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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific titles or descriptors related to movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Fantasy genre and related terms

    np_acts-logits-general · gemini-2.0-flash

    The Hobbit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     victim
    -0.51
    TemporalType
    -0.51
     channels
    -0.45
     Spre
    -0.45
     granules
    -0.43
     bParam
    -0.43
     suficientes
    -0.43
     ideale
    -0.43
    脚注の使い方
    -0.42
    useState
    -0.42
    POSITIVE LOGITS
     Tolkien
    1.05
     Hobbit
    0.99
     hobbit
    0.99
    olkien
    0.87
     Gandalf
    0.81
     Shire
    0.74
     Rings
    0.74
    andalf
    0.72
    Rings
    0.69
     Elves
    0.68
    Act Density 0.100%

    No Known Activations