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

    Neuronpedia

    INDEX
    Explanations

    string patterns or special characters in code or markup structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.00
    AsUp
    -0.95
    djangoproject
    -0.80
    הערות
    -0.78
    SequentialGroup
    -0.76
    ValueStyle
    -0.75
    ()]
    -0.75
    uxxxx
    -0.75
    évaluateur
    -0.69
    [toxicity=0]
    -0.69
    POSITIVE LOGITS
    !("{
    0.92
    ]<<"
    0.87
     $("<
    0.84
    {"
    0.81
    ("+
    0.80
    :"-
    0.80
     "~
    0.79
    ("--
    0.78
     "@
    0.78
    ="/
    0.78
    Act Density 0.162%

    No Known Activations