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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eko
    -0.16
    roller
    -0.15
    ammable
    -0.15
    ahoma
    -0.14
    embros
    -0.14
    uebas
    -0.14
    sta
    -0.14
    otype
    -0.14
    antro
    -0.14
    imenti
    -0.14
    POSITIVE LOGITS
    fulness
    0.20
    ness
    0.18
    /alert
    0.16
    ırak
    0.15
    -aware
    0.15
    732
    0.15
    ä¹İ
    0.14
    akit
    0.14
     delt
    0.14
    684
    0.14
    Act Density 0.035%

    No Known Activations