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

    Neuronpedia

    INDEX
    Explanations

    aggressive physical actions or altercations

    oai_token-act-pair · gpt-3.5-turbo

    violent actions and related physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horm
    -0.70
    erella
    -0.69
     Tycoon
    -0.69
    ahime
    -0.67
    vana
    -0.66
    inventoryQuantity
    -0.66
    osate
    -0.66
    stellar
    -0.65
    hower
    -0.64
     Maiden
    -0.64
    POSITIVE LOGITS
     abusive
    0.94
     protestors
    0.92
     bystanders
    0.88
     protesters
    0.88
     verbally
    0.81
     handcuffed
    0.81
     altercation
    0.81
     protester
    0.79
     disrespectful
    0.79
     assaulting
    0.78
    Act Density 0.345%

    No Known Activations