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

    Neuronpedia

    INDEX
    Explanations

    names of characters or figures associated with fantasy or fiction stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.66
     EDITION
    -0.65
    !/
    -0.62
    REDACTED
    -0.60
    pants
    -0.59
     Canary
    -0.57
    ãģ®éŃĶ
    -0.57
     Amend
    -0.56
    DOWN
    -0.55
    uala
    -0.55
    POSITIVE LOGITS
    ching
    1.06
    gging
    0.98
    ggle
    0.92
    uled
    0.91
    uling
    0.90
    etooth
    0.88
    chers
    0.87
    gged
    0.86
    kered
    0.86
    ggles
    0.85
    Act Density 0.193%

    No Known Activations