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

    Neuronpedia

    INDEX
    Explanations

    instances and references to programming and system-related exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to exceptions in programming or error messages.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     useRouter
    -0.81
    SMR
    -0.79
    httphttps
    -0.78
    setViewportView
    -0.78
    rrggbb
    -0.78
    PreferredItem
    -0.78
     TextAlign
    -0.76
    WriteTagHelper
    -0.76
     Marlene
    -0.75
    Marlene
    -0.75
    POSITIVE LOGITS
     Exception
    1.24
    Exception
    1.13
    EXCEPTION
    1.06
     exception
    1.06
    exception
    1.05
     Exceptions
    0.95
     exceptions
    0.93
    exceptions
    0.92
     exemption
    0.91
    Exceptions
    0.85
    Act Density 0.052%

    No Known Activations