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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and events in the Twilight series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    595
    -0.15
    rale
    -0.15
    itra
    -0.15
    otron
    -0.15
    GIN
    -0.14
     flaming
    -0.14
     Attribution
    -0.14
     Koch
    -0.14
    eldorf
    -0.14
    anh
    -0.13
    POSITIVE LOGITS
     Twilight
    0.32
     Eclipse
    0.25
     Bella
    0.24
     vampire
    0.22
     Fork
    0.22
     vamp
    0.22
    .eclipse
    0.22
    okane
    0.22
    clipse
    0.21
     twilight
    0.21
    Act Density 0.012%

    No Known Activations