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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    othermal
    -0.72
    existent
    -0.63
    amba
    -0.62
    astery
    -0.62
    ourgeois
    -0.61
    uno
    -0.60
    front
    -0.60
    verts
    -0.59
    rog
    -0.58
     polic
    -0.58
    POSITIVE LOGITS
    milo
    0.71
    pmwiki
    0.69
     Ital
    0.66
     Hasan
    0.66
    ãĤ¦ãĤ¹
    0.64
     Recession
    0.64
     unbeliev
    0.63
    iameter
    0.63
     horizont
    0.63
    âĶĢâĶĢâĶĢâĶĢ
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.