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

    Neuronpedia

    INDEX
    Explanations

    phrases related to absolute or definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesz
    -0.17
    istol
    -0.17
    елен
    -0.15
    imir
    -0.15
    egis
    -0.15
     Wind
    -0.15
    絡
    -0.15
    Ñĥка
    -0.15
    iminal
    -0.15
    OKIE
    -0.14
    POSITIVE LOGITS
    .opens
    0.16
     Bonds
    0.16
    Ł
    0.14
    roups
    0.14
    aro
    0.14
     Incredible
    0.14
    ference
    0.14
    arf
    0.14
    èİİ
    0.13
    Ñĥда
    0.13
    Act Density 0.002%

    No Known Activations