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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Franç
    -0.71
     Jagu
    -0.68
     rehearsal
    -0.66
     scrut
    -0.66
    ifa
    -0.61
    ãĥ¥
    -0.61
     Caf
    -0.60
    Twitter
    -0.59
     Emer
    -0.59
     Mahar
    -0.58
    POSITIVE LOGITS
     them
    1.13
     THEM
    0.92
     thereof
    0.89
    ĪĴ
    0.84
     Them
    0.70
     pear
    0.69
    ternally
    0.68
    vel
    0.67
    ypes
    0.65
    )",
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.