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

    Neuronpedia

    INDEX
    Explanations

    commands or instructional information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     paperback
    -0.70
     document
    -0.66
     Airbnb
    -0.65
     monopoly
    -0.61
     guest
    -0.60
     coax
    -0.60
     charter
    -0.60
     Garmin
    -0.60
     horizont
    -0.59
     primaries
    -0.59
    POSITIVE LOGITS
    âĢ
    1.78
    »
    1.31
    Â
    1.31
    ^
    1.30
    «
    1.29
    """
    1.26
    *
    1.25
    ´
    1.24
    **
    1.24
    "(
    1.23
    Act Density 2.145%

    No Known Activations