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

    Neuronpedia

    INDEX
    Explanations

    actions of confrontation and aggression

    oai_token-act-pair · gpt-3.5-turbo

    actions involving confrontation or physical engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -1.01
    ãĤ¦ãĤ¹
    -0.97
    negie
    -0.87
    inav
    -0.83
    luaj
    -0.82
    conom
    -0.81
    agate
    -0.76
    £ı
    -0.75
    ©¶æ¥µ
    -0.70
    audi
    -0.70
    POSITIVE LOGITS
     passers
    1.43
     officers
    1.29
     onlook
    1.21
     pedestrians
    1.21
     demonstrators
    1.14
     protesters
    1.14
     bystanders
    1.13
     deputies
    1.11
     occupants
    1.10
     motorists
    1.10
    Act Density 0.273%

    No Known Activations