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

    Neuronpedia

    INDEX
    Explanations

    common academic phrases and sentence structures often used in research papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    })));
    -0.87
    esez
    -0.74
     unknownFields
    -0.72
    KommentareTeilen
    -0.71
     beginnetje
    -0.71
    GEBURTSDATUM
    -0.70
    PreferredItem
    -0.69
     Insee
    -0.68
     noqa
    -0.67
    ніципалі
    -0.67
    POSITIVE LOGITS
    ebenarnya
    0.50
     väga
    0.48
    BagLayout
    0.47
    withstanding
    0.47
    près
    0.46
    Abbiamo
    0.46
    忙
    0.45
     figliu
    0.44
     CreateTagHelper
    0.44
    φαν
    0.44
    Act Density 0.341%

    No Known Activations