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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.16
     Sit
    -0.15
    arget
    -0.15
    owie
    -0.15
     dispatch
    -0.15
    lif
    -0.14
    çıł
    -0.14
    ools
    -0.14
    eel
    -0.14
    -Origin
    -0.13
    POSITIVE LOGITS
    ailer
    0.19
     Чи
    0.16
    irim
    0.15
    меÑĢик
    0.14
     Sheridan
    0.14
    documentation
    0.14
    uther
    0.14
    ritten
    0.14
    SCAN
    0.14
    iten
    0.14
    Act Density 0.016%

    No Known Activations