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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and percentages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.16
    fila
    -0.15
    OS
    -0.15
    urger
    -0.15
     Beard
    -0.14
    itude
    -0.14
     Tactical
    -0.14
    .AutoScaleMode
    -0.14
    urent
    -0.14
    ladı
    -0.14
    POSITIVE LOGITS
    usz
    0.18
    pta
    0.17
    oogle
    0.16
    åĽ
    0.15
    виÑĩай
    0.15
    _reporting
    0.15
    sole
    0.14
    .literal
    0.13
    nek
    0.13
    Simply
    0.13
    Act Density 0.090%

    No Known Activations