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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     сфере
    1.18
     Wellbeing
    1.07
    ționale
    1.01
    owneri
    1.01
     Hoodie
    1.00
     Māori
    1.00
    𝐩
    1.00
    țională
    0.99
    𝐟
    0.98
    ješ
    0.97
    POSITIVE LOGITS
    ↵
    0.88
    ratic
    0.74
    y
    0.74
     believes
    0.73
    log
    0.73
    百度
    0.72
     fascinating
    0.72
     unfortunate
    0.72
    Valentine
    0.71
    Задача
    0.70
    Act Density 0.000%

    No Known Activations