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

    Neuronpedia

    INDEX
    Explanations

    mentions of scientific journals called "Science" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the journal "Science"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     todd
    -0.72
     bron
    -0.68
    onymous
    -0.67
    teen
    -0.67
    ged
    -0.64
     saturated
    -0.63
     timers
    -0.62
     fentanyl
    -0.62
    arding
    -0.62
     subdued
    -0.60
    POSITIVE LOGITS
     Fiction
    1.09
    IDER
    0.79
    uality
    0.78
     fiction
    0.78
     Advisor
    0.77
    craft
    0.76
    Exper
    0.76
     Drink
    0.76
     Citation
    0.75
     Flavoring
    0.75
    Act Density 0.030%

    No Known Activations