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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ellig
    -0.62
    LOS
    -0.61
    )].
    -0.60
     HIM
    -0.60
    eln
    -0.60
     BELOW
    -0.59
    heon
    -0.58
    MODE
    -0.58
     Sark
    -0.58
    tones
    -0.56
    POSITIVE LOGITS
    76561
    0.92
     Corridor
    0.75
    ItemTracker
    0.75
    Reloaded
    0.71
    Construct
    0.71
    rett
    0.67
    ãĥīãĥ©ãĤ´ãĥ³
    0.66
    HCR
    0.65
    cule
    0.65
    Medium
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.