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

    Neuronpedia

    INDEX
    Explanations

    mentions of mirrors and reflective surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê´Ģ리ìŀIJ
    -0.16
    zion
    -0.15
    оÑĢм
    -0.15
    zione
    -0.15
    ãĥ³ãĤº
    -0.15
    een
    -0.15
    oled
    -0.15
    ãģķãĤī
    -0.15
    .matches
    -0.14
    ei
    -0.14
    POSITIVE LOGITS
    nger
    0.18
    atég
    0.14
    ı
    0.14
     Thief
    0.14
    rega
    0.14
    iming
    0.14
    SCAN
    0.14
     superst
    0.13
    ÑĤÑİ
    0.13
     Basics
    0.13
    Act Density 0.003%

    No Known Activations