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

    Neuronpedia

    INDEX
    Explanations

    words related to violent actions or incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.90
    Climate
    -0.76
    Reviewer
    -0.75
    VW
    -0.74
     Profit
    -0.70
    Polit
    -0.67
    Planet
    -0.67
    natureconservancy
    -0.66
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    Plan
    -0.65
    POSITIVE LOGITS
     penetrating
    1.02
     grenade
    1.00
     grenades
    0.99
     detonated
    0.97
     fired
    0.97
     wounding
    0.96
    powder
    0.95
     barr
    0.95
     inflicted
    0.92
     indiscrim
    0.92
    Act Density 0.086%

    No Known Activations