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

    Neuronpedia

    INDEX
    Explanations

    references to various types of weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.83
    lus
    -0.77
    dit
    -0.75
     Strawberry
    -0.73
    forth
    -0.70
    Adams
    -0.68
    apest
    -0.68
    ©¶æ
    -0.68
     coli
    -0.67
    uthor
    -0.67
    POSITIVE LOGITS
     caches
    1.11
     arsenal
    1.06
    powder
    1.04
     wielded
    1.02
     arsen
    0.96
     weapons
    0.94
    mith
    0.92
     stockpile
    0.90
     manufacturers
    0.89
     rifles
    0.87
    Act Density 0.049%

    No Known Activations