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

    Neuronpedia

    INDEX
    Explanations

    indicators of data structuring or references to datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.71
    tagHelperRunner
    -0.70
    didSet
    -0.64
    WriteTagHelper
    -0.63
    copg
    -0.61
    KommentareTeilen
    -0.59
     дописавши
    -0.58
     Мексичка
    -0.58
    достатки
    -0.57
     tartalomajánló
    -0.56
    POSITIVE LOGITS
     speciali
    0.53
    Following
    0.49
     AllAfrica
    0.49
    setzer
    0.48
     seguito
    0.48
     található
    0.46
    <eos>
    0.46
     Détails
    0.46
    Prior
    0.46
     aggiun
    0.46
    Act Density 0.154%

    No Known Activations