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

    Neuronpedia

    INDEX
    Explanations

    references to violent actions and explosive devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ----</
    -0.35
    Ƚ
    -0.35
    ArrowToggle
    -0.35
     استنادى
    -0.33
     तुल
    -0.33
     lenker
    -0.33
    layoutControl
    -0.32
    eleri
    -0.32
    exitRule
    -0.32
    cování
    -0.31
    POSITIVE LOGITS
     explosion
    2.27
     explosive
    2.23
     explode
    2.16
     exploding
    2.13
     explosions
    2.13
     bomb
    2.11
     exploded
    2.05
     explodes
    2.05
     Explo
    2.02
     explosives
    2.02
    Act Density 0.551%

    No Known Activations