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

    Neuronpedia

    INDEX
    Explanations

    references to prestigious educational institutions and their connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wheatley
    -0.91
     Hayward
    -0.75
     Coates
    -0.75
    libri
    -0.71
    vell
    -0.71
     Dent
    -0.70
    stuhl
    -0.69
     GNA
    -0.68
     Galla
    -0.67
     Rheinland
    -0.66
    POSITIVE LOGITS
     Normdatei
    0.83
     Danilo
    0.74
    Connecticut
    0.74
     Knicks
    0.72
     Connecticut
    0.70
    Lama
    0.69
     Hano
    0.68
     дописавши
    0.67
     Childs
    0.67
    dtos
    0.67
    Act Density 1.687%

    No Known Activations