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

    Neuronpedia

    INDEX
    Explanations

    scientific disciplines and academic positions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pload
    -0.77
    CRIP
    -0.73
    MSN
    -0.72
    ãĥ¼ãĥ³
    -0.70
    ãĥ¤
    -0.68
     blacklist
    -0.66
    ãĥīãĥ©
    -0.64
    inventoryQuantity
    -0.63
    ghazi
    -0.62
     KILL
    -0.61
    POSITIVE LOGITS
     faculty
    1.15
     doctoral
    1.15
     Faculty
    1.11
     professor
    1.06
     undergraduate
    1.04
     NYU
    1.03
     PhD
    1.03
     graduate
    1.01
     Cornell
    0.98
     UCLA
    0.98
    Act Density 0.112%

    No Known Activations