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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Domestic
    -0.16
     Seal
    -0.15
    ernes
    -0.14
    .Registry
    -0.14
    erm
    -0.14
    rol
    -0.14
    urst
    -0.14
    omon
    -0.14
    äº
    -0.14
     ضÙħÙĨ
    -0.14
    POSITIVE LOGITS
     longer
    0.28
     Longer
    0.24
     longest
    0.19
     overnight
    0.18
    -extra
    0.17
    -over
    0.15
    enan
    0.15
    allee
    0.15
     behind
    0.15
     lâu
    0.15
    Act Density 0.041%

    No Known Activations