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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "this" or "the current situation."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.68
    ariConfig
    -0.67
    ArgumentParser
    -0.66
    WebControls
    -0.63
    HtmlAttribute
    -0.63
    tagHelperRunner
    -0.57
     ferons
    -0.56
     razon
    -0.55
    帖最后由
    -0.55
     Alcott
    -0.53
    POSITIVE LOGITS
     nahilalakip
    0.68
    '])){
    0.58
     Efq
    0.57
     }}"></
    0.57
    ']],
    0.56
    actéris
    0.54
    veria
    0.54
     مشين
    0.52
    __*/
    0.52
    top
    0.51
    Act Density 0.034%

    No Known Activations