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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    endi
    -0.71
    ixtures
    -0.68
     realised
    -0.66
    cules
    -0.65
     chilly
    -0.64
    ilated
    -0.64
    ulsion
    -0.64
     phased
    -0.64
     aggress
    -0.62
    ominated
    -0.61
    POSITIVE LOGITS
    RIP
    0.76
    kefeller
    0.75
    irtual
    0.75
    WORK
    0.74
    ========
    0.73
    OAD
    0.72
    TPP
    0.72
    åĤ
    0.70
    å°Ĩ
    0.68
    Church
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.