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

    Neuronpedia

    INDEX
    Explanations

    lines of code in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    closing braces and function terminators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oresc
    -0.78
    uga
    -0.74
    orescence
    -0.70
    ascus
    -0.69
    idium
    -0.68
    aton
    -0.67
    arya
    -0.67
    VIDIA
    -0.66
    otine
    -0.65
    ardon
    -0.65
    POSITIVE LOGITS
     ACTIONS
    1.07
    else
    1.06
     Else
    1.00
     else
    0.99
     [/
    0.88
     }
    0.85
     };
    0.85
     MODULE
    0.83
     EVENTS
    0.82
     Finally
    0.80
    Act Density 0.014%

    No Known Activations