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
    them
    -0.18
     whats
    -0.15
    اÙĨÙĩ
    -0.14
     whereas
    -0.14
    NECT
    -0.14
    agu
    -0.14
     THEM
    -0.13
    iteDatabase
    -0.13
    ERCHANT
    -0.13
     him
    -0.13
    POSITIVE LOGITS
    soever
    0.47
     we
    0.34
     they
    0.31
    upon
    0.29
    /how
    0.23
    /if
    0.22
    -ever
    0.22
     she
    0.22
     you
    0.21
     he
    0.20
    Act Density 0.047%

    No Known Activations