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

    Neuronpedia

    INDEX
    Explanations

    references to arts-related topics such as art, culture, crafts, and artistic expressions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    odder
    -0.71
    aded
    -0.71
     Adin
    -0.70
     Paragu
    -0.68
    ading
    -0.68
    utations
    -0.68
    utable
    -0.65
    agher
    -0.65
    utation
    -0.64
    ishable
    -0.62
    POSITIVE LOGITS
    manship
    1.14
    esian
    1.04
    cape
    0.97
    pace
    0.84
     arts
    0.83
    chool
    0.81
    alon
    0.78
    isans
    0.77
    smanship
    0.75
     Profession
    0.75
    Act Density 10.347%

    No Known Activations