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

    Neuronpedia

    INDEX
    Explanations

    information related to health and medical topics, including diseases, treatments, and research findings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.45
    opoulos
    -0.43
    hiba
    -0.42
    aten
    -0.41
    ulously
    -0.41
    anium
    -0.41
     incidentally
    -0.41
     subsid
    -0.40
     destro
    -0.39
     constitu
    -0.38
    POSITIVE LOGITS
    Brow
    0.54
    Reading
    0.51
    Ill
    0.49
    Training
    0.45
    Prosecut
    0.44
    Around
    0.43
    Advertisement
    0.43
    Law
    0.42
    Cour
    0.42
    violence
    0.42
    Act Density 0.380%

    No Known Activations