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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ophon
    -0.71
    yssey
    -0.67
    entimes
    -0.66
    BuyableInstoreAndOnline
    -0.64
    efficients
    -0.64
    istically
    -0.64
    Project
    -0.63
    ITH
    -0.62
    ulia
    -0.62
    ocally
    -0.62
    POSITIVE LOGITS
     RR
    0.69
     Ready
    0.66
     PROT
    0.66
     LIM
    0.64
     CFR
    0.64
    PIN
    0.64
    ARE
    0.63
     ARC
    0.62
    stood
    0.61
    ergy
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.