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

    Neuronpedia

    INDEX
    Explanations

    sequences that represent data structure references or memory operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atum
    -0.17
    _basename
    -0.14
    535
    -0.14
    {}.
    -0.14
    LEM
    -0.13
    ody
    -0.13
    oth
    -0.13
     ustanov
    -0.13
    enda
    -0.13
    833
    -0.13
    POSITIVE LOGITS
    canf
    0.17
    κÏģι
    0.15
    izens
    0.15
    ovsky
    0.15
    Ä°Y
    0.14
    /*č↵
    0.14
    à¤Ĥà¤ľ
    0.14
    ercises
    0.14
     Jeans
    0.14
     çĭ
    0.14
    Act Density 0.074%

    No Known Activations