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

    Neuronpedia

    INDEX
    Explanations

    movie-related phrases emphasizing horror and thrill

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

    thriller films and horror movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     historiador
    -0.37
     egne
    -0.35
     peores
    -0.34
     completas
    -0.32
     gobern
    -0.31
    protoimpl
    -0.31
     ieg
    -0.30
     própria
    -0.30
     mépris
    -0.30
     república
    -0.30
    POSITIVE LOGITS
    ロウィン
    0.67
    transQ
    0.67
     EconPapers
    0.64
    béco
    0.63
     noDo
    0.61
     HasFactory
    0.61
    onAttach
    0.60
    majánló
    0.60
    ########.
    0.59
    writeFieldEnd
    0.58
    Act Density 0.037%

    No Known Activations