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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Berry
    -0.90
    gans
    -0.70
    imentary
    -0.68
    lean
    -0.67
    lihood
    -0.65
    ibilities
    -0.65
    itsch
    -0.64
     Germ
    -0.63
    Depth
    -0.62
    Form
    -0.61
    POSITIVE LOGITS
    cffff
    0.88
     corrid
    0.81
     confir
    0.78
     Strongh
    0.76
     redes
    0.71
     crest
    0.71
    EStream
    0.70
     helicop
    0.69
    nown
    0.68
    kees
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.