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

    Neuronpedia

    INDEX
    Explanations

    examples or instances in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ief
    -0.74
    ouls
    -0.72
    ternity
    -0.71
    ole
    -0.71
    ties
    -0.69
    resent
    -0.69
    ird
    -0.67
    ensibly
    -0.67
    rice
    -0.66
    nuts
    -0.66
    POSITIVE LOGITS
     illustrating
    1.09
     examples
    0.95
    wcsstore
    0.85
     subp
    0.84
     thereof
    0.83
     demonstrating
    0.82
     illustration
    0.81
     illustrate
    0.80
    Examples
    0.78
     example
    0.78
    Act Density 0.543%

    No Known Activations