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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     depress
    -0.69
     insert
    -0.69
    etheus
    -0.68
     sshd
    -0.66
     Bash
    -0.65
    ijn
    -0.65
     admire
    -0.64
    iegel
    -0.62
    zbek
    -0.62
    ogle
    -0.60
    POSITIVE LOGITS
    20439
    0.83
     toget
    0.81
    OOOOOOOO
    0.79
    âĹ¼
    0.78
    kees
    0.76
    UGH
    0.75
    wcs
    0.72
    auri
    0.71
    course
    0.69
    advertisement
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.