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

    Neuronpedia

    INDEX
    Explanations

    incremental quantities and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laden
    -0.14
    BackStack
    -0.14
    wig
    -0.14
     Evet
    -0.14
    gio
    -0.14
    Selectable
    -0.13
    ENTE
    -0.13
    .cn
    -0.13
    640
    -0.13
    %č↵
    -0.13
    POSITIVE LOGITS
     ones
    0.27
    ones
    0.23
    ÑĢоÑĩ
    0.17
    ONES
    0.16
    onen
    0.16
     Ones
    0.16
     Vaughan
    0.15
    à¥įतम
    0.14
    Ñģа
    0.14
     Civil
    0.13
    Act Density 0.128%

    No Known Activations