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

    Neuronpedia

    INDEX
    Explanations

    names of characters and entities in a narrative or scripted context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mahomet
    -0.88
     Aceh
    -0.78
     disambiguazione
    -0.77
     Platon
    -0.76
     Pallas
    -0.76
     Javan
    -0.75
     Haifa
    -0.72
     AssemblyCulture
    -0.72
     Medea
    -0.72
     Theron
    -0.72
    POSITIVE LOGITS
     McC
    0.86
     Mc
    0.84
    Mc
    0.74
     Tar
    0.74
     Ke
    0.73
     Ry
    0.73
     Ar
    0.70
     McQu
    0.69
     Mik
    0.68
     McCl
    0.67
    Act Density 1.286%

    No Known Activations