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

    Neuronpedia

    INDEX
    Explanations

    references to weapons and weapon-related concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gres
    -0.87
     coli
    -0.81
    noon
    -0.78
    lus
    -0.78
    cess
    -0.76
    forth
    -0.76
    apest
    -0.74
     Strawberry
    -0.74
     Niet
    -0.73
    atta
    -0.72
    POSITIVE LOGITS
    powder
    1.02
     salute
    0.91
     arsenal
    0.88
     weapons
    0.85
     caches
    0.85
     wielded
    0.85
     weapon
    0.84
     racks
    0.83
     manufacturer
    0.82
    kit
    0.79
    Act Density 8.259%

    No Known Activations