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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics related to various demographics and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    statistical reports or data points regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urry
    -0.70
     Debate
    -0.69
    pedia
    -0.69
     theorem
    -0.68
     Awakens
    -0.66
    thing
    -0.66
    ciation
    -0.65
    irmation
    -0.64
     distinction
    -0.64
    cknow
    -0.63
    POSITIVE LOGITS
     considered
    0.95
     eligible
    0.93
    wolves
    0.92
     able
    0.91
     supposed
    0.91
    nt
    0.90
     deemed
    0.90
    senal
    0.89
     capable
    0.88
     immune
    0.87
    Act Density 0.214%

    No Known Activations