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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing and authorship

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ️
    -0.57
     human
    -0.53
     (!__
    -0.50
    ")->
    -0.49
    ">(
    -0.49
    ர்
    -0.48
    таратура
    -0.48
     Walkover
    -0.48
     methodology
    -0.46
    liness
    -0.46
    POSITIVE LOGITS
    +#+#
    0.93
     propOrder
    0.87
    BeginContext
    0.82
    MigrationBuilder
    0.79
     ویکی‌پدیای
    0.75
    帖最后由
    0.70
    mobileqq
    0.66
     thanking
    0.66
    etcode
    0.65
     thanked
    0.64
    Act Density 0.003%

    No Known Activations