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

    Neuronpedia

    INDEX
    Explanations

    elements related to user and resource policies in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iane
    -0.15
    loys
    -0.15
    udeau
    -0.15
     Feld
    -0.15
     fold
    -0.15
    ux
    -0.14
    ova
    -0.14
    immel
    -0.14
     singleton
    -0.14
     versa
    -0.13
    POSITIVE LOGITS
    rost
    0.16
    YST
    0.16
     Lester
    0.15
    chwitz
    0.15
    iaux
    0.15
    yst
    0.15
    olah
    0.14
    nut
    0.14
    ongan
    0.14
    acz
    0.14
    Act Density 0.039%

    No Known Activations