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

    Neuronpedia

    INDEX
    Explanations

    words with unusual characters or symbols in them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    WARD
    -0.74
    wards
    -0.69
     Commodore
    -0.68
    swick
    -0.66
     Sidd
    -0.66
    ITNESS
    -0.63
    washed
    -0.61
     Stard
    -0.59
     SOS
    -0.58
     gratification
    -0.58
    POSITIVE LOGITS
    ł
    1.45
    ¾
    1.42
    ĭ
    1.41
    Ĵ
    1.41
    ģ
    1.38
    ĵ
    1.37
    Į
    1.33
    ©
    1.30
    ı
    1.29
    Ī
    1.26
    Act Density 0.023%

    No Known Activations