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

    Neuronpedia

    INDEX
    Explanations

    words that emphasize quantifiable attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ale
    -0.16
    Incoming
    -0.15
    ippers
    -0.15
    oon
    -0.15
    æī¶
    -0.14
    oons
    -0.14
    ease
    -0.14
    getID
    -0.14
    Disclosure
    -0.14
    ç¿
    -0.14
    POSITIVE LOGITS
     appeals
    0.16
    ÑģоÑĤ
    0.16
    amet
    0.15
    retty
    0.15
     Appeals
    0.14
    heit
    0.14
    лаÑĤи
    0.14
     Monte
    0.14
    rg
    0.14
    .Java
    0.14
    Act Density 0.004%

    No Known Activations