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

    Neuronpedia

    INDEX
    Explanations

    references to tanks, either literally as in a military vehicle or metaphorically as a storage container

    oai_token-act-pair · gpt-3.5-turbo

    references to tanks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -1.03
    theless
    -0.74
    çīĪ
    -0.70
    女
    -0.69
    TERN
    -0.68
    ãĤ±
    -0.67
    VID
    -0.64
    éĹ
    -0.64
    bread
    -0.64
    BOOK
    -0.64
    POSITIVE LOGITS
    erness
    1.05
    tank
    0.95
    arded
    0.93
    ard
    0.91
    ards
    0.91
    yard
    0.87
    ategory
    0.83
    arding
    0.83
    mates
    0.82
    buster
    0.81
    Act Density 0.010%

    No Known Activations