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

    Neuronpedia

    INDEX
    Explanations

    email addresses for queries and comments

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evidence
    -0.90
    agree
    -0.68
     organs
    -0.66
     allegations
    -0.65
     infl
    -0.64
    independence
    -0.64
     opposes
    -0.64
    anism
    -0.63
    independent
    -0.63
    aneously
    -0.63
    POSITIVE LOGITS
     bunch
    1.36
     lot
    1.26
     couple
    1.21
     few
    1.17
     bit
    1.10
     nice
    1.09
     handful
    1.08
     little
    1.00
     glimpse
    0.99
     decent
    0.97
    Act Density 0.848%

    No Known Activations