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

    Neuronpedia

    INDEX
    Explanations

    words related to introspection and self-reflection

    oai_token-act-pair · gpt-3.5-turbo

    references to personal introspection and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manned
    -0.79
    MER
    -0.73
     Forbes
    -0.73
     Collider
    -0.72
     FY
    -0.72
     RIS
    -0.71
     EW
    -0.71
     Lands
    -0.69
     EUR
    -0.68
     ARM
    -0.66
    POSITIVE LOGITS
     emptiness
    0.98
     emotions
    0.92
     Meditation
    0.91
     habits
    0.91
    awareness
    0.90
     feelings
    0.90
     selves
    0.90
     meditation
    0.90
     Primordial
    0.89
     behaviours
    0.88
    Act Density 1.085%

    No Known Activations