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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters and their relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Buffered
    -0.16
    ague
    -0.15
     sperma
    -0.15
    ãĤ´ãĥª
    -0.15
     OVERRIDE
    -0.15
    ACE
    -0.14
    ãĥ§
    -0.14
    tdown
    -0.14
    åľ
    -0.14
    akah
    -0.14
    POSITIVE LOGITS
     Peter
    0.35
     Hook
    0.33
     Wendy
    0.32
    Peter
    0.30
     Never
    0.29
     Pan
    0.29
    Hook
    0.28
     Darling
    0.27
     hook
    0.27
     peter
    0.26
    Act Density 0.002%

    No Known Activations