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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tein
    -0.80
    irs
    -0.70
     sorts
    -0.70
     Blocks
    -0.67
     handcuffs
    -0.66
     cracks
    -0.65
     delim
    -0.65
    FLAG
    -0.64
     bricks
    -0.64
     crack
    -0.63
    POSITIVE LOGITS
    rera
    0.75
    reath
    0.72
    ashtra
    0.72
    irled
    0.71
     Weaver
    0.69
    olina
    0.68
    etter
    0.68
    Machine
    0.68
    veyard
    0.68
    ItemTracker
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.