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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐉
    -0.08
    AG
    -0.07
    є
    -0.07
     Investigations
    -0.07
    黑
    -0.07
    velopment
    -0.07
     Baron
    -0.06
    AM
    -0.06
    ब
    -0.06
     barracks
    -0.06
    POSITIVE LOGITS
     Firm
    0.07
    `='$
    0.07
     pr
    0.07
    ➿
    0.07
     Apt
    0.07
    xCB
    0.07
    قوي
    0.07
    띠
    0.07
     Primitive
    0.06
    短板
    0.06
    Act Density 0.001%

    No Known Activations