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

    Neuronpedia

    INDEX
    Explanations

    adjectives denoting uniqueness or difference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "distinct" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttp
    -0.73
    jury
    -0.70
    Ö¼
    -0.67
    ITED
    -0.66
    CDC
    -0.65
    annis
    -0.65
    deb
    -0.61
    USD
    -0.60
    pez
    -0.60
    Doctors
    -0.59
    POSITIVE LOGITS
    ively
    1.75
    iveness
    1.28
    iates
    1.02
    iary
    0.99
    edIn
    0.92
    iating
    0.91
    ially
    0.88
     distinct
    0.88
    iator
    0.87
    iated
    0.85
    Act Density 0.027%

    No Known Activations