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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of legitimacy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apas
    -0.18
     å¥
    -0.14
     Gupta
    -0.14
    tract
    -0.14
    _MT
    -0.14
    sdale
    -0.14
    rw
    -0.14
    ocks
    -0.14
    yas
    -0.14
    illon
    -0.14
    POSITIVE LOGITS
    úsqueda
    0.17
    itimate
    0.17
    formation
    0.17
    amate
    0.17
    žÃŃ
    0.15
    PAL
    0.14
    ordova
    0.14
    rowsable
    0.14
    /legal
    0.14
    zig
    0.14
    Act Density 0.013%

    No Known Activations