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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities followed by nouns

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to quantities and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    charge
    -0.76
    matter
    -0.76
    ighter
    -0.75
    bsite
    -0.72
    udeb
    -0.71
    à¥
    -0.71
    actionDate
    -0.70
    zzy
    -0.70
    earth
    -0.67
    ENSE
    -0.67
    POSITIVE LOGITS
     finalists
    1.09
     ways
    0.83
     contenders
    0.80
     remaining
    0.78
     quir
    0.77
     factors
    0.75
     reasons
    0.75
     siblings
    0.75
     choices
    0.72
     categories
    0.72
    Act Density 0.084%

    No Known Activations