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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    RFC
    -0.84
    opic
    -0.73
    rano
    -0.73
    pak
    -0.66
     sworn
    -0.66
    arily
    -0.62
     ..."
    -0.62
    unts
    -0.60
    conservancy
    -0.60
    footed
    -0.60
    POSITIVE LOGITS
    ione
    0.71
     havoc
    0.67
    DERR
    0.64
    isi
    0.64
     Magicka
    0.64
     ACTIONS
    0.63
    rendered
    0.63
    aii
    0.60
     Imm
    0.60
    anza
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.