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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıн
    -0.17
    ka
    -0.16
     destruct
    -0.16
    ams
    -0.15
    ences
    -0.14
    @brief
    -0.14
    omer
    -0.14
    alles
    -0.14
    etas
    -0.14
    enie
    -0.14
    POSITIVE LOGITS
    pie
    0.16
    iative
    0.15
    raki
    0.15
    688
    0.15
    agr
    0.14
    iser
    0.14
    agento
    0.14
    icut
    0.14
    agli
    0.14
    isol
    0.14
    Act Density 0.021%

    No Known Activations