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

    Neuronpedia

    INDEX
    Explanations

    question marks and other punctuation that indicates uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eters
    -0.17
    utex
    -0.15
    CREMENT
    -0.15
    edelta
    -0.14
     Gund
    -0.14
    etty
    -0.14
    nga
    -0.14
    Ñħодим
    -0.14
    antino
    -0.14
    VRT
    -0.13
    POSITIVE LOGITS
    ynn
    0.16
    åºŃ
    0.15
    umped
    0.15
    QL
    0.15
    ource
    0.14
    ereum
    0.14
    Ïīδ
    0.14
    ogue
    0.13
    040
    0.13
    eer
    0.13
    Act Density 0.048%

    No Known Activations