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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Corps" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.73
    ishly
    -0.66
    iable
    -0.65
    ting
    -0.64
     Kardashian
    -0.63
    isher
    -0.63
    urtles
    -0.63
    GBT
    -0.62
    icious
    -0.62
    ourning
    -0.62
    POSITIVE LOGITS
    '
    1.50
    hip
    1.43
    hips
    1.32
    hire
    1.23
    ystem
    1.17
    ',
    1.12
    hift
    1.10
    ']
    1.05
    mith
    1.02
    '.
    1.01
    Act Density 0.088%

    No Known Activations