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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lima
    -0.65
    appropriate
    -0.65
     è£ıç
    -0.64
     detectors
    -0.62
    wrong
    -0.62
     isolate
    -0.57
     Yates
    -0.56
    resa
    -0.55
    ONES
    -0.55
     isolated
    -0.55
    POSITIVE LOGITS
    Tact
    0.90
    tion
    0.80
    tions
    0.77
     Warcraft
    0.76
    ¯¯¯¯¯¯¯¯
    0.75
    DCS
    0.75
    sed
    0.72
    ernaut
    0.72
    ————
    0.72
    Spawn
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.