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

    Neuronpedia

    INDEX
    Explanations

    films and media that feature horror or supernatural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MISC
    -0.15
    namen
    -0.14
    ollapsed
    -0.14
    trieve
    -0.13
    ROUP
    -0.13
    ¤¤
    -0.13
    ضا
    -0.13
    -_
    -0.13
    ÛĮدÛĮ
    -0.13
    à¥ĩ-
    -0.12
    POSITIVE LOGITS
    ‘s
    0.38
    /The
    0.27
    “,
    0.24
    which
    0.23
     Redux
    0.22
    -era
    0.22
    ¸
    0.22
    ‘
    0.21
     II
    0.21
     fame
    0.20
    Act Density 0.128%

    No Known Activations