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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns or names of places, particularly focusing on locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAttribute
    -0.38
     par
    -0.37
     acting
    -0.34
     sta
    -0.34
     front
    -0.34
    TextBoxColumn
    -0.33
    DeclareMath
    -0.33
     bantu
    -0.33
     vote
    -0.33
     clearly
    -0.32
    POSITIVE LOGITS
    lamabad
    0.70
    GOTREF
    0.66
    setVerticalGroup
    0.62
    tanooga
    0.59
    iſen
    0.59
    ValueStyle
    0.58
     ciudad
    0.57
    ſehen
    0.57
     ſei
    0.55
     utafitiHapana
    0.55
    Act Density 0.421%

    No Known Activations