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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¢âĢ¢
    -0.65
     Shades
    -0.65
    zik
    -0.64
    ivalent
    -0.64
    ometown
    -0.63
     Seasons
    -0.63
    LOAD
    -0.62
    steps
    -0.62
    terior
    -0.62
    ESH
    -0.61
    POSITIVE LOGITS
     fiction
    1.21
     Fiction
    1.11
    craft
    0.88
    icist
    0.86
     literacy
    0.81
    fiction
    0.80
    mong
    0.80
    bench
    0.79
    onomy
    0.78
     science
    0.78
    Act Density 0.027%

    No Known Activations