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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications and product details

    oai_token-act-pair · gpt-3.5-turbo

    colons and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.82
    mble
    -0.79
    uve
    -0.78
    bered
    -0.73
    dinand
    -0.72
    ivable
    -0.72
     tremend
    -0.72
    oud
    -0.71
    attled
    -0.67
     offending
    -0.67
    POSITIVE LOGITS
     Provided
    1.04
     http
    0.89
     https
    0.87
     TBD
    0.85
    YES
    0.84
    ³³³³³³³³³³³³³³³³
    0.83
     Unknown
    0.82
     Provides
    0.82
     Yeah
    0.81
     Introduced
    0.81
    Act Density 0.152%

    No Known Activations