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

    Neuronpedia

    INDEX
    Explanations

    instances of self-affirmation and demonstrating competence or worthiness

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and references to individual identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retrieval
    -0.66
    uld
    -0.64
    UM
    -0.60
     Medline
    -0.60
    arton
    -0.59
    panel
    -0.59
    rouse
    -0.58
     winds
    -0.58
     Torrent
    -0.58
    mentioned
    -0.58
    POSITIVE LOGITS
     exist
    0.83
     AUTH
    0.75
     superiority
    0.74
     trustworthy
    0.73
     authentic
    0.72
    ãģĻ
    0.70
     worthy
    0.70
     exists
    0.69
    chwitz
    0.69
     cares
    0.69
    Act Density 0.384%

    No Known Activations