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

    Neuronpedia

    INDEX
    Explanations

    numbers with some specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igators
    -0.75
    ications
    -0.72
    uyomi
    -0.71
    ience
    -0.70
    Stage
    -0.69
    ition
    -0.69
    iment
    -0.68
    igious
    -0.67
    ist
    -0.66
    ioned
    -0.66
    POSITIVE LOGITS
    09
    1.06
    07
    0.99
    05
    0.96
    059
    0.96
    08
    0.95
    06
    0.95
    04
    0.91
    089
    0.90
    090
    0.90
    03
    0.90
    Act Density 0.052%

    No Known Activations