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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and variable manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <",
    -0.80
     ?>/
    -0.78
    Extinguishing
    -0.77
    [];
    -0.76
     ostavi
    -0.75
    ]){
    -0.73
    ()){
    -0.73
    $_['
    -0.73
    :\/\/
    -0.73
    }],
    -0.70
    POSITIVE LOGITS
     is
    0.50
    ervazione
    0.49
    jsii
    0.49
    ättern
    0.47
     =
    0.47
     domanda
    0.45
     suivant
    0.44
    anhänger
    0.43
    Гото
    0.42
    BASELINE
    0.42
    Act Density 0.126%

    No Known Activations