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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict or physical altercations

    oai_token-act-pair · gpt-3.5-turbo

    actions related to confrontational or violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Authors
    -0.78
    enhagen
    -0.70
     Gutenberg
    -0.69
     Tolkien
    -0.65
    è¦ļéĨĴ
    -0.64
     alumni
    -0.64
    cedented
    -0.63
    artisan
    -0.63
     castles
    -0.62
     endors
    -0.61
    POSITIVE LOGITS
     peacefully
    0.78
     disturbance
    0.74
     awoke
    0.73
    Charges
    0.72
     calmly
    0.71
     himself
    0.71
     ur
    0.69
     911
    0.68
     agitated
    0.67
     voluntarily
    0.66
    Act Density 0.418%

    No Known Activations