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

    Neuronpedia

    INDEX
    Explanations

    violence-related actions, particularly physical attacks

    oai_token-act-pair · gpt-3.5-turbo

    instances of physical violence or assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£
    -0.83
    DragonMagazine
    -0.81
    iterranean
    -0.75
    imester
    -0.74
    gio
    -0.74
    arcity
    -0.73
    inventoryQuantity
    -0.71
    CLASS
    -0.71
    encia
    -0.71
    lopp
    -0.70
    POSITIVE LOGITS
     senseless
    0.95
     buttocks
    0.94
     unconscious
    0.91
     classmate
    0.87
     rapist
    0.81
     girlfriend
    0.80
     asshole
    0.77
     unarmed
    0.77
     innocent
    0.77
     violently
    0.77
    Act Density 0.338%

    No Known Activations