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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.64
    ckså
    -0.59
     ſhall
    -0.58
     nakalista
    -0.58
     Epistle
    -0.58
    -0.55
    Slf
    -0.54
    arithmic
    -0.54
    sweise
    -0.54
     stället
    -0.54
    POSITIVE LOGITS
    <bos>
    0.98
     meleg
    0.51
    Hawai
    0.49
     Hutchins
    0.46
    ínű
    0.45
    Borde
    0.44
     Stande
    0.44
    t
    0.43
     Vanden
    0.42
     hurt
    0.42
    Act Density 0.174%

    No Known Activations