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

    Neuronpedia

    INDEX
    Explanations

    ratings or scores associated with films or products

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

    positive ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.54
     Administrativna
    -0.44
    identified
    -0.43
    reasonably
    -0.43
    省市镇
    -0.42
    parsedMessage
    -0.42
     Insets
    -0.41
     viti
    -0.41
    MathML
    -0.41
    urlencoded
    -0.40
    POSITIVE LOGITS
     rating
    0.61
     deserving
    0.52
     deserved
    0.50
     definitely
    0.49
     worthy
    0.48
     truly
    0.47
     ratings
    0.47
     RATING
    0.46
     excellent
    0.46
    Truly
    0.46
    Act Density 0.008%

    No Known Activations