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

    Neuronpedia

    INDEX
    Explanations

    lines of code or keywords related to programming functions and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldem
    -0.14
     Mund
    -0.14
    unsch
    -0.14
    edium
    -0.14
    illi
    -0.14
     Duch
    -0.14
    ceries
    -0.14
    Ñģли
    -0.13
    upertino
    -0.13
    _GLOBAL
    -0.13
    POSITIVE LOGITS
    átek
    0.15
    lamaz
    0.14
    cassert
    0.14
    WXYZ
    0.14
     赤
    0.13
    رØŃ
    0.13
    Calling
    0.13
     Calling
    0.13
     rfl
    0.13
     localVar
    0.13
    Act Density 0.001%

    No Known Activations