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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mechdragon
    -0.78
    est
    -0.70
     Trog
    -0.66
    anthrop
    -0.66
    ause
    -0.65
     Ax
    -0.64
     Thrust
    -0.63
     Briggs
    -0.63
     Ruff
    -0.62
     Boost
    -0.61
    POSITIVE LOGITS
    ategories
    0.86
    qqa
    0.84
    allery
    0.80
    ertodd
    0.80
    javascript
    0.80
    ouls
    0.76
    VERTISEMENT
    0.75
    ometimes
    0.74
    ãĤ»
    0.74
    aukee
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.