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

    Neuronpedia

    INDEX
    Explanations

    elements related to character choices and transformations in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ape
    -0.16
    iform
    -0.15
    IRC
    -0.15
    ourcem
    -0.14
    ipers
    -0.14
    urban
    -0.14
     Circus
    -0.14
    |--
    -0.14
    orgia
    -0.14
    ung
    -0.14
    POSITIVE LOGITS
     Frozen
    0.33
     Elsa
    0.31
    Frozen
    0.28
     Anna
    0.21
     frozen
    0.21
     Disney
    0.20
     Rap
    0.20
    Anna
    0.20
    snow
    0.19
     겨
    0.19
    Act Density 0.007%

    No Known Activations