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

    Neuronpedia

    INDEX
    Explanations

    references to wartime battles or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    perm
    -0.72
    andro
    -0.71
    Wan
    -0.70
    Wheel
    -0.69
    uana
    -0.69
    credit
    -0.68
     Nig
    -0.68
    Cub
    -0.67
    bery
    -0.66
    à
    -0.66
    POSITIVE LOGITS
     commanders
    1.07
     commander
    1.05
     battlefield
    0.96
     combat
    0.96
     artillery
    0.96
    combat
    0.91
     barracks
    0.90
     battalion
    0.89
     combatants
    0.89
     trenches
    0.88
    Act Density 0.107%

    No Known Activations