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

    Neuronpedia

    INDEX
    Explanations

    discourse markers indicating that someone is stepping through a mathematical argument, often checking work

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¿Ļæĺ¯
    -0.07
    -that
    -0.07
     thats
    -0.07
    roi
    -0.06
    itoris
    -0.06
     yes
    -0.06
     sounds
    -0.06
     nothing
    -0.06
     ìĿ´ëĬĶ
    -0.06
     hå
    -0.06
    POSITIVE LOGITS
     now
    0.13
     Now
    0.13
    Now
    0.12
     maintenant
    0.10
    _now
    0.10
    çİ°åľ¨
    0.09
     ahora
    0.09
    now
    0.09
     teÄı
    0.09
    	now
    0.09
    Act Density 0.151%

    No Known Activations