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

    Neuronpedia

    INDEX
    Explanations

    numbers preceded by the letter 'b'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bilt
    -0.69
    æ©Ł
    -0.59
     XY
    -0.58
    Plex
    -0.58
     Nadu
    -0.58
     Spartan
    -0.56
    ãĥ´ãĤ¡
    -0.56
     Pharaoh
    -0.55
     Deity
    -0.54
     por
    -0.53
    POSITIVE LOGITS
    ibli
    1.11
    idd
    1.09
    abb
    1.05
    rows
    1.05
    ibliography
    1.01
    aked
    1.00
    abbling
    0.97
    raid
    0.97
    urt
    0.96
    rawn
    0.95
    Act Density 8.003%

    No Known Activations