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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various scientific disciplines and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to science in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seasons
    -0.73
    âĢ¢âĢ¢
    -0.67
    leased
    -0.66
    ometown
    -0.65
    LOAD
    -0.64
    ivalent
    -0.64
    pora
    -0.63
    doms
    -0.63
    ESH
    -0.63
     Shades
    -0.63
    POSITIVE LOGITS
     fiction
    1.24
     Fiction
    1.13
    craft
    0.84
     literacy
    0.83
     science
    0.83
    mong
    0.82
    science
    0.80
    icist
    0.79
    fiction
    0.79
    istry
    0.78
    Act Density 0.030%

    No Known Activations