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

    Neuronpedia

    INDEX
    Explanations

    theatrical elements and character-driven narratives in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶Į
    -0.18
    tower
    -0.16
     bì
    -0.15
    аÑĢÑĩ
    -0.15
    rå
    -0.14
    ãĥ§
    -0.14
    orpion
    -0.14
     tower
    -0.14
    rames
    -0.14
    nex
    -0.14
    POSITIVE LOGITS
     Hook
    0.29
     Peter
    0.27
     Wendy
    0.27
     Pan
    0.26
     hook
    0.25
    Hook
    0.25
     Darling
    0.24
    HOOK
    0.23
    Peter
    0.23
    hook
    0.23
    Act Density 0.005%

    No Known Activations