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

    Neuronpedia

    INDEX
    Explanations

    technical terms and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.75
     disadvant
    -0.70
    ModLoader
    -0.69
     compe
    -0.69
    TAIN
    -0.68
     Palestin
    -0.67
    tenance
    -0.66
    WAYS
    -0.66
     Staples
    -0.65
    HAEL
    -0.65
    POSITIVE LOGITS
    ebra
    1.11
    ooming
    1.06
    eros
    1.05
    ipped
    1.04
    ither
    0.95
    ipping
    0.95
    ippers
    0.94
    odiac
    0.92
    ipper
    0.90
    oned
    0.89
    Act Density 4.137%

    No Known Activations