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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines and reports

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ********************************
    -0.79
    whatever
    -0.68
    Hunt
    -0.68
    iton
    -0.67
    NOW
    -0.66
    Magikarp
    -0.65
    Tweet
    -0.65
    minecraft
    -0.64
    Advertisements
    -0.64
    him
    -0.64
    POSITIVE LOGITS
     Reuters
    0.83
     Hide
    0.81
     REUTERS
    0.77
     Caption
    0.76
     Cindy
    0.72
    window
    0.72
     Thousands
    0.68
     Nasa
    0.67
     People
    0.66
     Laura
    0.66
    Act Density 0.069%

    No Known Activations