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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     renegoti
    1.05
     Precis
    1.02
     ello
    1.02
    tive
    1.02
    ulates
    1.01
    ximately
    1.00
     centerpiece
    0.99
     Right
    0.99
     Negoti
    0.98
    orestation
    0.98
    POSITIVE LOGITS
    𝐌
    1.51
    𝐑
    1.47
    িল্লা
    1.41
    াৰ
    1.39
    𝐋
    1.36
     decidió
    1.32
     preguntó
    1.30
    𝐍
    1.30
     saludables
    1.29
    𝐏
    1.28
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.