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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values that may represent significant data points or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swearing
    -0.62
     Sachs
    -0.60
     Lauder
    -0.59
     ment
    -0.58
     Goodman
    -0.58
     Cutter
    -0.57
     recognition
    -0.57
     Palest
    -0.57
    idence
    -0.56
     pitched
    -0.56
    POSITIVE LOGITS
    96
    1.26
    76
    1.24
    90
    1.22
    86
    1.21
    87
    1.20
    73
    1.19
    54
    1.19
    89
    1.18
    63
    1.18
    56
    1.18
    Act Density 0.230%

    No Known Activations