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

    Neuronpedia

    INDEX
    Explanations

    terms related to military activities and conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶģ
    -0.84
    DAY
    -0.80
    nob
    -0.76
    galitarian
    -0.75
    apest
    -0.73
    gger
    -0.73
    heimer
    -0.72
    upon
    -0.72
    bos
    -0.70
    orative
    -0.69
    POSITIVE LOGITS
     commanders
    1.06
     dictatorship
    1.03
     fatig
    1.03
     commander
    0.97
     intervention
    0.97
     maneuvers
    0.96
     units
    0.95
     drills
    0.93
     personnel
    0.93
     stationed
    0.93
    Act Density 0.037%

    No Known Activations