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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity and praise

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

    great wonderful awesome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLR
    -0.44
     candle
    -0.42
    DockStyle
    -0.42
    PropertyChanging
    -0.41
    MessageTagHelper
    -0.41
    mahl
    -0.40
     INTERESAR
    -0.40
    帖最后由
    -0.40
    ChildScrollView
    -0.39
    RTLI
    -0.39
    POSITIVE LOGITS
    Wonderful
    0.63
     للمعارف
    0.62
     great
    0.58
     Wonderful
    0.57
    great
    0.57
    Great
    0.56
     wonderful
    0.56
    wonderful
    0.55
     مرئيه
    0.54
     awesome
    0.52
    Act Density 0.016%

    No Known Activations