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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets with specific variable names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "foo" in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATING
    -0.80
    yrim
    -0.79
    EMBER
    -0.76
    atory
    -0.74
    ATES
    -0.72
    aries
    -0.71
    ISION
    -0.70
    APD
    -0.70
    inki
    -0.69
    ATOR
    -0.67
    POSITIVE LOGITS
     foo
    0.73
    ça
    0.72
    cellent
    0.70
     syrup
    0.67
    nect
    0.66
     Foo
    0.66
    manship
    0.65
    shire
    0.65
    gerald
    0.65
    foo
    0.64
    Act Density 0.027%

    No Known Activations