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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or expressions of doubt

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

    Negation before "surprise" or similar words

    np_acts-logits-general · gemini-2.0-flash

    not surprising / no surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.67
    mobileqq
    -0.65
    Tikang
    -0.63
     initComponents
    -0.62
    !*\
    -0.60
    HtmlAttribute
    -0.59
     autorytatywna
    -0.59
    __':
    -0.58
    اشتی
    -0.57
    writeValue
    -0.57
    POSITIVE LOGITS
     surprise
    1.45
    surprise
    1.17
     surprised
    1.10
     Surprise
    1.07
     surprises
    1.06
     surprising
    1.05
     shock
    1.02
     wonder
    1.02
     surpris
    1.00
    Surprise
    1.00
    Act Density 0.171%

    No Known Activations