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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     שוליים
    -0.79
     للمعارف
    -0.77
     ligiloj
    -0.75
     يتيمه
    -0.73
    +#+
    -0.72
     تانيه
    -0.70
    orited
    -0.69
     estekak
    -0.69
    Portail
    -0.66
    出版年
    -0.64
    POSITIVE LOGITS
     confidently
    0.42
     समीक्षाओं
    0.40
    diğini
    0.40
    houding
    0.40
    nyata
    0.39
    visão
    0.39
    جی
    0.39
     cosa
    0.39
    rollen
    0.39
    afficheront
    0.38
    Act Density 0.006%

    No Known Activations