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

    Neuronpedia

    INDEX
    Explanations

    phrases that express specific qualities or characteristics of people, experiences, or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bour
    -0.18
     likely
    -0.16
    rote
    -0.14
    بÙĪر
    -0.14
    af
    -0.14
     yesterday
    -0.14
    ä¹ĭ
    -0.14
    ings
    -0.14
    rella
    -0.14
     eventual
    -0.14
    POSITIVE LOGITS
     coincidence
    0.19
     pleasure
    0.18
     duty
    0.18
     wonder
    0.18
    égor
    0.17
    engin
    0.17
    unger
    0.16
     toss
    0.15
     Duty
    0.15
     matter
    0.15
    Act Density 0.126%

    No Known Activations