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

    Neuronpedia

    INDEX
    Explanations

    titles of movies and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elige
    -0.14
    alama
    -0.14
     norm
    -0.13
    ansi
    -0.13
    kaz
    -0.13
    mont
    -0.13
    antity
    -0.13
    reso
    -0.13
     cig
    -0.13
    uki
    -0.13
    POSITIVE LOGITS
     review
    0.88
     Review
    0.75
    review
    0.73
    -review
    0.72
     reviews
    0.72
     REVIEW
    0.69
     reviewed
    0.68
    Review
    0.67
    _review
    0.66
     reviewing
    0.63
    Act Density 0.273%

    No Known Activations