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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.65
     dozen
    -0.50
     foods
    -0.48
    UGE
    -0.48
     Samo
    -0.47
    lox
    -0.47
     Huss
    -0.47
    dd
    -0.46
     Barak
    -0.46
    ScrollPane
    -0.46
    POSITIVE LOGITS
    TintMode
    0.79
     становника
    0.71
     Affiliations
    0.68
    modelBuilder
    0.68
    \{\\
    0.66
    новниш
    0.65
     EconPapers
    0.65
     MainAxisSize
    0.60
    nocache
    0.60
     CreateTagHelper
    0.60
    Act Density 0.005%

    No Known Activations