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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    I hope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abweich
    -0.43
     katholischen
    -0.43
    IntoConstraints
    -0.40
    ViewImports
    -0.40
    GOTREF
    -0.40
     Sünde
    -0.40
     escase
    -0.40
    をお願い
    -0.40
     Nachbarn
    -0.40
     Bewegungen
    -0.39
    POSITIVE LOGITS
     enjoy
    1.30
    enjoy
    1.19
     enjoyment
    1.14
     Enjoy
    1.13
     enjoying
    1.10
     enjoyed
    1.10
     enjoys
    1.07
     ENJOY
    1.06
    Enjoy
    1.06
    Enjoying
    0.96
    Act Density 0.059%

    No Known Activations