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

    Neuronpedia

    INDEX
    Explanations

    locations or places where specific events occur or individuals are found

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    apult
    -0.67
    ³³³³³³³³
    -0.64
    ets
    -0.64
     guessing
    -0.64
    ply
    -0.59
    rolet
    -0.58
    telling
    -0.58
     Pwr
    -0.57
    âĨ
    -0.56
    yi
    -0.56
    POSITIVE LOGITS
    upon
    1.16
    abouts
    1.11
    soever
    0.93
    fore
    0.76
     frequ
    0.73
    izen
    0.71
     houses
    0.68
    abama
    0.66
    izens
    0.65
     [|
    0.65
    Act Density 11.428%

    No Known Activations