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

    Neuronpedia

    INDEX
    Explanations

    instances of legal jargon and classifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    böz
    -0.46
    Hidden
    -0.44
    啼
    -0.42
     sist
    -0.40
    jaus
    -0.40
    ÁT
    -0.40
    atop
    -0.40
    дове
    -0.40
     latent
    -0.40
    piele
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    0.79
    transQ
    0.72
    UnusedPrivate
    0.68
    kloped
    0.68
    Autoritní
    0.67
    enderror
    0.67
     متعلقه
    0.66
     sauf
    0.65
    EqualsAnd
    0.65
    حياتها
    0.64
    Act Density 0.240%

    No Known Activations