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

    Neuronpedia

    INDEX
    Explanations

    numbers associated with financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucle
    -0.74
    ufact
    -0.67
    abol
    -0.67
    ailed
    -0.65
    ographed
    -0.64
    actic
    -0.63
    uba
    -0.61
    semble
    -0.61
    alyses
    -0.60
    colm
    -0.60
    POSITIVE LOGITS
    s
    0.83
    eatures
    0.72
    escription
    0.71
    «ĺ
    0.70
    erness
    0.70
    plate
    0.69
    Percent
    0.68
    px
    0.68
    ULAR
    0.67
    erie
    0.66
    Act Density 0.051%

    No Known Activations