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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Morgan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    czy
    -0.17
    ersed
    -0.16
    repid
    -0.15
    cj
    -0.15
    indre
    -0.15
    itters
    -0.15
     Cascade
    -0.15
    ikt
    -0.14
     Îļο
    -0.14
    ynes
    -0.14
    POSITIVE LOGITS
     Stanley
    0.28
    Stan
    0.21
     stan
    0.19
    atic
    0.19
    za
    0.18
    stan
    0.18
    wand
    0.18
     Sind
    0.17
    elli
    0.17
    wg
    0.17
    Act Density 0.006%

    No Known Activations