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

    Neuronpedia

    INDEX
    Explanations

    references to different types of paper products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.87
    ]--;
    -0.86
    Witam
    -0.85
    paravant
    -0.83
     uitges
    -0.80
    olische
    -0.79
    URIComponent
    -0.78
    )++;
    -0.78
    DataAnnotations
    -0.78
    centerX
    -0.77
    POSITIVE LOGITS
     PAPER
    1.81
     Paper
    1.74
    Paper
    1.69
     paper
    1.66
    paper
    1.61
     Papers
    1.54
     papers
    1.48
    PAPER
    1.47
     PAPERS
    1.42
    papier
    1.24
    Act Density 0.108%

    No Known Activations