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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    GH
    -0.79
    abo
    -0.78
    wo
    -0.75
    hemy
    -0.69
    Exception
    -0.69
    oom
    -0.68
    ski
    -0.68
    ushes
    -0.68
    umm
    -0.67
     Oo
    -0.66
    POSITIVE LOGITS
     psychiat
    0.82
    xual
    0.75
     Leafs
    0.73
     consortium
    0.71
     tremend
    0.69
     division
    0.62
     FORM
    0.61
     CTR
    0.60
    team
    0.60
    lda
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.