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

    Neuronpedia

    INDEX
    Explanations

    the word "up" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -0.87
     cref
    -0.80
     nonatomic
    -0.78
     Bete
    -0.74
    iyle
    -0.73
     TextStyle
    -0.73
    ]--;
    -0.72
    bronn
    -0.71
     SSC
    -0.69
     habr
    -0.67
    POSITIVE LOGITS
     Up
    2.53
     up
    2.53
    Up
    2.39
     UP
    2.30
    up
    2.23
    UP
    2.02
     ups
    1.55
    ups
    1.54
     Ups
    1.45
    アップ
    1.45
    Act Density 0.111%

    No Known Activations