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

    Neuronpedia

    INDEX
    Explanations

    words related to weapons

    oai_token-act-pair · gpt-3.5-turbo

    mentions of weapons and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.79
    gres
    -0.78
    lus
    -0.76
     Strawberry
    -0.73
    uthor
    -0.69
    annel
    -0.68
     coli
    -0.67
    apest
    -0.66
    ŃĶ
    -0.66
    atta
    -0.65
    POSITIVE LOGITS
     caches
    1.17
    powder
    1.05
     arsenal
    1.00
     wielded
    0.98
     manufacturers
    0.94
    mith
    0.92
     arsen
    0.90
     stockpile
    0.90
     manufacturer
    0.89
     systems
    0.87
    Act Density 0.072%

    No Known Activations