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

    Neuronpedia

    INDEX
    Explanations

    statements that emphasize agreement or affirmation in conversation

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

    of course,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CreateModel
    -0.39
     TestBed
    -0.35
    -------------</
    -0.34
    glied
    -0.34
     entr
    -0.33
     مشارکت‌کنندگان
    -0.33
    setVerticalGroup
    -0.33
    httphttps
    -0.33
    formik
    -0.32
    DOCTYPE
    -0.32
    POSITIVE LOGITS
     oczywiście
    0.83
    czywiście
    0.83
    følgelig
    0.82
     course
    0.76
     Course
    0.75
    eraard
    0.75
     natuurlijk
    0.75
    Course
    0.74
    course
    0.73
     freilich
    0.72
    Act Density 0.014%

    No Known Activations