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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter "U" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific product models or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bars
    -0.69
     hust
    -0.68
    cipline
    -0.66
     juggling
    -0.60
     remarks
    -0.60
     Dickinson
    -0.59
     Discipline
    -0.59
     courtesy
    -0.59
     dispers
    -0.58
     dismissal
    -0.57
    POSITIVE LOGITS
    seless
    1.40
    topia
    1.35
    nexpected
    1.29
    gly
    1.27
    PDATED
    1.27
    lyss
    1.21
    prising
    1.19
    pperc
    1.14
    LT
    1.13
    topic
    1.05
    Act Density 0.048%

    No Known Activations