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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    urry
    -0.71
    isec
    -0.65
    issance
    -0.63
    cale
    -0.62
     interpol
    -0.61
    ze
    -0.60
    illary
    -0.60
     (=
    -0.59
    xia
    -0.59
     oriented
    -0.58
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    0.75
    earcher
    0.71
    wcsstore
    0.69
     separatist
    0.65
    minist
    0.63
     Bene
    0.63
    entin
    0.62
    itutional
    0.62
    bsp
    0.62
     separatists
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.