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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal classifications and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zas
    -0.17
    gger
    -0.15
    atto
    -0.14
    anno
    -0.14
    warts
    -0.14
    unct
    -0.14
    oken
    -0.14
    cko
    -0.13
    brane
    -0.13
    juan
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    icut
    0.17
    SOR
    0.16
    LEV
    0.15
    amas
    0.15
    piel
    0.15
    ColumnInfo
    0.15
    ElementType
    0.15
    ages
    0.14
    Ł
    0.14
    Act Density 0.003%

    No Known Activations