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

    Neuronpedia

    INDEX
    Explanations

    names of individuals with the initial "M" or sequences of numbers separated by periods

    oai_token-act-pair · gpt-3.5-turbo

    identifiers and numeric values in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -0.75
    ò
    -0.73
    DeliveryDate
    -0.71
     eleph
    -0.70
    ñ
    -0.70
    ĸļ士
    -0.68
     earthqu
    -0.67
    oreAnd
    -0.63
     exting
    -0.62
    Ĝ
    -0.61
    POSITIVE LOGITS
    .,
    1.33
    .
    1.31
    .?
    1.30
    .;
    1.23
    .:
    1.19
    .-
    1.18
    ./
    1.13
    .,"
    1.12
    ._
    1.08
    .—
    1.03
    Act Density 0.274%

    No Known Activations