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

    Neuronpedia

    INDEX
    Explanations

    words related to uniqueness or specificity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "distinct" and variations related to uniqueness or differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.76
    jury
    -0.71
    ttp
    -0.70
    Ö¼
    -0.64
    nery
    -0.63
    USD
    -0.61
    IVER
    -0.61
     calmly
    -0.60
    ITED
    -0.60
    CLA
    -0.60
    POSITIVE LOGITS
    ively
    1.65
    iveness
    1.20
    iating
    1.02
    iary
    1.02
    iates
    0.99
    iations
    0.93
    iated
    0.92
    edIn
    0.90
     distinct
    0.88
    iator
    0.88
    Act Density 0.014%

    No Known Activations