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

    Neuronpedia

    INDEX
    Explanations

    instances of firearms and their use in violent contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.63
     asyncio
    -0.57
     فريبيس
    -0.56
    +#+#
    -0.53
    inkgo
    -0.52
     échelle
    -0.51
     Sched
    -0.50
    Composable
    -0.50
    échelle
    -0.49
    racuse
    -0.49
    POSITIVE LOGITS
     shooting
    2.12
     shot
    1.99
     shoot
    1.99
     shots
    1.86
     firing
    1.86
    shooting
    1.77
     shooter
    1.74
     Shooting
    1.74
     shoots
    1.74
    Shooting
    1.72
    Act Density 0.451%

    No Known Activations