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

    Neuronpedia

    INDEX
    Explanations

    statements involving predictions or forecasting

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to forecasting or making predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atin
    -0.74
    tha
    -0.70
    unal
    -0.67
    untu
    -0.66
    ":"/
    -0.65
    atri
    -0.65
    ansk
    -0.65
    ento
    -0.64
    dx
    -0.63
    bestos
    -0.63
    POSITIVE LOGITS
     predicts
    0.89
     predict
    0.88
     forecasts
    0.86
    pred
    0.85
     doom
    0.83
     predicted
    0.82
     predictions
    0.82
     prediction
    0.77
     predicting
    0.76
     Prediction
    0.73
    Act Density 0.027%

    No Known Activations