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

    Neuronpedia

    INDEX
    Explanations

    the past tense of the verb 'predict'

    oai_token-act-pair · gpt-4-turbo

    predictions or statements about the future

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "predicted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tha
    -0.78
    zanne
    -0.75
    itol
    -0.74
    atri
    -0.70
    unal
    -0.70
    xia
    -0.70
    atha
    -0.69
    Bio
    -0.69
    ste
    -0.69
    cit
    -0.68
    POSITIVE LOGITS
     predicts
    1.09
     predict
    1.07
     predicted
    1.03
     forecasts
    1.00
     predictions
    0.98
     doom
    0.88
     forecast
    0.87
     prediction
    0.84
     predicting
    0.84
    ãĤ¼ãĤ¦ãĤ¹
    0.77
    Act Density 0.015%

    No Known Activations