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

    Neuronpedia

    INDEX
    Explanations

    references to the usage of substances or practices often related to health or protocols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    en
    -0.91
    o
    -0.89
    er
    -0.81
    es
    -0.71
    fer
    -0.71
    F
    -0.69
    Scha
    -0.68
    Y
    -0.67
    y
    -0.67
    u
    -0.66
    POSITIVE LOGITS
     Usage
    1.23
     usage
    1.09
    usage
    1.09
    Usage
    1.05
    USAGE
    1.02
    usages
    0.97
     USAGE
    0.95
     usages
    0.88
    ^(@)
    0.88
    BibitemShut
    0.85
    Act Density 0.005%

    No Known Activations