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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    icity
    -0.69
    otte
    -0.66
    ãĥ¼
    -0.65
     Eh
    -0.63
     Donation
    -0.62
     GOODMAN
    -0.59
     JS
    -0.59
     SOS
    -0.59
     PIT
    -0.59
    ogene
    -0.57
    POSITIVE LOGITS
     misunder
    0.86
    senal
    0.85
     mosqu
    0.82
     obser
    0.78
     horm
    0.76
    beh
    0.76
     newsp
    0.74
     Ukrain
    0.73
     exha
    0.71
     lapt
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.