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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Anything
    -0.67
    ³³³³
    -0.63
     Bound
    -0.62
     VIDEOS
    -0.61
     Anyway
    -0.61
    BACK
    -0.59
    ãĤª
    -0.59
     Delicious
    -0.57
     Federation
    -0.56
     Beet
    -0.55
    POSITIVE LOGITS
    oping
    1.01
    oped
    0.94
     accompanies
    0.93
     frequ
    0.91
    soever
    0.88
     preceded
    0.88
     resided
    0.84
     specialize
    0.81
     accompanied
    0.81
     specializes
    0.80
    Act Density 10.181%

    No Known Activations