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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" and variations of it used in contexts that express emphasis or conclusion

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

    so followed by a consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.77
    Personendaten
    -0.68
     Menſchen
    -0.58
    pholes
    -0.57
     Chwiliwch
    -0.57
    <unused32>
    -0.56
    󰈻
    -0.56
    ᔢ
    -0.56
    𝆺
    -0.56
     שוליים
    -0.56
    POSITIVE LOGITS
     So
    0.28
    ENJOY
    0.27
     Profitez
    0.27
    Enjoy
    0.26
     cara
    0.26
     ethylene
    0.26
    isNameExpr
    0.26
    这意味着
    0.26
    这一点
    0.26
     verspre
    0.26
    Act Density 0.017%

    No Known Activations