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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical violence and bodily harm

    oai_token-act-pair · gpt-3.5-turbo

    violent actions and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivals
    -0.83
    Maps
    -0.78
    SPA
    -0.74
    Money
    -0.71
    roleum
    -0.70
     Beasts
    -0.70
    Introduced
    -0.70
    Ranked
    -0.69
    Bus
    -0.68
    iseum
    -0.68
    POSITIVE LOGITS
     protr
    1.03
    stretched
    0.98
     exposing
    0.92
     horizontally
    0.88
     backwards
    0.87
     revealing
    0.87
     sideways
    0.87
     tightly
    0.86
     perpend
    0.85
     neatly
    0.83
    Act Density 0.207%

    No Known Activations