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

    Neuronpedia

    INDEX
    Explanations

    words that are related to a specific book, possibly related to hidden secrets or details within the book

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ss" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.72
    TPP
    -0.68
    paralle
    -0.66
    ts
    -0.62
     Petraeus
    -0.62
    wealth
    -0.61
    few
    -0.61
    tained
    -0.61
     Kut
    -0.60
    scene
    -0.60
    POSITIVE LOGITS
    ault
    1.11
    alid
    1.04
    ession
    1.03
    ystem
    1.02
    creen
    0.98
    ometimes
    0.97
    essions
    0.95
    andra
    0.95
    alon
    0.94
    arah
    0.94
    Act Density 0.016%

    No Known Activations