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

    Neuronpedia

    INDEX
    Explanations

    occurrences of square brackets and parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &'
    -0.60
     Hig
    -0.59
    ѝ
    -0.58
    AndEndTag
    -0.56
     AS
    -0.56
    ɵɵ
    -0.56
     Co
    -0.55
    كذا
    -0.55
     Burke
    -0.54
     close
    -0.54
    POSITIVE LOGITS
     plufieurs
    0.95
     ainfi
    0.93
     feroit
    0.91
     enfans
    0.91
     auroit
    0.89
     måte
    0.89
     rechange
    0.85
     ffilm
    0.85
    principalColumn
    0.85
     fotográfico
    0.84
    Act Density 0.071%

    No Known Activations