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

    Neuronpedia

    INDEX
    Explanations

    citations and references in scientific literature

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.89
    RenderAtEndOf
    -0.77
     فريبيس
    -0.73
     Jefus
    -0.72
     Theſe
    -0.66
     Monfieur
    -0.65
    ſelves
    -0.65
     Cæsar
    -0.65
     Beſ
    -0.61
     '\\;'
    -0.60
    POSITIVE LOGITS
     ambos
    0.67
     keduanya
    0.65
     Both
    0.61
    both
    0.61
     two
    0.60
     both
    0.59
     duo
    0.59
     pair
    0.59
    Both
    0.58
     दोनों
    0.56
    Act Density 0.027%

    No Known Activations