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

    Neuronpedia

    INDEX
    Explanations

    words related to names and titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    wagen
    -0.67
    taboola
    -0.61
     gears
    -0.59
     sidewalks
    -0.58
    ĨĴ
    -0.58
     panc
    -0.58
     liter
    -0.57
    interstitial
    -0.57
    ¬¼
    -0.56
    ĸļ
    -0.56
    POSITIVE LOGITS
    aline
    0.90
    istration
    0.71
    itness
    0.70
    ause
    0.70
    anamo
    0.69
    ainment
    0.68
    minus
    0.68
     Ake
    0.68
    enment
    0.67
    andise
    0.66
    Act Density 0.096%

    No Known Activations