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

    Neuronpedia

    INDEX
    Explanations

    mentions of military units and assignments

    oai_token-act-pair · gpt-3.5-turbo

    military ranks and unit designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flaw
    -0.80
     greed
    -0.80
     leaks
    -0.78
     tipping
    -0.77
     skew
    -0.76
     anonymity
    -0.76
     disclosures
    -0.75
     chatter
    -0.75
     silence
    -0.75
     tether
    -0.75
    POSITIVE LOGITS
     Regiment
    1.54
     Infantry
    1.36
     Battalion
    1.35
     Volunteers
    1.19
     Division
    1.17
     Corps
    1.14
     Territ
    1.14
     Association
    1.14
     Brigade
    1.12
     Federation
    1.06
    Act Density 0.549%

    No Known Activations