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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or codes within a text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.82
     externalToEVAOnly
    -0.82
    odied
    -0.74
    atics
    -0.73
    redit
    -0.71
    assies
    -0.71
    akespe
    -0.71
    ewitness
    -0.71
    bered
    -0.70
    riages
    -0.69
    POSITIVE LOGITS
    st
    1.16
    507
    0.80
    naire
    0.77
    EngineDebug
    0.76
    506
    0.76
    IME
    0.75
    504
    0.75
    eous
    0.74
    503
    0.73
    âģ
    0.71
    Act Density 0.041%

    No Known Activations