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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion and subjective viewpoints

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

    Followed by subjective words after "my"

    np_acts-logits-general · gemini-2.0-flash

    personal opinion or view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.74
     للمعارف
    -0.74
     فريبيس
    -0.73
     ""],
    -0.69
     AssemblyCompany
    -0.63
     ModelExpression
    -0.61
     насељу
    -0.61
     مشين
    -0.61
     '\\;'
    -0.60
    contentLoaded
    -0.59
    POSITIVE LOGITS
     opinion
    1.21
     view
    0.88
     humble
    0.85
    opinion
    0.85
     opinión
    0.83
     humilde
    0.79
     experience
    0.78
     belief
    0.75
     estimation
    0.74
     Opinion
    0.73
    Act Density 0.203%

    No Known Activations