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

    Neuronpedia

    INDEX
    Explanations

    terms associated with the act of whipping or similar actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.16
    asu
    -0.15
    loating
    -0.15
    erva
    -0.14
     Rowe
    -0.14
    ovo
    -0.14
    _prepare
    -0.13
     pulver
    -0.13
    wy
    -0.13
    oshi
    -0.13
    POSITIVE LOGITS
    .Pixel
    0.17
    ourt
    0.15
    TAIL
    0.15
    ument
    0.15
     lt
    0.15
    opper
    0.15
     tail
    0.14
    rut
    0.14
     Annunci
    0.14
     Gur
    0.14
    Act Density 0.006%

    No Known Activations