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

    Neuronpedia

    INDEX
    Explanations

    expressions of subjective experiences and positive sentiments

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

    Positive sentiment after a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives after was/is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.56
    RenderAtEndOf
    -0.56
     թվական
    -0.52
    lexikon
    -0.49
    amd
    -0.48
    <bos>
    -0.48
    AutoresizingMask
    -0.47
    andu
    -0.47
    vdots
    -0.46
    styleable
    -0.45
    POSITIVE LOGITS
     amazing
    0.88
     fantastic
    0.87
     great
    0.86
     brilliant
    0.85
     wonderful
    0.81
    fantastic
    0.81
     awesome
    0.81
    wonderful
    0.78
     marvelous
    0.77
    great
    0.77
    Act Density 0.186%

    No Known Activations