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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "over" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a widespread occurrence or phenomenon across multiple locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.65
    Prev
    -0.64
    ":[{"
    -0.64
    oka
    -0.63
    =-=-
    -0.63
    uum
    -0.62
    ahime
    -0.62
    Completed
    -0.61
    ysis
    -0.61
    ================================
    -0.61
    POSITIVE LOGITS
    drive
    0.88
    blown
    0.75
    priced
    0.73
    whelming
    0.71
    loading
    0.71
    uffs
    0.70
    grown
    0.69
    )=(
    0.68
    beans
    0.68
    nuts
    0.67
    Act Density 0.015%

    No Known Activations