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

    Neuronpedia

    INDEX
    Explanations

    text related to medical conditions or autoimmune diseases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    abase
    -1.08
    avorite
    -1.06
     reel
    -0.97
    usercontent
    -0.95
    undreds
    -0.93
    ufact
    -0.91
    gerald
    -0.90
    ournals
    -0.89
    psey
    -0.88
     inval
    -0.87
    POSITIVE LOGITS
    Mods
    0.98
    Administ
    0.92
    ãĥĢ
    0.90
    destruct
    0.90
     Tennis
    0.89
     Torment
    0.89
    foundation
    0.88
    ciation
    0.88
    wagen
    0.87
    Assistant
    0.87
    Act Density 3.671%

    No Known Activations