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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ample
    -0.79
    agues
    -0.71
    assis
    -0.69
     ante
    -0.66
    amber
    -0.66
    VIDIA
    -0.65
    angelo
    -0.65
    ario
    -0.64
    oscope
    -0.64
     Resurrection
    -0.64
    POSITIVE LOGITS
    icable
    0.71
     Nare
    0.69
     cc
    0.67
    body
    0.65
    dyl
    0.64
     exha
    0.63
    dh
    0.63
    yang
    0.62
    dy
    0.61
     LF
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.