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

    Neuronpedia

    INDEX
    Explanations

    mentions of international matters or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to international law and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.95
    veyard
    -0.89
    gger
    -0.81
    thora
    -0.77
    onna
    -0.76
    _-
    -0.75
    atto
    -0.74
    haps
    -0.74
    uden
    -0.73
    onies
    -0.72
    POSITIVE LOGITS
     treaty
    1.02
     treaties
    1.00
     diplomatic
    0.90
     Affairs
    0.90
     humanitarian
    0.88
     affairs
    0.87
     terrorism
    0.84
     espionage
    0.81
     Confederation
    0.81
     sanctions
    0.81
    Act Density 0.021%

    No Known Activations