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

    Neuronpedia

    INDEX
    Explanations

    named entities and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morrison
    -0.17
    é¾
    -0.17
    e
    -0.16
     plain
    -0.15
    ning
    -0.15
    ornings
    -0.15
    wan
    -0.14
     Loose
    -0.13
    ç³»
    -0.13
     contrast
    -0.13
    POSITIVE LOGITS
    Ú¯ÛĮر
    0.17
    ÑĢÑĥн
    0.16
    hoff
    0.15
    ä¸įäºĨ
    0.15
    ripsi
    0.15
     INDIRECT
    0.15
    ersh
    0.14
    ARRIER
    0.14
    é¥
    0.14
    bih
    0.13
    Act Density 0.087%

    No Known Activations