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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "way" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whats
    -0.16
    ickerView
    -0.16
    ÙĩÙĨ
    -0.16
    ëŀĢ
    -0.14
     Yourself
    -0.14
    Ñģен
    -0.14
    uld
    -0.14
    asal
    -0.14
    urs
    -0.14
    saldo
    -0.14
    POSITIVE LOGITS
     they
    0.23
    ward
    0.23
     that
    0.23
     we
    0.23
    (s
    0.22
     mÃł
    0.22
     things
    0.20
     wherein
    0.19
     ÏĢοÏħ
    0.18
    /how
    0.17
    Act Density 0.044%

    No Known Activations