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

    Neuronpedia

    INDEX
    Explanations

    instances of the contraction "you're."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awa
    -0.18
    rep
    -0.16
    zimmer
    -0.15
    styleType
    -0.15
    reach
    -0.15
    qus
    -0.15
    react
    -0.15
    prit
    -0.15
    reed
    -0.15
    CADE
    -0.15
    POSITIVE LOGITS
     gonna
    0.19
    becca
    0.16
     able
    0.16
    s
    0.16
    eks
    0.16
    ihan
    0.16
    illy
    0.16
    igious
    0.15
    ified
    0.15
    nbsp
    0.15
    Act Density 0.003%

    No Known Activations