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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of originality or original works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #+#
    -0.95
     Réponses
    -0.89
     decoradas
    -0.79
     дописавши
    -0.78
     <=",
    -0.75
    MeasureSpec
    -0.73
    chaun
    -0.71
     berbicara
    -0.70
     voeten
    -0.69
     Foxx
    -0.69
    POSITIVE LOGITS
     original
    1.97
    Original
    1.90
     ORIGINAL
    1.89
     Original
    1.83
    original
    1.76
    ORIGINAL
    1.69
     originals
    1.65
     orig
    1.62
     originale
    1.42
     Originals
    1.40
    Act Density 0.077%

    No Known Activations