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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.54
    ...</
    -0.50
    *}[
    -0.49
    */),
    -0.46
     them
    -0.44
    enumi
    -0.43
     Италијани
    -0.43
    省市镇
    -0.43
    cel
    -0.43
    置き
    -0.43
    POSITIVE LOGITS
    GOTREF
    0.82
     <<<<<<<<<<<<<<
    0.77
    RUnlock
    0.74
    PropertyChanging
    0.69
    XmlRootElement
    0.68
     مُعرِّف
    0.66
     magnétique
    0.65
     Fichier
    0.64
     CreateTagHelper
    0.64
     uParam
    0.64
    Act Density 0.000%

    No Known Activations