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

    Neuronpedia

    INDEX
    Explanations

    references to darkness, dark imagery, and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osoever
    -0.84
    tyfik
    -0.79
    katapos
    -0.66
     gynhyrchwyd
    -0.66
    եց
    -0.65
    كذا
    -0.65
    ↩
    -0.63
    RenderAtEndOf
    -0.63
    gogo
    -0.62
    ≦)
    -0.61
    POSITIVE LOGITS
     DARK
    1.75
     dark
    1.74
     Dark
    1.70
     darkness
    1.63
    Dark
    1.60
    DARK
    1.58
    dark
    1.57
    Darkness
    1.56
    darkness
    1.53
     darker
    1.49
    Act Density 0.132%

    No Known Activations