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

    Neuronpedia

    INDEX
    Explanations

    references to darkness and related themes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osoever
    -0.94
     propOrder
    -0.90
    tyfik
    -0.88
    __":
    -0.85
     protoimpl
    -0.82
    RenderAtEndOf
    -0.82
    isseurs
    -0.79
    oneofs
    -0.79
     AssemblyTitle
    -0.78
    ngdoc
    -0.78
    POSITIVE LOGITS
     dark
    2.32
     Dark
    2.28
     DARK
    2.18
    Dark
    2.16
    dark
    2.08
    DARK
    2.00
     darkness
    1.61
     darker
    1.60
    Darkness
    1.49
     darkest
    1.48
    Act Density 0.034%

    No Known Activations