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

    Neuronpedia

    INDEX
    Explanations

    references to shadows and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thrones
    -0.73
    kesmas
    -0.70
     समीक्षाओं
    -0.68
    ỡng
    -0.68
    ьаж
    -0.68
    czaj
    -0.67
     Bikini
    -0.67
     '\\;'
    -0.67
    glades
    -0.65
     Halal
    -0.65
    POSITIVE LOGITS
    ito
    0.90
     Keith
    0.89
     shadow
    0.89
     Shadow
    0.85
    Keith
    0.78
    Shadow
    0.76
    shadow
    0.73
    ita
    0.71
    ITA
    0.67
     Dust
    0.66
    Act Density 0.057%

    No Known Activations