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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and other similar characters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tornillo
    -0.49
     unnamed
    -0.48
    DISK
    -0.48
    !*\
    -0.45
    ViewById
    -0.44
    WithMany
    -0.44
    atist
    -0.44
    erek
    -0.44
    Tbh
    -0.43
     Band
    -0.43
    POSITIVE LOGITS
     referrerpolicy
    0.82
     nahilalakip
    0.72
    ########.
    0.69
    RuleContext
    0.68
    RegressionTest
    0.67
     صوتيه
    0.65
    XMLSchema
    0.59
    DeleteBehavior
    0.59
     للمعارف
    0.58
     Normdatei
    0.57
    Act Density 0.015%

    No Known Activations