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

    Neuronpedia

    INDEX
    Explanations

    qualifiers or judgments expressing approval or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quality and moral qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.78
    worm
    -0.75
    warming
    -0.72
    ELD
    -0.70
    OLD
    -0.68
    berman
    -0.67
    tower
    -0.67
    orman
    -0.66
    ortium
    -0.65
    guard
    -0.65
    POSITIVE LOGITS
    itatively
    1.29
    iological
    0.97
    atically
    0.93
     sidx
    0.88
     qual
    0.85
     externalToEVAOnly
    0.84
    iations
    0.83
     guiActiveUn
    0.81
     Flavoring
    0.79
    iology
    0.78
    Act Density 0.030%

    No Known Activations