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

    Neuronpedia

    INDEX
    Explanations

    questions and statements about existence and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.20
     Berm
    -0.16
    sville
    -0.16
    ictor
    -0.15
    riend
    -0.15
    QUI
    -0.15
    ระ
    -0.14
    ernet
    -0.14
    sworth
    -0.14
    -END
    -0.14
    POSITIVE LOGITS
     else
    0.16
     Acres
    0.15
    pun
    0.15
     Bard
    0.15
     pur
    0.14
     Tate
    0.14
    bid
    0.14
     pun
    0.14
     virgin
    0.14
     bel
    0.14
    Act Density 0.061%

    No Known Activations