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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Feder" which might be associated with names like "Federica" or "Federico"

    oai_token-act-pair · gpt-3.5-turbo

    references to federal entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    talk
    -0.72
    bone
    -0.71
     Carbuncle
    -0.70
    dream
    -0.66
    dress
    -0.64
     mamm
    -0.64
    Drug
    -0.64
    XL
    -0.63
     Clever
    -0.63
    sets
    -0.63
    POSITIVE LOGITS
    ALLY
    0.88
    ations
    0.87
     Feder
    0.86
    ational
    0.85
    itures
    0.83
    iture
    0.82
    ationally
    0.82
    atell
    0.82
    folios
    0.81
    igree
    0.80
    Act Density 0.018%

    No Known Activations