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

    Neuronpedia

    INDEX
    Explanations

    words related to different types of weapons

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weapons and weaponry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.82
    lus
    -0.77
     coli
    -0.74
     Strawberry
    -0.72
    forth
    -0.71
    greSQL
    -0.69
     Organic
    -0.68
    noon
    -0.67
    apest
    -0.67
    fo
    -0.67
    POSITIVE LOGITS
     weapon
    0.91
    powder
    0.89
     salute
    0.88
     weapons
    0.85
     wielded
    0.82
     manufacturer
    0.77
     arsenal
    0.76
     caches
    0.75
    izes
    0.74
    weapon
    0.72
    Act Density 0.017%

    No Known Activations