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

    Neuronpedia

    INDEX
    Explanations

    repeated use of definite and indefinite articles in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Baillargeon
    -0.83
    Vidite
    -0.74
     dépens
    -0.73
     vœux
    -0.72
     ModelExpression
    -0.70
     kaarangay
    -0.69
     AspNetCore
    -0.69
     rempliss
    -0.68
     feroit
    -0.67
     propOrder
    -0.67
    POSITIVE LOGITS
    Примечания
    0.65
     social
    0.63
    ιού
    0.58
    ignant
    0.55
    ########.
    0.55
    ologi
    0.54
    YLE
    0.52
    chino
    0.52
     real
    0.52
     combat
    0.52
    Act Density 0.270%

    No Known Activations