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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ITED
    -0.78
    atern
    -0.78
    iking
    -0.67
    ´
    -0.67
    unction
    -0.66
    aven
    -0.65
    ITS
    -0.65
     tether
    -0.64
    FN
    -0.63
    isf
    -0.62
    POSITIVE LOGITS
    abwe
    0.86
     PACs
    0.64
    ãĤ¼
    0.64
     shooter
    0.63
    halla
    0.62
     scrimmage
    0.61
     terrorists
    0.60
     outcome
    0.60
    ihadi
    0.59
     Explosion
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.