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

    Neuronpedia

    INDEX
    Explanations

    descriptions of firearms being used in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of gunfire or shooting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Username
    -0.83
    redo
    -0.77
    ahime
    -0.73
    anth
    -0.70
    abled
    -0.66
    abase
    -0.64
    ospels
    -0.64
    fecture
    -0.64
     Ratings
    -0.63
    Parent
    -0.62
    POSITIVE LOGITS
     unarmed
    1.16
     indiscrim
    0.93
     killing
    0.91
     bursts
    0.90
     targets
    0.87
     projectiles
    0.85
     explosions
    0.84
     blasts
    0.83
     wounding
    0.83
     disbel
    0.82
    Act Density 0.377%

    No Known Activations