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

    Neuronpedia

    INDEX
    Explanations

    references to military tanks

    oai_token-act-pair · gpt-3.5-turbo

    references to military vehicles, specifically tanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -1.00
    女
    -0.91
    bread
    -0.75
    çīĪ
    -0.74
    duction
    -0.68
    VID
    -0.68
     Scand
    -0.67
    âĸ¬âĸ¬
    -0.66
    cause
    -0.66
    ãĤ±
    -0.66
    POSITIVE LOGITS
    tank
    1.17
    erness
    1.13
     tank
    1.07
     tanks
    0.95
     Tank
    0.94
    ered
    0.84
    oldown
    0.83
    arded
    0.82
     tanker
    0.82
    wagen
    0.82
    Act Density 0.006%

    No Known Activations