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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymce
    -0.52
     upvote
    -0.51
     ocorreu
    -0.50
     preventivo
    -0.49
     crucifix
    -0.47
    imeni
    -0.47
     originalmente
    -0.47
    präch
    -0.46
    érienne
    -0.46
     gefahren
    -0.45
    POSITIVE LOGITS
     new
    1.80
    new
    1.40
    新的
    1.37
     nueva
    1.36
     nieuwe
    1.33
    新
    1.31
     newly
    1.31
     nuevo
    1.30
     nouveaux
    1.28
     newest
    1.28
    Act Density 0.134%

    No Known Activations