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

    Neuronpedia

    INDEX
    Explanations

    themes of secrets and hidden truths within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apsed
    -0.17
    cestor
    -0.16
    Äı
    -0.15
    ansen
    -0.14
    /embed
    -0.14
    erness
    -0.14
     колÑĮ
    -0.14
    ritel
    -0.14
    åĽ´
    -0.14
    ÑĤÑĢи
    -0.13
    POSITIVE LOGITS
     underlying
    0.18
     revealed
    0.15
    lied
    0.14
     Shuttle
    0.14
    omi
    0.14
    ores
    0.14
     secrets
    0.14
     Bryan
    0.14
     décou
    0.14
    omba
    0.14
    Act Density 0.082%

    No Known Activations