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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    laus
    -0.77
    MpServer
    -0.74
    omever
    -0.71
    BuyableInstoreAndOnline
    -0.70
    ulpt
    -0.67
    worm
    -0.67
    uria
    -0.65
    ebin
    -0.65
    ications
    -0.64
    fitting
    -0.64
    POSITIVE LOGITS
    sembly
    0.68
    hyde
    0.68
     Dispatch
    0.64
     Recall
    0.63
     checkout
    0.59
     anything
    0.59
     onwards
    0.59
     vomit
    0.59
    fly
    0.58
     da
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.