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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     perceptions
    1.37
     estimators
    1.35
     prevalence
    1.32
     prepayment
    1.30
     dissonance
    1.27
     rapidamente
    1.27
    いる
    1.26
     κάτι
    1.24
     群
    1.19
     inroads
    1.19
    POSITIVE LOGITS
    ع
    1.24
    Evil
    1.21
    pick
    1.14
    um
    1.08
    er
    1.07
    unoscut
    1.07
    dit
    1.06
    umiem
    1.03
    ので
    1.03
    Updating
    1.02
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.