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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hints
    0.45
     IST
    0.42
     hints
    0.41
     nm
    0.41
     COX
    0.41
     tense
    0.40
     Mich
    0.40
     pairwise
    0.39
     NST
    0.38
     attest
    0.38
    POSITIVE LOGITS
    граф
    0.43
    Ros
    0.40
    삭
    0.39
    Unifier
    0.38
    Gravestone
    0.37
    Raquete
    0.37
     pausing
    0.37
     바람
    0.36
     moveable
    0.36
    move
    0.35
    Act Density 0.000%

    No Known Activations