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

    Neuronpedia

    INDEX
    Explanations

    the word "dark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     müſſen
    -0.73
     laſſen
    -0.68
     eventId
    -0.66
     productId
    -0.65
     ſind
    -0.64
     sessionId
    -0.64
    evos
    -0.64
     companyId
    -0.63
     Witherspoon
    -0.63
    BibitemShut
    -0.62
    POSITIVE LOGITS
     dark
    1.93
     Dark
    1.78
    Dark
    1.74
     DARK
    1.74
    dark
    1.71
    DARK
    1.45
     darker
    1.25
     darkest
    1.24
     oscuro
    1.23
     dunklen
    1.16
    Act Density 0.006%

    No Known Activations