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

    Neuronpedia

    INDEX
    Explanations

    dates, locations, and names of people

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or closing punctuation marks in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frog
    -0.67
    products
    -0.63
    users
    -0.62
    sembly
    -0.61
     cloves
    -0.61
    Ń·
    -0.60
     domestically
    -0.60
     sails
    -0.60
     burner
    -0.59
     spam
    -0.59
    POSITIVE LOGITS
    Actor
    0.76
    Madison
    0.74
    Associated
    0.72
     ILCS
    0.71
    Original
    0.71
    htaking
    0.69
    Correct
    0.69
    TAG
    0.68
    Letter
    0.67
    Ev
    0.67
    Act Density 0.096%

    No Known Activations