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

    Neuronpedia

    INDEX
    Explanations

    negations or the word "no" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arse
    -0.17
     scant
    -0.15
    anzi
    -0.15
    null
    -0.14
    ÑĢеж
    -0.14
    ongs
    -0.14
    é¡
    -0.14
    pis
    -0.14
    ivery
    -0.14
    Ñĥки
    -0.14
    POSITIVE LOGITS
     reason
    0.23
     denying
    0.22
     need
    0.20
     doubt
    0.20
     chance
    0.18
     guarantee
    0.17
     way
    0.17
     question
    0.17
    ади
    0.16
    ItemSelected
    0.16
    Act Density 0.046%

    No Known Activations