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

    Neuronpedia

    INDEX
    Explanations

    tokens associated with programming logic and control flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kitt
    -0.74
    ancia
    -0.70
    mps
    -0.70
     Gump
    -0.69
    おり
    -0.68
     Lobo
    -0.68
    urd
    -0.68
    FLU
    -0.67
    iod
    -0.66
     Kirs
    -0.66
    POSITIVE LOGITS
    )*/
    1.09
    */
    1.05
    AsUp
    0.98
    */
    0.93
     Dooley
    0.92
    */
    0.92
    })*/
    0.88
    >-->
    0.86
    ungkinan
    0.86
    edicated
    0.85
    Act Density 0.113%

    No Known Activations