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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating membership or composition of groups or teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.16
    ¢åįķ
    -0.16
    .Logic
    -0.15
     Olson
    -0.14
    ovy
    -0.14
    овиÑĩ
    -0.14
    ilo
    -0.14
    å®ľ
    -0.14
    tie
    -0.13
     way
    -0.13
    POSITIVE LOGITS
    ttp
    0.15
    setImage
    0.15
    нак
    0.15
    Å¡ek
    0.14
    uggy
    0.14
     Bren
    0.14
     Ñįк
    0.14
    以为
    0.14
     nóng
    0.14
    WISE
    0.14
    Act Density 0.103%

    No Known Activations