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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     /
    1.17
    เอก
    1.16
     zaten
    1.09
                                   
    1.06
     Affirm
    1.05
      
    1.04
     )
    1.04
     биографи
    1.03
       
    1.01
     At
    1.01
    POSITIVE LOGITS
    ナス
    1.31
    allowSlide
    1.23
    <unused1669>
    1.22
    <unused345>
    1.22
    <unused270>
    1.21
    лке
    1.20
     slopes
    1.19
     lathes
    1.17
    🖔
    1.16
    <unused1745>
    1.16
    Act Density 0.005%

    No Known Activations