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

    Neuronpedia

    INDEX
    Explanations

    concepts related to conditions, relationships, and consequences in discussions about categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    morph
    -0.16
     ë°ĶëĿ¼
    -0.15
    à¸ģà¸ķ
    -0.15
    490
    -0.15
     morph
    -0.14
    質
    -0.14
    references
    -0.14
    edd
    -0.14
    gaard
    -0.14
    IGENCE
    -0.14
    POSITIVE LOGITS
     milit
    0.17
     superv
    0.16
     incident
    0.15
     bids
    0.15
     deg
    0.15
     must
    0.15
     doubt
    0.14
     crow
    0.14
     bid
    0.14
     afford
    0.14
    Act Density 0.354%

    No Known Activations