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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

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

    purpose or intention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ammans
    -0.48
     avoient
    -0.43
    ((-
    -0.41
     enfans
    -0.40
     normaux
    -0.40
     fenomeno
    -0.38
     sonno
    -0.37
    Transparency
    -0.37
     évêque
    -0.37
     pouvoit
    -0.37
    POSITIVE LOGITS
     için
    1.36
     लिए
    0.87
     위해
    0.84
     জন্য
    0.77
     위한
    0.69
     uchun
    0.64
     üzere
    0.63
     تكبرها
    0.61
    ForType
    0.58
    ために
    0.57
    Act Density 0.001%

    No Known Activations