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

    Neuronpedia

    INDEX
    Explanations

    dates and times mentioned in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     aides
    -0.91
    Enlarge
    -0.89
    toggle
    -0.84
     ÂŃ
    -0.79
     tumult
    -0.78
     advisers
    -0.76
    Newsletter
    -0.76
     POLITICO
    -0.74
     afterward
    -0.73
    Adds
    -0.72
    POSITIVE LOGITS
     whilst
    1.17
     Whilst
    1.15
    Âł
    1.02
     ³³
    0.99
     âĸĪ
    0.95
     USD
    0.93
     Youtube
    0.92
     HUGE
    0.91
     ~
    0.91
     HW
    0.90
    Act Density 1.438%

    No Known Activations