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

    Neuronpedia

    INDEX
    Explanations

    words related to predictability or prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prediction or forecasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zanne
    -0.75
    mis
    -0.71
     Antiqu
    -0.71
    unal
    -0.71
    tha
    -0.70
    ":"/
    -0.68
    gur
    -0.67
     Wine
    -0.66
    Tea
    -0.63
    este
    -0.63
    POSITIVE LOGITS
     predict
    1.25
     predicts
    1.01
     predicting
    0.99
    ively
    0.97
     probabilities
    0.97
     predictions
    0.92
     predicted
    0.91
     Predict
    0.91
    ministic
    0.89
     prediction
    0.89
    Act Density 0.006%

    No Known Activations