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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of a specific name or figure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _dense
    -0.16
    onga
    -0.16
    vier
    -0.15
    åĩºåĵģèĢħ
    -0.15
    ergy
    -0.14
    Compact
    -0.14
    Ñīик
    -0.14
    arius
    -0.14
    rud
    -0.14
    ме
    -0.14
    POSITIVE LOGITS
    RAD
    0.16
    rad
    0.16
    zas
    0.15
    anan
    0.15
    hest
    0.14
    lı
    0.14
    Äĵ
    0.14
     integr
    0.14
    atto
    0.14
    .CONTENT
    0.14
    Act Density 0.020%

    No Known Activations