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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or trademarks

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "original" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wal
    -0.84
    rosso
    -0.72
    ega
    -0.71
    Adv
    -0.70
    gerald
    -0.70
    rom
    -0.68
    rology
    -0.68
    roph
    -0.68
    riz
    -0.67
    rop
    -0.67
    POSITIVE LOGITS
    ity
    1.33
    ITY
    0.94
     impetus
    0.90
     trilogy
    0.87
     sin
    0.82
     intent
    0.81
     conception
    0.80
    iator
    0.79
     intention
    0.79
     incarnation
    0.78
    Act Density 0.034%

    No Known Activations