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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    řeba
    -0.58
     otomatig
    -0.56
     المعيارى
    -0.48
     Duty
    -0.46
    duty
    -0.46
    <()>
    -0.46
    ：“……”
    -0.46
    elter
    -0.45
    antMatchers
    -0.45
    ⊂
    -0.45
    POSITIVE LOGITS
     rating
    0.83
     ✭✭
    0.70
     stars
    0.69
    rating
    0.67
     RATING
    0.65
    RATING
    0.64
     Rating
    0.63
    Rating
    0.62
     ratings
    0.61
     faute
    0.60
    Act Density 0.212%

    No Known Activations