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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imize
    -0.71
    eny
    -0.68
     withdraw
    -0.67
     unm
    -0.66
     faire
    -0.66
    BILITIES
    -0.66
    iband
    -0.65
    bring
    -0.65
    mage
    -0.64
    iencies
    -0.64
    POSITIVE LOGITS
     Plenty
    1.01
     Numerous
    0.97
     Indeed
    0.94
     Several
    0.87
     Various
    0.85
     Dozens
    0.81
     Throughout
    0.80
     Earlier
    0.79
     Recent
    0.78
     Nor
    0.78
    Act Density 0.299%

    No Known Activations