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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to source code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatus
    -0.82
     Democr
    -0.80
     Flavoring
    -0.77
    swer
    -0.77
    iversal
    -0.75
    abouts
    -0.70
    strous
    -0.70
    iscopal
    -0.66
    rily
    -0.64
    esville
    -0.63
    POSITIVE LOGITS
     code
    1.17
     snippet
    1.13
    code
    1.05
     codes
    1.03
    codes
    0.95
     snippets
    0.86
     coded
    0.86
    otle
    0.85
     snipp
    0.85
     interpreter
    0.85
    Act Density 0.013%

    No Known Activations