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

    Neuronpedia

    INDEX
    Explanations

    phrases with the pattern "a or a" followed by a single word

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edit
    -0.85
    Edit
    -0.83
    Events
    -0.81
    words
    -0.80
    reports
    -0.75
    orders
    -0.72
    groups
    -0.72
    issues
    -0.71
    warn
    -0.71
    results
    -0.70
    POSITIVE LOGITS
    rouse
    1.03
     lot
    0.93
     handful
    0.90
     combination
    0.90
    esthetic
    0.89
     mere
    0.87
     bunch
    0.84
     precursor
    0.83
    cknowled
    0.81
     dozen
    0.81
    Act Density 0.400%

    No Known Activations