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

    Neuronpedia

    INDEX
    Explanations

    words related to deep engagement or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unp
    -0.16
    pare
    -0.14
     Loft
    -0.14
    ize
    -0.14
    airy
    -0.14
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.14
    wy
    -0.13
    adora
    -0.13
     Across
    -0.13
     Dies
    -0.13
    POSITIVE LOGITS
     deeper
    0.23
     deep
    0.23
     deeply
    0.19
     completely
    0.19
     immer
    0.18
     deepest
    0.18
     totally
    0.17
    deep
    0.17
     neck
    0.17
     surrounded
    0.17
    Act Density 0.059%

    No Known Activations