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

    Neuronpedia

    INDEX
    Explanations

    names and titles associated with historical contexts and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lilith
    -0.67
     rø
    -0.67
    pij
    -0.66
     Nog
    -0.61
     Herrera
    -0.61
     Lovel
    -0.61
     Obl
    -0.60
     Gij
    -0.59
     svå
    -0.59
     Mathieu
    -0.58
    POSITIVE LOGITS
    Datuak
    0.94
    CppCodeGen
    0.94
    Chham
    0.93
     Bex
    0.92
     Florentine
    0.87
    HIND
    0.82
     Activision
    0.82
    ctg
    0.82
     McAllister
    0.81
    -------------</
    0.81
    Act Density 7.841%

    No Known Activations