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

    Neuronpedia

    INDEX
    Explanations

    information related to time, dates, and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numeric patterns or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.75
    loo
    -0.73
    fruit
    -0.70
    quit
    -0.70
    quez
    -0.67
     strugg
    -0.66
    alities
    -0.66
    jected
    -0.65
    alysed
    -0.65
    interstitial
    -0.64
    POSITIVE LOGITS
    ISTER
    0.82
    mAh
    0.80
    rpm
    0.73
    nm
    0.73
    arters
    0.73
    gp
    0.72
    FFFF
    0.72
     GHz
    0.70
    ertain
    0.69
    --+
    0.67
    Act Density 0.033%

    No Known Activations