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

    Neuronpedia

    INDEX
    Explanations

    patterned sequences with special characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Droid
    -0.58
     Libyan
    -0.56
     Kenyan
    -0.52
     relay
    -0.52
     blacklist
    -0.52
     scattering
    -0.51
     rom
    -0.50
     board
    -0.50
     limitation
    -0.50
     bounty
    -0.50
    POSITIVE LOGITS
    ¹
    1.06
    Į
    0.91
    ¢
    0.88
    ²
    0.87
    ı
    0.87
    ¬
    0.86
    ¡
    0.86
    Ĵ
    0.85
    £
    0.84
    ł
    0.83
    Act Density 0.375%

    No Known Activations