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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherford
    -0.17
    erah
    -0.16
    ounce
    -0.15
    emek
    -0.15
     Transitional
    -0.15
     Mayer
    -0.14
    į¼
    -0.14
    inery
    -0.14
    ritz
    -0.14
     sympathy
    -0.14
    POSITIVE LOGITS
     overall
    0.17
     experiences
    0.17
     Zi
    0.16
     experience
    0.15
    overall
    0.15
     repeat
    0.15
    -net
    0.15
    92
    0.15
    repeat
    0.15
    ÑĮÑı
    0.15
    Act Density 0.303%

    No Known Activations