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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers formatted in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    patterns of numerical sequences or timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.75
    alysed
    -0.71
    fruit
    -0.71
    interstitial
    -0.70
    quez
    -0.70
    alities
    -0.69
    anthrop
    -0.68
     strugg
    -0.67
    loo
    -0.66
    jected
    -0.66
    POSITIVE LOGITS
    mAh
    0.82
    ISTER
    0.82
    rpm
    0.77
    gp
    0.75
    Hz
    0.73
    pta
    0.70
     GHz
    0.70
    âĤ¬
    0.69
    ##
    0.69
    FFFF
    0.68
    Act Density 0.047%

    No Known Activations