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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to weapons and equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.79
    lus
    -0.72
    cess
    -0.72
     Strawberry
    -0.71
    dit
    -0.69
     Manz
    -0.67
    forth
    -0.65
     Debor
    -0.64
    aways
    -0.63
    iannopoulos
    -0.63
    POSITIVE LOGITS
    powder
    1.11
     wielded
    0.96
     arsenal
    0.93
     salute
    0.88
     caches
    0.87
     weapons
    0.86
    mith
    0.81
    kit
    0.80
    usable
    0.80
     weapon
    0.79
    Act Density 0.039%

    No Known Activations