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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks used in programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     standard
    -0.15
     whose
    -0.14
    ational
    -0.14
     principle
    -0.14
     and
    -0.14
     Principle
    -0.14
     who
    -0.14
     same
    -0.14
     average
    -0.13
     alternative
    -0.13
    POSITIVE LOGITS
     nil
    0.50
    nil
    0.36
    -nil
    0.30
    (nil
    0.30
    	nil
    0.28
    :nil
    0.26
     Nil
    0.26
    _nil
    0.25
    Nil
    0.25
    ,nil
    0.24
    Act Density 0.004%

    No Known Activations