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

    Neuronpedia

    INDEX
    Explanations

    terms related to nonviolence and terms related to violence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence and nonviolence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rot
    -0.76
    rosc
    -0.76
    ween
    -0.75
    GPU
    -0.72
     Tycoon
    -0.71
    ulas
    -0.70
    cedented
    -0.69
    awed
    -0.69
    ummies
    -0.69
    ibo
    -0.68
    POSITIVE LOGITS
     nonviolent
    0.95
     disobedience
    0.75
     cessation
    0.71
    violent
    0.71
     pacif
    0.71
     activism
    0.70
     measure
    0.70
     agitation
    0.69
     justice
    0.68
     resistance
    0.68
    Act Density 0.008%

    No Known Activations