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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration and mutual development in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.74
    Diweddarwch
    -0.57
     وتسجيلات
    -0.55
     monté
    -0.54
    <bos>
    -0.54
     précé
    -0.53
     enfans
    -0.53
     insuffisamment
    -0.52
     maïs
    -0.51
     apoi
    -0.51
    POSITIVE LOGITS
    ereich
    0.58
     whites
    0.57
    ::*;
    0.54
    OGND
    0.53
     Velo
    0.52
     Numerade
    0.52
    пт
    0.52
    ండి
    0.52
     Stere
    0.52
     grades
    0.51
    Act Density 0.115%

    No Known Activations