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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and logical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.75
     that
    -0.63
     propOrder
    -0.59
     chứ
    -0.54
     nahilalakip
    -0.52
    Respectfully
    -0.50
    annica
    -0.50
    ของคุณ
    -0.49
     but
    -0.49
     المعيارى
    -0.49
    POSITIVE LOGITS
     terdapat
    0.65
     мы
    0.65
     ia
    0.65
     они
    0.61
     можно
    0.61
     этот
    0.61
     существует
    0.61
    situation
    0.60
     οι
    0.60
     tämä
    0.59
    Act Density 0.026%

    No Known Activations