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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "declare" and its variations, indicating announcements or formal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eway
    -0.15
    cake
    -0.15
    ipi
    -0.15
    ëĭ¹
    -0.15
    ÃŁer
    -0.15
    728
    -0.14
    íģ
    -0.14
    uzey
    -0.14
    verter
    -0.14
    _regularizer
    -0.14
    POSITIVE LOGITS
    ums
    0.19
    dcc
    0.15
    inger
    0.15
    indle
    0.15
     possession
    0.14
    umn
    0.14
    l
    0.14
    anson
    0.14
    anton
    0.14
    0.13
    Act Density 0.009%

    No Known Activations