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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "paper"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.80
    FormTagHelper
    -0.78
    paravant
    -0.74
    rescence
    -0.73
    DataAnnotations
    -0.71
     CWE
    -0.71
    ]--;
    -0.71
     betweenstory
    -0.71
    {{/
    -0.71
     Glance
    -0.69
    POSITIVE LOGITS
     PAPER
    1.80
     Paper
    1.72
    Paper
    1.68
     paper
    1.66
     Papers
    1.61
    paper
    1.60
    PAPER
    1.59
     papers
    1.50
     PAPERS
    1.50
    Papers
    1.35
    Act Density 0.030%

    No Known Activations