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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and research methods

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe mathematical or scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .�
    -0.80
    .''
    -0.76
     elsewhere
    -0.73
    .","
    -0.70
    "}],"
    -0.69
     theirs
    -0.69
    alon
    -0.68
     accordingly
    -0.67
     them
    -0.65
    ''.
    -0.62
    POSITIVE LOGITS
     Wikipedia
    0.69
     ebook
    0.67
     semen
    0.67
     nude
    0.66
     Gmail
    0.66
     Tinder
    0.66
     homosexual
    0.65
     pronoun
    0.64
     plagiar
    0.64
     orgasm
    0.64
    Act Density 0.991%

    No Known Activations