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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and reflections of oneself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adiens
    -0.16
    ignum
    -0.15
    engin
    -0.15
    UIL
    -0.15
    wire
    -0.14
    override
    -0.14
    zcze
    -0.14
    gran
    -0.14
     prev
    -0.13
     æ©Ł
    -0.13
    POSITIVE LOGITS
    nger
    0.17
    jis
    0.17
    ı
    0.16
    rored
    0.15
    anine
    0.15
    ande
    0.15
    inati
    0.14
    inde
    0.14
    reflection
    0.14
    rası
    0.13
    Act Density 0.017%

    No Known Activations