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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to aggression and violations of international law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -1.01
     Clarence
    -0.87
     Slate
    -0.81
     Huff
    -0.80
     Trout
    -0.80
    maxwell
    -0.76
     Hatch
    -0.76
     Quartz
    -0.76
     Ghostbusters
    -0.76
     Wem
    -0.75
    POSITIVE LOGITS
     aggression
    1.35
     imperialist
    1.28
     aggress
    1.27
     provocation
    1.20
    terrorist
    1.18
     imperialism
    1.18
     treacher
    1.17
     barbaric
    1.17
     barbar
    1.16
     Daesh
    1.16
    Act Density 0.527%

    No Known Activations