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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships among concepts or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (*((
    -0.15
    ç¿Ķ
    -0.14
    acman
    -0.14
    agnitude
    -0.13
    ubb
    -0.13
    ÏĦÎŃ
    -0.13
    *width
    -0.13
     gri
    -0.12
    _TC
    -0.12
    verbatim
    -0.12
    POSITIVE LOGITS
     connection
    0.62
     connections
    0.56
     link
    0.56
     relationship
    0.55
    connection
    0.50
     links
    0.49
    connections
    0.46
     connexion
    0.46
     relationships
    0.45
     relation
    0.45
    Act Density 0.283%

    No Known Activations