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

    Neuronpedia

    INDEX
    Explanations

    words related to ego and self-perception

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ego."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.71
    Recomm
    -0.68
    Topic
    -0.66
    thouse
    -0.64
    ells
    -0.64
     footsteps
    -0.62
    AKING
    -0.61
    È
    -0.60
    poon
    -0.60
    dayName
    -0.60
    POSITIVE LOGITS
    istical
    1.10
     ego
    0.90
    eson
    0.79
    oenix
    0.76
     infl
    0.75
    terior
    0.75
    regate
    0.75
     quot
    0.73
    aminer
    0.73
     gratification
    0.72
    Act Density 0.054%

    No Known Activations