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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to media sources or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pronouns
    -0.70
     clitor
    -0.68
     Franch
    -0.66
     accordingly
    -0.64
     attent
    -0.63
     conver
    -0.63
     repe
    -0.62
     follows
    -0.61
     verbs
    -0.61
     pronoun
    -0.60
    POSITIVE LOGITS
    Reuters
    1.12
    AFP
    1.12
    Bloomberg
    1.06
    Flickr
    1.05
    Getty
    1.04
    Associated
    1.02
    Courtesy
    0.99
    CBC
    0.97
    EPA
    0.89
    GoldMagikarp
    0.85
    Act Density 0.050%

    No Known Activations