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

    Neuronpedia

    INDEX
    Explanations

    references to specific book titles and series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kanye
    -0.14
    lore
    -0.14
    PATCH
    -0.14
    aved
    -0.13
     yüz
    -0.13
    ä¿®
    -0.13
    ().'/
    -0.13
     Define
    -0.13
     Wars
    -0.13
    loh
    -0.13
    POSITIVE LOGITS
     crime
    0.39
     mystery
    0.35
     mysteries
    0.35
     Crime
    0.33
     detective
    0.33
    Crime
    0.32
     Mystery
    0.30
    crime
    0.30
     detectives
    0.30
     murder
    0.29
    Act Density 0.148%

    No Known Activations