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

    Neuronpedia

    INDEX
    Explanations

    articles and determiners in legal text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.73
    IntoConstraints
    -0.72
    NameInMap
    -0.71
     BorderRadius
    -0.69
    prüche
    -0.69
     ccm
    -0.69
    +#+#
    -0.69
    RetentionPolicy
    -0.68
    verwijspagina
    -0.67
     समीक्षक
    -0.66
    POSITIVE LOGITS
     I
    0.63
    Related
    0.52
     menudo
    0.52
     '../
    0.51
    Seth
    0.50
    RELATED
    0.50
    </h3>
    0.49
     Collins
    0.48
     jeux
    0.48
    Lester
    0.48
    Act Density 0.020%

    No Known Activations