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

    Neuronpedia

    INDEX
    Explanations

    references to darkness or dark themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.85
    cotch
    -0.84
     Roskov
    -0.83
     NSCoder
    -0.82
     MainAxisSize
    -0.81
    ANEOUS
    -0.76
    osoever
    -0.73
    yntaxException
    -0.73
    NameInMap
    -0.71
    __*/
    -0.70
    POSITIVE LOGITS
     dark
    1.25
     Dark
    1.14
    DARK
    1.10
     DARK
    1.10
    Dark
    1.08
    dark
    1.06
     oscuro
    0.93
     darkness
    0.81
     gelap
    0.79
     dunklen
    0.78
    Act Density 0.056%

    No Known Activations