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

    Neuronpedia

    INDEX
    Explanations

    references to Roman culture, history, and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drawer
    -0.17
    alet
    -0.17
    gin
    -0.17
    μÏĢο
    -0.16
    atonin
    -0.15
     Drawer
    -0.15
    uitka
    -0.15
    redient
    -0.14
    leton
    -0.14
    istring
    -0.14
    POSITIVE LOGITS
     Catholic
    0.30
     numer
    0.24
     Catholics
    0.24
     Empire
    0.23
    ov
    0.23
     numeral
    0.23
    ized
    0.23
    ians
    0.22
     catholic
    0.22
    esco
    0.21
    Act Density 0.016%

    No Known Activations