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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ItemLevel
    -0.84
     Riv
    -0.76
     Creat
    -0.75
     Reincarn
    -0.74
    SpaceEngineers
    -0.72
     Revival
    -0.72
    soType
    -0.70
    oros
    -0.69
     Restoration
    -0.69
     Seeking
    -0.68
    POSITIVE LOGITS
     catch
    1.32
    catch
    0.88
     catches
    0.76
     catching
    0.69
    rots
    0.69
     hitch
    0.66
     rallying
    0.64
    osed
    0.64
     Ake
    0.64
     cents
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.