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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    them
    -0.18
     whats
    -0.14
     rằng
    -0.14
    iteDatabase
    -0.14
    اÙĨÙĩ
    -0.13
    anko
    -0.13
    민
    -0.13
     them
    -0.13
    .routing
    -0.13
     ведÑĮ
    -0.13
    POSITIVE LOGITS
    soever
    0.44
     we
    0.34
     they
    0.31
    upon
    0.29
     she
    0.22
     you
    0.22
     he
    0.21
     there
    0.21
    /if
    0.20
    -ever
    0.20
    Act Density 0.044%

    No Known Activations