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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of articles, publications, and editorials

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gestures
    -0.79
     deployments
    -0.76
     rehe
    -0.71
    roo
    -0.71
    agree
    -0.70
     arming
    -0.68
     unlocking
    -0.66
    zees
    -0.66
    zik
    -0.65
    iors
    -0.65
    POSITIVE LOGITS
     newspapers
    1.35
    Journal
    1.25
     newspaper
    1.20
     Newspaper
    1.13
     Weekly
    1.13
     magazine
    1.10
     Daily
    1.09
     Chronicle
    1.08
     Magazine
    1.04
     Huffington
    1.03
    Act Density 0.325%

    No Known Activations