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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "morality"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pta
    -0.73
     Reboot
    -0.72
     Tycoon
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.64
    Customer
    -0.62
     Carbuncle
    -0.61
     depreciation
    -0.60
    erness
    -0.57
     Socket
    -0.56
    0000000
    -0.56
    POSITIVE LOGITS
    pheus
    1.36
    atorium
    1.13
    imoto
    1.10
    rison
    1.10
    rigan
    1.09
    bid
    1.00
    ality
    0.98
    als
    0.96
    phe
    0.95
    ikawa
    0.95
    Act Density 0.034%

    No Known Activations