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

    Neuronpedia

    INDEX
    Explanations

    references to methodologies or methods used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lets
    -0.20
    teen
    -0.17
    let
    -0.16
    .makeText
    -0.15
    лиÑĨ
    -0.15
    indh
    -0.15
    lexer
    -0.14
    deen
    -0.14
    á»įng
    -0.14
    ween
    -0.14
    POSITIVE LOGITS
    ical
    0.34
    ological
    0.33
    ically
    0.31
    ologies
    0.30
    ologically
    0.27
    ICAL
    0.23
    ology
    0.22
    ologie
    0.22
    论
    0.21
    ologic
    0.21
    Act Density 0.036%

    No Known Activations