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

    Neuronpedia

    INDEX
    Explanations

    keywords related to uniqueness or special characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unique" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.66
    ©¶æ
    -0.65
    ruary
    -0.65
    docs
    -0.62
    jury
    -0.61
    Īè
    -0.60
    Loading
    -0.60
    apers
    -0.59
    ttp
    -0.59
    mol
    -0.59
    POSITIVE LOGITS
     identifier
    1.11
    ively
    1.09
     identifiers
    1.03
    ties
    0.97
    iveness
    0.92
    iates
    0.88
     characteristics
    0.88
     blend
    0.88
    ities
    0.87
    iator
    0.87
    Act Density 0.054%

    No Known Activations