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

    Neuronpedia

    INDEX
    Explanations

    terms related to customer reviews and feedback

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

    review or reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.60
    labus
    -0.54
    fillType
    -0.47
    AsUp
    -0.46
    transQ
    -0.45
    pushFollow
    -0.44
     surla
    -0.43
    úgó
    -0.43
    internalType
    -0.42
    OCCURRED
    -0.42
    POSITIVE LOGITS
     reviews
    2.08
     Reviews
    1.73
     review
    1.73
    reviews
    1.70
    Reviews
    1.64
     reviewers
    1.63
    review
    1.55
     reviewer
    1.52
     REVIEWS
    1.50
     Review
    1.45
    Act Density 0.123%

    No Known Activations