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

    Neuronpedia

    INDEX
    Explanations

    names that start with "Ly" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DERR
    -0.77
    sburgh
    -0.68
    raints
    -0.64
     UID
    -0.60
     EDITION
    -0.59
    ardless
    -0.59
    perture
    -0.58
     Boards
    -0.57
    shots
    -0.57
    urities
    -0.56
    POSITIVE LOGITS
    onna
    1.08
    nda
    1.07
    nton
    1.02
    comed
    1.00
    rics
    0.98
    ric
    0.97
    rique
    0.96
    ttle
    0.94
    onel
    0.92
    mp
    0.92
    Act Density 0.019%

    No Known Activations