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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Dark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illy
    -0.17
    ãĤ·ãĥ¼
    -0.15
    _DC
    -0.15
    abr
    -0.15
    avirus
    -0.14
    /templates
    -0.14
    SetColor
    -0.14
    DataRow
    -0.14
    ÎŃν
    -0.14
    pio
    -0.14
    POSITIVE LOGITS
    ness
    0.24
    er
    0.23
     matter
    0.21
     Matter
    0.20
     GDK
    0.19
     Side
    0.19
     side
    0.18
    matter
    0.18
     Horse
    0.18
     tower
    0.18
    Act Density 0.008%

    No Known Activations