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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ratings and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.16
    pole
    -0.15
    zens
    -0.14
    lea
    -0.13
    AdapterFactory
    -0.13
    Fixture
    -0.13
    uto
    -0.13
    iad
    -0.13
    .GroupLayout
    -0.13
    _THRESH
    -0.13
    POSITIVE LOGITS
     stars
    0.23
     rating
    0.21
    stars
    0.20
     Stars
    0.19
     star
    0.19
    rating
    0.16
    _rating
    0.16
    Stars
    0.16
     æĺŁ
    0.16
     Rating
    0.16
    Act Density 0.034%

    No Known Activations