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

    Neuronpedia

    INDEX
    Explanations

    titles or phrases related to historical wars

    oai_token-act-pair · gpt-3.5-turbo

    references to various wars and battles throughout history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.85
    vana
    -0.83
    ffer
    -0.82
    nce
    -0.79
    nea
    -0.75
    oen
    -0.74
    nsic
    -0.71
    ascript
    -0.70
    vp
    -0.68
    inez
    -0.68
    POSITIVE LOGITS
     wills
    1.29
     attrition
    1.05
     sexes
    0.99
     Roses
    0.92
     sorts
    0.88
     ideologies
    0.85
     Ideas
    0.84
     ideas
    0.84
     clans
    0.83
     nerves
    0.82
    Act Density 0.093%

    No Known Activations