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

    Neuronpedia

    INDEX
    Explanations

    language and dialect terms related to specific groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    jen
    -0.56
    ensitivity
    -0.48
    nonumber
    -0.47
     المعيارى
    -0.46
    upyter
    -0.45
    ➟
    -0.45
     read
    -0.44
     natu
    -0.43
     Kwan
    -0.43
    کان
    -0.43
    POSITIVE LOGITS
     dialects
    0.86
     EconPapers
    0.86
     dialect
    0.69
     Exacts
    0.65
     itſelf
    0.64
    ViewFeatures
    0.60
     BorderRadius
    0.59
     }}"></
    0.59
     vocales
    0.59
    quial
    0.58
    Act Density 0.028%

    No Known Activations