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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms related to a particular topic or individual

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -1.15
    LECT
    -1.02
     trickle
    -0.94
     constrained
    -0.90
     censored
    -0.90
    BuyableInstoreAndOnline
    -0.89
     Grateful
    -0.87
    DEN
    -0.87
     Metropolitan
    -0.86
     Korra
    -0.86
    POSITIVE LOGITS
    izoph
    1.88
    izophren
    1.57
    utz
    1.40
    afer
    1.36
    uler
    1.35
    midt
    1.29
    acht
    1.29
    nee
    1.29
    aeper
    1.28
    immer
    1.27
    Act Density 0.742%

    No Known Activations