    zzly
    0.41
     tôi
    0.40
    googleapis
    0.40
    timo
    0.40
    Act Density 0.151%

    No Known Activations