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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     discursive
    1.72
     coarsely
    1.70
     agnostic
    1.68
    Ⅴ
    1.60
     unaffected
    1.60
     disrupted
    1.59
     esteem
    1.59
     kerosene
    1.59
     shave
    1.58
     helm
    1.56
    POSITIVE LOGITS
    দীপ
    1.83
    contents
    1.71
    cedented
    1.70
    ist
    1.68
    𝚜
    1.63
    قبل
    1.63
    𝚋
    1.60
     כן
    1.60
    στο
    1.60
    ал
    1.57
    Act Density 0.000%

    No Known Activations