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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tank."

    oai_token-act-pair · gpt-3.5-turbo

    references to tanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.92
    BOOK
    -0.72
    ————
    -0.68
    teness
    -0.67
    phony
    -0.67
    ãĥ¬
    -0.66
     Brotherhood
    -0.65
    theless
    -0.65
     Lod
    -0.65
    çīĪ
    -0.65
    POSITIVE LOGITS
    erness
    1.22
    ard
    1.00
    mates
    0.99
    ards
    0.99
    ered
    0.94
    yard
    0.94
    agers
    0.93
    tank
    0.91
    ering
    0.90
    tops
    0.85
    Act Density 0.040%

    No Known Activations