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

    Neuronpedia

    INDEX
    Explanations

    sections of code that contain docstrings or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Linux
    -0.15
     ÙħتØŃ
    -0.14
    ael
    -0.14
    anj
    -0.13
    /autoload
    -0.13
    cia
    -0.13
     Mixed
    -0.13
    iac
    -0.13
    cast
    -0.13
    озÑı
    -0.13
    POSITIVE LOGITS
    ovsky
    0.16
    rol
    0.15
    -uri
    0.14
    uld
    0.14
    ë§IJ
    0.14
    .IntPtr
    0.14
    ungan
    0.14
    ãģ£ãģ¨
    0.14
     layer
    0.13
    ROL
    0.13
    Act Density 0.005%

    No Known Activations