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

    Neuronpedia

    INDEX
    Explanations

    syntactical elements and structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _runner
    -0.16
    onia
    -0.15
    atrix
    -0.15
    ares
    -0.15
     om
    -0.15
    e
    -0.14
    inos
    -0.14
    _smooth
    -0.14
    lectron
    -0.14
     Downing
    -0.14
    POSITIVE LOGITS
    úsqueda
    0.16
    anje
    0.15
     karak
    0.15
    HandlerContext
    0.14
     Fen
    0.14
    oldem
    0.14
    å¼±
    0.14
    ümÃ¼ÅŁ
    0.14
     баг
    0.13
    ombat
    0.13
    Act Density 0.059%

    No Known Activations