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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.86
     tremend
    -0.79
    rama
    -0.70
    lished
    -0.70
    LINE
    -0.69
     prol
    -0.65
    lishing
    -0.63
     Tales
    -0.62
     benchmarks
    -0.62
    ãģĭ
    -0.62
    POSITIVE LOGITS
    othal
    0.69
     vap
    0.68
    abol
    0.68
    itaire
    0.65
    Reply
    0.63
    ¯¯¯¯
    0.62
    ipes
    0.61
     cancellation
    0.58
     Dull
    0.58
    uckle
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.