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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    margin
    -0.69
    )?
    -0.67
     GMT
    -0.67
     Unch
    -0.64
    Posts
    -0.60
     Merchants
    -0.58
    ))))
    -0.58
     Ans
    -0.58
    -)
    -0.57
    beit
    -0.56
    POSITIVE LOGITS
     apprehension
    0.79
    selves
    0.79
    lain
    0.73
     solicitor
    0.72
    aukee
    0.71
     fian
    0.69
    odynam
    0.65
    igmatic
    0.65
    MpServer
    0.65
    illance
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.