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

    Neuronpedia

    INDEX
    Explanations

    numerical information, such as measurements, percentages, and dates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    igators
    -0.80
    aminer
    -0.78
    thumbnails
    -0.75
    ition
    -0.75
    uyomi
    -0.75
    iment
    -0.74
    oat
    -0.74
    ications
    -0.74
    ience
    -0.73
    ngth
    -0.73
    POSITIVE LOGITS
    09
    1.08
    07
    1.06
    059
    1.04
    08
    1.03
    05
    1.02
    06
    1.01
    04
    0.99
    089
    0.99
    03
    0.96
    ELD
    0.94
    Act Density 6.576%

    No Known Activations