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

    Neuronpedia

    INDEX
    Explanations

    expressions related to introspection and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .authenticate
    -0.15
    oya
    -0.15
    itre
    -0.14
    oku
    -0.14
    itr
    -0.13
    shint
    -0.13
    à¥įयव
    -0.13
    iedades
    -0.13
    osterone
    -0.13
     Introduced
    -0.13
    POSITIVE LOGITS
     imagination
    0.48
     imag
    0.46
     imagin
    0.39
     fantas
    0.38
     fantasy
    0.38
     fantasies
    0.35
    dream
    0.35
    imag
    0.35
     imagining
    0.35
    imagin
    0.35
    Act Density 0.246%

    No Known Activations