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

    Neuronpedia

    INDEX
    Explanations

    numerical values and codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical patterns and values, particularly related to counts or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igators
    -0.71
    igious
    -0.70
    ition
    -0.70
    uyomi
    -0.69
    istas
    -0.68
    ingham
    -0.67
    ience
    -0.67
    fman
    -0.67
    ions
    -0.67
    iment
    -0.65
    POSITIVE LOGITS
    09
    1.06
    07
    1.00
    05
    0.96
    059
    0.95
    06
    0.95
    08
    0.94
    089
    0.91
    04
    0.90
    03
    0.89
    090
    0.85
    Act Density 0.041%

    No Known Activations