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

    Neuronpedia

    INDEX
    Explanations

    references to population statistics and counts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SPATH
    -0.87
    mentaux
    -0.81
    monary
    -0.78
    UVWXYZ
    -0.78
    cedentes
    -0.74
    ядок
    -0.74
     umana
    -0.74
    audiovisuel
    -0.74
    daq
    -0.71
     Spade
    -0.69
    POSITIVE LOGITS
     Архів
    0.75
     million
    0.74
     Marston
    0.70
    zeit
    0.66
     Million
    0.66
    stylers
    0.65
    Eins
    0.65
    Diz
    0.65
     triệu
    0.64
     billion
    0.63
    Act Density 0.016%

    No Known Activations