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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and concepts within code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.16
    |.
    -0.15
    ,
    -0.15
    >NN
    -0.15
    >.
    -0.15
    *,
    -0.14
     Incontri
    -0.14
    licken
    -0.14
    1
    -0.14
    arer
    -0.14
    POSITIVE LOGITS
    '↵
    0.21
    '↵↵
    0.19
    "↵
    0.18
    '
    0.17
    ’↵
    0.17
    "↵↵
    0.17
     "↵
    0.16
    strict
    0.16
    "č↵
    0.16
    `↵
    0.16
    Act Density 0.012%

    No Known Activations