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

    Neuronpedia

    INDEX
    Explanations

    references to star ratings and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asal
    -0.18
    alez
    -0.15
     ÑģвеÑĢ
    -0.15
    uxe
    -0.15
    tie
    -0.15
    éľĬ
    -0.14
    )((((
    -0.14
    ffa
    -0.14
     Verfüg
    -0.14
    stem
    -0.14
    POSITIVE LOGITS
     rating
    0.29
    rating
    0.25
     star
    0.24
     Rating
    0.24
     stars
    0.23
     ratings
    0.21
    .rating
    0.21
    -rating
    0.21
    _rating
    0.21
    Rating
    0.20
    Act Density 0.050%

    No Known Activations