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

    Neuronpedia

    INDEX
    Explanations

    mentions of explosive devices and related activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aird
    -0.91
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.78
    UTC
    -0.74
    }}}
    -0.72
    Reviewer
    -0.70
    luaj
    -0.69
    gres
    -0.68
    dit
    -0.67
     Parent
    -0.66
     Parables
    -0.65
    POSITIVE LOGITS
     detonated
    1.58
     deton
    1.39
     explosives
    1.18
     grenade
    1.14
     grenades
    1.14
     disposal
    1.13
     bomb
    1.11
     bombs
    1.04
    bomb
    1.02
     explosions
    1.01
    Act Density 0.080%

    No Known Activations