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

    Neuronpedia

    INDEX
    Explanations

    references to darkness or dark imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osoever
    -0.81
    mfrac
    -0.67
    եց
    -0.62
    katapos
    -0.62
    verley
    -0.61
    tyfik
    -0.60
    vra
    -0.58
    RenderAtEndOf
    -0.58
    PROPS
    -0.58
    gogo
    -0.58
    POSITIVE LOGITS
     darkness
    1.51
     DARK
    1.50
    Darkness
    1.46
     Dark
    1.45
    darkness
    1.44
     dark
    1.43
    DARK
    1.41
     Darkness
    1.38
    Dark
    1.36
    dark
    1.31
    Act Density 0.181%

    No Known Activations