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

    Neuronpedia

    INDEX
    Explanations

    references to horror themes and elements in literature or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.70
     campeones
    -0.55
    casecmp
    -0.50
    WithIOException
    -0.50
    bigoplus
    -0.49
    IsMutable
    -0.49
    ']")
    -0.48
     matahari
    -0.47
     fiecare
    -0.45
     StringTokenizer
    -0.45
    POSITIVE LOGITS
     horror
    1.05
     Horror
    1.05
    Horror
    1.04
    horror
    0.96
     haunted
    0.91
     creepy
    0.88
     Haunted
    0.86
     spooky
    0.85
     scary
    0.83
    Haunted
    0.82
    Act Density 0.329%

    No Known Activations