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

    Neuronpedia

    INDEX
    Explanations

    references to foreign entities or matters

    oai_token-act-pair · gpt-3.5-turbo

    references to foreign entities or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byss
    -0.83
    illation
    -0.80
    FUL
    -0.79
    ividual
    -0.76
     GOODMAN
    -0.76
    aurus
    -0.74
    YR
    -0.74
    hots
    -0.73
    chens
    -0.73
    uden
    -0.72
    POSITIVE LOGITS
     affairs
    1.10
     nationals
    1.09
     countries
    0.88
     Affairs
    0.86
     embassies
    0.85
     languages
    0.85
     relations
    0.81
     shores
    0.80
     nations
    0.79
     observers
    0.79
    Act Density 0.021%

    No Known Activations