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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assistance and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olik
    -0.18
    udeau
    -0.17
    asar
    -0.16
    лек
    -0.16
    ogan
    -0.16
    uide
    -0.15
    çķ
    -0.15
    TEGR
    -0.14
    ohana
    -0.14
    ToBounds
    -0.14
    POSITIVE LOGITS
     of
    0.19
     yours
    0.17
     của
    0.17
    ạn
    0.17
     by
    0.16
    clamation
    0.16
     from
    0.16
     hers
    0.15
    264
    0.15
    ings
    0.14
    Act Density 0.095%

    No Known Activations