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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    udeb
    -0.71
    resist
    -0.69
    hold
    -0.68
    ado
    -0.67
    enser
    -0.66
    ugen
    -0.65
    iggs
    -0.65
    integ
    -0.63
    urrent
    -0.63
    adden
    -0.62
    POSITIVE LOGITS
     Qiao
    0.73
     DW
    0.66
     DPR
    0.65
     Rebell
    0.65
     Devi
    0.65
     Imm
    0.61
     JR
    0.60
     DM
    0.59
    æĺ
    0.58
     Oo
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.