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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonatomic
    -0.79
    ResumeLayout
    -0.78
    SpringBootTest
    -0.74
    HtmlAttribute
    -0.73
    endregion
    -0.72
     paramString
    -0.68
    SourceChecksum
    -0.68
     habr
    -0.68
    bibitem
    -0.67
     pylab
    -0.67
    POSITIVE LOGITS
     Up
    2.39
    Up
    2.30
     UP
    2.27
    up
    2.20
    UP
    2.15
     up
    1.82
    ups
    1.44
     ups
    1.34
     Ups
    1.33
    Ups
    1.31
    Act Density 0.121%

    No Known Activations