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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and titles from the "Nancy Drew" series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.15
     lean
    -0.15
    lass
    -0.15
     Lean
    -0.14
    ift
    -0.14
     Leonard
    -0.14
    ister
    -0.14
    hani
    -0.14
    icken
    -0.13
    acias
    -0.13
    POSITIVE LOGITS
     himself
    0.16
    olynomial
    0.16
    iana
    0.15
    illard
    0.15
    rina
    0.15
     Damon
    0.15
    adol
    0.14
    CHED
    0.14
    ogo
    0.14
    ConnectionFactory
    0.14
    Act Density 0.113%

    No Known Activations