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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cemment
    -0.64
    ichier
    -0.60
     Cæsar
    -0.59
     vieler
    -0.57
     feveral
    -0.57
    ſelves
    -0.56
     ſeveral
    -0.56
     propOrder
    -0.55
    άζ
    -0.55
     ocurrir
    -0.55
    POSITIVE LOGITS
    Cuánto
    0.80
     What
    0.77
    Combien
    0.76
     what
    0.73
     Combien
    0.68
    What
    0.67
     cuánto
    0.67
     amount
    0.64
    Сколько
    0.63
     Сколько
    0.62
    Act Density 0.136%

    No Known Activations