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

    Neuronpedia

    INDEX
    Explanations

    articles and definitive references to common subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictions
    -0.76
     Languages
    -0.75
    ocry
    -0.75
    seys
    -0.71
     Books
    -0.68
    andom
    -0.68
     Bulg
    -0.67
     Mysteries
    -0.66
    artments
    -0.66
    ernels
    -0.65
    POSITIVE LOGITS
    é¾įåĸļ士
    0.72
    control
    0.68
    IJ
    0.65
     caution
    0.64
    enson
    0.63
     responsibility
    0.62
    inelli
    0.62
     blame
    0.61
     dissolved
    0.61
    é¾
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.