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

    Neuronpedia

    INDEX
    Explanations

    words related to likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    references to probabilities or likelihood of events occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DATA
    -0.81
    Meta
    -0.78
    Series
    -0.74
    Cart
    -0.72
    atra
    -0.72
    cart
    -0.72
    Physical
    -0.71
    Bed
    -0.70
    MT
    -0.69
    ILE
    -0.69
    POSITIVE LOGITS
    llor
    1.01
     chances
    1.00
     odds
    0.81
    pring
    0.80
     prospects
    0.78
    hift
    0.75
     Rouhani
    0.75
    paren
    0.71
    bably
    0.69
    cffff
    0.69
    Act Density 0.014%

    No Known Activations