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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sacrific
    -0.73
     destro
    -0.73
    aimon
    -0.71
    iverpool
    -0.68
    rup
    -0.66
     exting
    -0.65
    anism
    -0.64
    ministic
    -0.64
     proble
    -0.62
    umenthal
    -0.62
    POSITIVE LOGITS
    ĸļ
    0.85
    drawn
    0.76
    plane
    0.66
     cousins
    0.64
     proven
    0.60
     developed
    0.59
     been
    0.59
    enance
    0.59
     fewer
    0.59
     nothing
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.