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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chränk
    -0.69
     Teg
    -0.64
    setupUi
    -0.62
    最快更新
    -0.62
    margins
    -0.62
     dimethyl
    -0.62
    ạm
    -0.61
    脚注の使い方
    -0.60
    atriz
    -0.60
     foils
    -0.59
    POSITIVE LOGITS
     comprised
    1.44
     consists
    1.35
     comprises
    1.30
     terdiri
    1.27
     comprising
    1.24
     consist
    1.23
     consisted
    1.21
     consisting
    1.21
     composée
    1.20
     gồm
    1.16
    Act Density 0.181%

    No Known Activations