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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "meta" or discussions related to metacognition and self-referential themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ιαν
    -0.16
    shal
    -0.16
    tech
    -0.16
    ÑĢÑĥб
    -0.16
    eltas
    -0.15
    ADS
    -0.15
    ederland
    -0.15
    psy
    -0.15
     mills
    -0.15
    atoria
    -0.15
    POSITIVE LOGITS
    /met
    0.23
    (meta
    0.23
     Met
    0.23
     meta
    0.21
     met
    0.21
    /meta
    0.21
    .Meta
    0.20
     Meta
    0.20
    ropolis
    0.20
    ropolitan
    0.18
    Act Density 0.013%

    No Known Activations