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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     azok
    -0.56
     genoux
    -0.54
    bayern
    -0.52
    ınt
    -0.50
     bit
    -0.50
     vált
    -0.49
     malah
    -0.48
    ukunfts
    -0.47
     Yung
    -0.47
     sık
    -0.47
    POSITIVE LOGITS
     auquel
    1.10
     springfox
    1.00
    __":
    0.96
    ]")]
    0.96
    原始内容存档于
    0.96
     duquel
    0.94
     Whom
    0.94
    + 
    0.94
     WHICH
    0.90
     auxquelles
    0.90
    Act Density 0.137%

    No Known Activations