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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and functions in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldon
    -0.19
    ress
    -0.15
    'gc
    -0.14
    ooth
    -0.14
    plib
    -0.14
    елиÑĩ
    -0.14
    agn
    -0.14
    nesc
    -0.14
    eturn
    -0.14
    Ñıз
    -0.14
    POSITIVE LOGITS
    tors
    0.16
    ëĦ·
    0.15
    raž
    0.14
    ToList
    0.14
     Evet
    0.14
    allon
    0.14
    仲
    0.14
    rupt
    0.13
    ¥
    0.13
    unittest
    0.13
    Act Density 0.057%

    No Known Activations