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

    Neuronpedia

    INDEX
    Explanations

    coding-related keywords and actions, particularly in relation to data structures and object management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.17
    ["
    -0.17
     ["
    -0.17
    ("
    -0.16
     |↵
    -0.15
     +
    -0.15
    (("
    -0.14
    Ãħ
    -0.14
    )((
    -0.14
     |
    -0.14
    POSITIVE LOGITS
    (const
    0.47
    (int
    0.42
    (bool
    0.40
    (void
    0.36
    (unsigned
    0.36
    (char
    0.34
    (uint
    0.34
     int
    0.29
    (float
    0.29
     const
    0.28
    Act Density 0.020%

    No Known Activations