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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating comparisons and superlatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poco
    -0.56
     peu
    -0.53
     nice
    -0.53
    OGND
    -0.51
    loh
    -0.50
     pouco
    -0.50
    kunt
    -0.49
    bilang
    -0.48
    Erfolge
    -0.48
     دیکھیے
    -0.48
    POSITIVE LOGITS
    iest
    1.35
     happiest
    1.31
     safest
    1.28
     healthiest
    1.26
     freshest
    1.22
     lightest
    1.21
     heaviest
    1.20
    ariest
    1.20
    ziest
    1.17
     greatest
    1.17
    Act Density 0.445%

    No Known Activations