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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Brief
    -0.95
    ataka
    -0.92
    ħĭ
    -0.86
     Commissioner
    -0.84
    imir
    -0.81
    rones
    -0.81
    ļéĨĴ
    -0.80
    imer
    -0.79
     Dull
    -0.78
    inis
    -0.77
    POSITIVE LOGITS
     (>
    1.44
     (~
    1.15
     (<
    1.05
     of
    1.05
    bang
    1.01
    UID
    0.95
    ÙĪ
    0.87
    Downloadha
    0.85
     thereof
    0.84
     imaginable
    0.82
    Act Density 1.651%

    No Known Activations