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

    Neuronpedia

    INDEX
    Explanations

    actions and events involving conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anahtar
    -0.56
     møte
    -0.52
    Composable
    -0.52
    rungsseite
    -0.52
    AndPassword
    -0.49
    oa̍t
    -0.49
    veren
    -0.48
     Shift
    -0.48
     consultato
    -0.47
    ulemon
    -0.47
    POSITIVE LOGITS
     shots
    0.86
    PMailer
    0.84
     bombardment
    0.81
     shooting
    0.77
     shot
    0.77
     firing
    0.76
     missiles
    0.75
     targeting
    0.75
    shots
    0.75
     missile
    0.74
    Act Density 0.411%

    No Known Activations