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

    Neuronpedia

    INDEX
    Explanations

    words related to various professions and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Azerb
    -0.62
     disadvant
    -0.58
     Seym
    -0.58
    DonaldTrump
    -0.56
    ibrary
    -0.50
     accord
    -0.49
     Sutherland
    -0.48
     Vaugh
    -0.47
     suspic
    -0.47
     Moroc
    -0.47
    POSITIVE LOGITS
     alike
    1.07
     thereof
    0.84
     respectively
    0.77
    cellaneous
    0.74
     versa
    0.72
     thereto
    0.71
     thereafter
    0.67
    axter
    0.63
     Streets
    0.57
     consequ
    0.56
    Act Density 0.854%

    No Known Activations