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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically related to individuals like public figures

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of individual names, particularly "Kagan" and "Ogan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.75
     mutual
    -0.68
    Score
    -0.67
    İĭ
    -0.67
     luck
    -0.63
     backlog
    -0.63
    âĢ¢âĢ¢
    -0.63
     apprehension
    -0.62
     abdom
    -0.62
     predictive
    -0.62
    POSITIVE LOGITS
    igans
    1.04
    agan
    1.04
    za
    1.03
    atin
    0.96
    arde
    0.96
    zeb
    0.96
    lein
    0.92
    ocene
    0.91
    azi
    0.88
    itating
    0.87
    Act Density 0.007%

    No Known Activations