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

    Neuronpedia

    INDEX
    Explanations

    references to personalization and ownership in the text

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

    the positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.45
     household
    -0.37
     dụ
    -0.35
    toPromise
    -0.35
    
    -0.34
     physicians
    -0.33
     koning
    -0.33
     quæ
    -0.32
     Dhabi
    -0.32
     Wikiseite
    -0.32
    POSITIVE LOGITS
     للمعارف
    0.70
     idéia
    0.65
     nice
    0.62
     aporta
    0.59
    xase
    0.59
    Nice
    0.57
     idea
    0.57
     ddelweddau
    0.54
    nice
    0.53
     Nice
    0.52
    Act Density 0.012%

    No Known Activations