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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CNT
    -0.08
    _nd
    -0.07
    yang
    -0.07
    aca
    -0.07
     favour
    -0.07
    销
    -0.06
    ✿
    -0.06
    Matching
    -0.06
    Hack
    -0.06
    bps
    -0.06
    POSITIVE LOGITS
    -reset
    0.08
     adulte
    0.08
     allegations
    0.08
     hommes
    0.08
    阍
    0.08
     rencontres
    0.07
    出局
    0.07
     şikayet
    0.07
     formulate
    0.07
    htt
    0.07
    Act Density 0.000%

    No Known Activations