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

    Neuronpedia

    INDEX
    Explanations

    instances related to a specific organization called "Legion"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Legion" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.70
    gets
    -0.69
    ahn
    -0.69
    sweet
    -0.66
     CHO
    -0.62
    mins
    -0.60
     Pwr
    -0.60
    fulness
    -0.60
     Zucker
    -0.59
    pson
    -0.59
    POSITIVE LOGITS
    naire
    1.92
    naires
    1.81
     Legion
    0.94
    arium
    0.88
    aries
    0.86
    arily
    0.80
    esses
    0.80
    ary
    0.80
    atus
    0.78
    icum
    0.76
    Act Density 0.014%

    No Known Activations