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

    Neuronpedia

    INDEX
    Explanations

    interrogative words indicating questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.16
    ITO
    -0.15
    alty
    -0.15
    ill
    -0.15
    idis
    -0.14
    IMUM
    -0.14
    orate
    -0.14
    ubat
    -0.14
     -
    -0.14
    ople
    -0.13
    POSITIVE LOGITS
    soever
    0.21
    ever
    0.18
    -ever
    0.14
     NOTIFY
    0.14
    utsch
    0.14
    목
    0.14
    ालत
    0.14
    obe
    0.14
     ÑĪи
    0.14
    icha
    0.13
    Act Density 0.112%

    No Known Activations