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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "illusion" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheet
    -0.15
    ñana
    -0.15
    emat
    -0.14
    Xd
    -0.14
    yectos
    -0.14
    isz
    -0.14
     Baths
    -0.14
    hatt
    -0.14
    elor
    -0.13
    ắp
    -0.13
    POSITIVE LOGITS
    rious
    0.17
    /mock
    0.16
    sworth
    0.15
    aye
    0.14
    etti
    0.14
    Chance
    0.14
    ota
    0.14
    nal
    0.14
    922
    0.14
    etten
    0.14
    Act Density 0.009%

    No Known Activations