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

    Neuronpedia

    INDEX
    Explanations

    phrases that assert or emphasize factual statements

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

    in fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.52
     betweenstory
    -0.52
    ThemeOverlay
    -0.48
    ifikationer
    -0.46
     tentunya
    -0.43
    
    -0.41
    ReusableCell
    -0.41
     Италијани
    -0.41
     يتيمه
    -0.41
    MessageOf
    -0.40
    POSITIVE LOGITS
    multicolumn
    0.51
    Personendaten
    0.49
     مشين
    0.48
    ftagPool
    0.48
     שוליים
    0.47
     Chwiliwch
    0.46
    rungsseite
    0.45
    \[
    0.44
     very
    0.44
    isinstance
    0.44
    Act Density 0.009%

    No Known Activations