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

    Neuronpedia

    INDEX
    Explanations

    references to classic literature or storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    typeid
    -0.16
    assi
    -0.15
    onaut
    -0.14
     fascist
    -0.14
    boss
    -0.14
    lias
    -0.14
    ois
    -0.14
    ARC
    -0.14
    .nt
    -0.14
     Reich
    -0.14
    POSITIVE LOGITS
     Poe
    0.34
     Edgar
    0.25
     Raven
    0.21
     ebony
    0.19
     Dup
    0.18
     Len
    0.16
     narr
    0.16
     narrator
    0.15
     Duy
    0.15
     Vaults
    0.15
    Act Density 0.010%

    No Known Activations