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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, such as names of individuals and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     mourut
    -0.91
     eorum
    -0.88
     ejus
    -0.83
     trouva
    -0.80
    RectangleBorder
    -0.80
     PLWABN
    -0.78
     vinil
    -0.77
     LIRE
    -0.75
     travaillons
    -0.75
     tantum
    -0.75
    POSITIVE LOGITS
     has
    0.80
     attemp
    0.78
     exemplifies
    0.77
     is
    0.75
     began
    0.73
     ftw
    0.73
     definately
    0.72
     succinctly
    0.69
     embodies
    0.69
     occupies
    0.69
    Act Density 2.105%

    No Known Activations