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

    Neuronpedia

    INDEX
    Explanations

    words related to keeping up with various topics or staying informed

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BALL
    -1.03
     Barg
    -1.01
     Glock
    -1.00
    FAULT
    -0.93
     Kahn
    -0.91
     Fields
    -0.91
    yne
    -0.88
    BUT
    -0.87
     Torn
    -0.87
     Caldwell
    -0.86
    POSITIVE LOGITS
    dates
    1.16
    endra
    1.13
     appearances
    1.09
    ris
    1.03
    iments
    1.00
    motion
    0.99
    icts
    0.99
    vation
    0.98
    urga
    0.97
    inet
    0.97
    Act Density 0.379%

    No Known Activations