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

    Neuronpedia

    INDEX
    Explanations

    ratings or evaluations related to stars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.88
    -0.85
     InputDecoration
    -0.84
     JpaRepository
    -0.80
    AndEndTag
    -0.79
    Бахар
    -0.78
    <()>
    -0.77
    +#+
    -0.76
     يتيمه
    -0.76
    帖最后由
    -0.75
    POSITIVE LOGITS
     stars
    1.01
     star
    0.94
    stars
    0.92
     Stars
    0.87
    star
    0.84
    Stars
    0.82
     STARS
    0.77
     estrellas
    0.71
    Star
    0.71
     Star
    0.70
    Act Density 0.790%

    No Known Activations