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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ista
    -0.72
    MAS
    -0.71
    Meg
    -0.69
    perture
    -0.69
    *.
    -0.67
     VICE
    -0.65
     OnePlus
    -0.65
    代
    -0.64
    dfx
    -0.64
     slider
    -0.64
    POSITIVE LOGITS
     targ
    0.74
     Ct
    0.69
    ruct
    0.66
    ebted
    0.66
    stand
    0.64
     Haf
    0.64
     Memor
    0.64
    pret
    0.63
     Chero
    0.63
     exting
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.