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

    Neuronpedia

    INDEX
    Explanations

    words related to distinctiveness or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "distinct" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.77
    jury
    -0.68
    Ö¼
    -0.66
    nery
    -0.65
     bumped
    -0.64
    ITED
    -0.61
    ttp
    -0.61
     Phelps
    -0.61
     calmly
    -0.60
     Zombies
    -0.59
    POSITIVE LOGITS
    ively
    1.54
    iveness
    1.26
    iating
    1.12
    iates
    1.11
    iations
    1.01
    iator
    1.00
    edIn
    0.96
    iated
    0.95
    iary
    0.91
    iable
    0.90
    Act Density 0.013%

    No Known Activations