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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing and submitting reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "review" or "rating"

    np_acts-logits-general · gemini-2.0-flash

    reviews and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convocatoria
    -0.37
     aulas
    -0.36
     intptr
    -0.35
     rozwiązania
    -0.35
    Rüyada
    -0.35
     sintética
    -0.35
    adpleegd
    -0.34
    rrggbb
    -0.34
     Schenk
    -0.34
     COMMERCIAL
    -0.34
    POSITIVE LOGITS
     Yelp
    0.51
     चीज़ों
    0.51
     review
    0.50
     Feedback
    0.50
     Ratings
    0.49
     ratings
    0.48
     rating
    0.47
     grader
    0.46
    ratings
    0.45
     feedback
    0.45
    Act Density 0.300%

    No Known Activations