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

    Neuronpedia

    INDEX
    Explanations

    expressions with the word "bit"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a moderate degree or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alsh
    -0.70
    inarily
    -0.68
     Grave
    -0.65
    itars
    -0.63
    stice
    -0.63
    taining
    -0.63
    ordan
    -0.63
    æ©
    -0.62
    inate
    -0.61
    ovies
    -0.61
    POSITIVE LOGITS
    terness
    1.04
     bit
    0.90
    buck
    0.89
    bit
    0.80
    umen
    0.76
    catentry
    0.75
    umin
    0.74
    chery
    0.72
    quart
    0.69
    mask
    0.69
    Act Density 0.020%

    No Known Activations