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

    Neuronpedia

    INDEX
    Explanations

    ISBNs and dois in academic references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    itutional
    -0.98
    abal
    -0.97
    abo
    -0.97
    olas
    -0.92
    omnia
    -0.92
    atel
    -0.91
    hips
    -0.90
    obyl
    -0.90
    orie
    -0.89
    zech
    -0.88
    POSITIVE LOGITS
    ctors
    0.97
    é»Ĵ
    0.92
    æ©Ł
    0.91
    76561
    0.89
    WARN
    0.88
    1016
    0.86
     gp
    0.85
     theorem
    0.83
    ãĤ¦ãĤ¹
    0.82
    1007
    0.81
    Act Density 0.065%

    No Known Activations