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

    Neuronpedia

    INDEX
    Explanations

    specific numeric or structural patterns within textual data, particularly with symbols like commas, parentheses, and dollar signs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.74
     Obf
    -0.64
     Audiodateien
    -0.64
    WEBPACK
    -0.63
     STRO
    -0.62
    хіво
    -0.62
    Vanjske
    -0.60
    tagHelperRunner
    -0.60
    fromnode
    -0.59
     HasFactory
    -0.59
    POSITIVE LOGITS
     etc
    0.80
    *,
    0.80
    .$,
    0.75
    *),
    0.74
    //
    0.73
     *,
    0.70
     ,
    0.69
    ”,
    0.68
    etc
    0.67
     $,
    0.66
    Act Density 0.570%

    No Known Activations