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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer programming syntax and features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to devices and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.78
     Flavoring
    -0.73
    qua
    -0.71
    igh
    -0.68
    utics
    -0.66
     Believe
    -0.66
    rolet
    -0.66
     Murd
    -0.66
    utic
    -0.66
     Fifth
    -0.64
    POSITIVE LOGITS
     name
    1.29
     identifier
    1.27
     IDs
    1.20
    Name
    1.20
     names
    1.19
     description
    1.14
     selector
    1.12
     ID
    1.09
    NAME
    1.09
     descriptions
    1.09
    Act Density 0.309%

    No Known Activations