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

    Neuronpedia

    INDEX
    Explanations

    references to ordinal numbers, specifically focusing on "fifth" and "sixth."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    er
    -0.95
    ه
    -0.75
    ers
    -0.73
    es
    -0.71
    ة
    -0.66
     Bel
    -0.66
    eri
    -0.66
     Sec
    -0.64
    ing
    -0.64
     Ges
    -0.63
    POSITIVE LOGITS
     ISNI
    1.09
    theless
    0.92
     propOrder
    0.92
    anniversaire
    0.86
    multer
    0.84
    etheless
    0.83
     Theſe
    0.83
    Hentet
    0.82
    fifths
    0.82
    Normdaten
    0.81
    Act Density 0.015%

    No Known Activations