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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant personal experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.00
     purpoſe
    -0.94
     ſmall
    -0.88
     leaſt
    -0.87
     pleaſure
    -0.84
     greateſt
    -0.84
     ſeveral
    -0.83
     Monfieur
    -0.83
     Diſ
    -0.82
     Conſ
    -0.81
    POSITIVE LOGITS
     experience
    1.02
     Process
    0.94
    Process
    0.88
     EXPERIENCE
    0.88
     process
    0.84
     Experience
    0.83
    experience
    0.82
     processo
    0.77
    Experience
    0.77
    Проце
    0.75
    Act Density 0.166%

    No Known Activations