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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.71
    ãĤ´ãĥ³
    -0.71
    olo
    -0.70
    plete
    -0.64
    ét
    -0.64
    livion
    -0.63
    ée
    -0.61
    zilla
    -0.61
     anew
    -0.61
     alongside
    -0.60
    POSITIVE LOGITS
     aforementioned
    1.01
     heaviest
    1.01
     greatest
    1.00
     earliest
    0.99
    ses
    0.99
     strongest
    0.97
     biggest
    0.97
     toughest
    0.97
     brightest
    0.96
     smallest
    0.94
    Act Density 0.124%

    No Known Activations