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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their relationships in adaptations of popular stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãły
    -0.17
     sneak
    -0.15
     Columbus
    -0.14
     leadership
    -0.14
     Sne
    -0.14
     levy
    -0.14
    nad
    -0.13
     counselors
    -0.13
     Spar
    -0.13
     repeat
    -0.13
    POSITIVE LOGITS
     Sherlock
    0.26
     Holmes
    0.24
    croft
    0.20
     Conan
    0.17
    Crime
    0.17
     Crime
    0.17
    ìħľ
    0.17
     Watson
    0.16
     Poe
    0.15
     Mori
    0.15
    Act Density 0.054%

    No Known Activations