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

    Neuronpedia

    INDEX
    Explanations

    references to historical wars and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to wars and their impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.90
    rac
    -0.83
    )=(
    -0.79
    angelo
    -0.73
    ray
    -0.73
    çīĪ
    -0.72
    aye
    -0.71
    igans
    -0.68
    ONY
    -0.68
    phia
    -0.67
    POSITIVE LOGITS
    enegger
    0.96
    schild
    0.85
     waged
    0.77
     Afghanistan
    0.75
     raged
    0.75
     Armageddon
    0.73
     raging
    0.69
     Roses
    0.69
     attrition
    0.69
     Medals
    0.69
    Act Density 0.329%

    No Known Activations