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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions and nouns associated with relationships and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufen
    -0.15
    illian
    -0.15
    udson
    -0.15
    ossal
    -0.14
    é¼ł
    -0.14
    vara
    -0.14
     Bray
    -0.14
    chwitz
    -0.14
    CCA
    -0.14
     Gravity
    -0.13
    POSITIVE LOGITS
    onda
    0.15
     Sad
    0.14
    bach
    0.14
     McGu
    0.14
    uga
    0.14
    lon
    0.14
     Avg
    0.14
     DISCLAIMER
    0.14
    -----------*/↵
    0.14
    349
    0.14
    Act Density 0.002%

    No Known Activations