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

    Neuronpedia

    INDEX
    Explanations

    words related to reviews or assessments of documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Alba
    -0.69
     Schulte
    -0.69
    któ
    -0.66
     ausz
    -0.65
     Piet
    -0.64
    Lmao
    -0.64
     fais
    -0.63
     scratch
    -0.63
     test
    -0.59
     camps
    -0.59
    POSITIVE LOGITS
     Reviews
    1.51
     Review
    1.46
    Reviews
    1.38
     reviews
    1.34
    Review
    1.34
     REVIEWS
    1.34
    REVIEW
    1.34
     REVIEW
    1.32
    review
    1.26
     reviewer
    1.24
    Act Density 0.079%

    No Known Activations