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

    Neuronpedia

    INDEX
    Explanations

    mentions of something being special or unique

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "special."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.70
     Twain
    -0.68
     Ri
    -0.68
    anon
    -0.67
     Cah
    -0.63
    tics
    -0.62
    ·
    -0.62
    amus
    -0.62
    conom
    -0.61
    arer
    -0.61
    POSITIVE LOGITS
    ised
    1.17
    ties
    1.03
    izations
    0.96
    isations
    0.96
    isable
    0.90
    ized
    0.88
     relativity
    0.86
    ities
    0.82
     sauce
    0.82
    arily
    0.81
    Act Density 0.021%

    No Known Activations