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

    Neuronpedia

    INDEX
    Explanations

    references to ghosts and supernatural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSION
    -0.16
    .CodeAnalysis
    -0.15
    onder
    -0.15
    ä¿
    -0.14
    arian
    -0.13
    /fixtures
    -0.13
    èĸ¦
    -0.13
    urses
    -0.13
    neau
    -0.13
    缼
    -0.13
    POSITIVE LOGITS
    ly
    0.35
    busters
    0.32
    buster
    0.26
    liness
    0.23
    liest
    0.21
    LY
    0.20
    ed
    0.20
    writers
    0.19
    writer
    0.19
    writing
    0.19
    Act Density 0.009%

    No Known Activations