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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Fab" and "ian"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Fabian" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blazing
    -0.70
     whales
    -0.67
     surv
    -0.65
     Miko
    -0.65
     tack
    -0.64
     antidote
    -0.63
    İĭ
    -0.61
     Anchorage
    -0.61
     withdrawals
    -0.60
     thumb
    -0.60
    POSITIVE LOGITS
    ulous
    1.47
    rics
    1.41
    ulously
    1.36
    ruary
    1.32
    rique
    1.30
    rik
    1.27
    riz
    1.17
    iola
    1.07
    ric
    1.05
    rika
    1.05
    Act Density 0.037%

    No Known Activations