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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.77
    cy
    -0.75
    ded
    -0.71
     Baton
    -0.69
     Hov
    -0.69
    o
    -0.68
     Folsom
    -0.68
    ことはない
    -0.67
    СТЬ
    -0.66
     Rowan
    -0.66
    POSITIVE LOGITS
     WHICH
    1.34
    Datuak
    1.30
     Which
    1.21
    which
    1.14
     which
    1.13
    Which
    1.13
    ]**
    1.06
     wich
    1.03
    TypedDataSet
    0.99
    ArgsConstructor
    0.98
    Act Density 0.162%

    No Known Activations