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

    Neuronpedia

    INDEX
    Explanations

    references to positivity or upbeat themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.15
    tr
    -0.15
    eker
    -0.15
    inea
    -0.15
    pool
    -0.14
    acji
    -0.14
    Ĺi
    -0.14
    ispers
    -0.14
    DMI
    -0.14
    emente
    -0.14
    POSITIVE LOGITS
    ITIVE
    0.27
    itivity
    0.24
    ITIONS
    0.24
    itional
    0.23
    izione
    0.23
    itive
    0.22
    session
    0.21
    idon
    0.21
    itives
    0.21
    iciones
    0.21
    Act Density 0.014%

    No Known Activations