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

    Neuronpedia

    INDEX
    Explanations

    the concept of self-reference in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogn
    -0.16
    asil
    -0.15
    agy
    -0.15
     stub
    -0.15
    uty
    -0.14
    ware
    -0.14
    ardin
    -0.14
    .sponge
    -0.14
    ilded
    -0.13
    ayo
    -0.13
    POSITIVE LOGITS
     itself
    0.18
    semblies
    0.16
    chaft
    0.15
    ï¸ı
    0.15
    -même
    0.14
    tones
    0.14
    endoza
    0.14
    ighton
    0.14
    ptal
    0.14
    ään
    0.14
    Act Density 0.043%

    No Known Activations