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

    Neuronpedia

    INDEX
    Explanations

    years or centuries mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific centuries mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avering
    -0.93
    abol
    -0.91
    uana
    -0.91
    andering
    -0.88
    bid
    -0.86
    bor
    -0.86
    alid
    -0.86
    unal
    -0.83
    obal
    -0.81
    bara
    -0.80
    POSITIVE LOGITS
    mAh
    1.12
     MHz
    0.99
    MHz
    0.95
     certs
    0.89
    1200
    0.84
     Series
    0.78
    1800
    0.78
    1100
    0.76
    1900
    0.75
     hrs
    0.74
    Act Density 0.013%

    No Known Activations