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

    Neuronpedia

    INDEX
    Explanations

    references to darkness or dark themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.79
    NameInMap
    -0.72
    RenderAtEndOf
    -0.71
     endwhile
    -0.71
     noDo
    -0.70
    SequentialGroup
    -0.69
     Stedman
    -0.68
     tartalomajánló
    -0.64
    ictwo
    -0.64
    LookAnd
    -0.63
    POSITIVE LOGITS
     dark
    1.02
     Dark
    1.01
     DARK
    0.93
    DARK
    0.91
    dark
    0.91
    Dark
    0.91
     oscuro
    0.85
     oscura
    0.69
    Darkness
    0.68
     darkest
    0.68
    Act Density 0.098%

    No Known Activations