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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and rhetorical questions

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

    about you / my mom / am an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.72
    BagConstraints
    -0.60
    باردا
    -0.54
     صوتيه
    -0.52
    𓃵
    -0.52
    Ⴈ
    -0.52
    bootstrapcdn
    -0.52
    〼
    -0.52
    rillation
    -0.51
    征詢我
    -0.51
    POSITIVE LOGITS
     school
    0.38
     everybody
    0.37
    school
    0.35
    école
    0.34
     diamants
    0.34
     dieux
    0.33
     kid
    0.33
     ennemi
    0.32
    Everybody
    0.31
     Everybody
    0.31
    Act Density 0.021%

    No Known Activations