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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     millenn
    -0.70
    ereo
    -0.68
     affiliation
    -0.66
     independently
    -0.65
     unilaterally
    -0.65
    born
    -0.64
     sponsorship
    -0.64
     peacefully
    -0.64
    ãĥ¡
    -0.64
    ¯
    -0.61
    POSITIVE LOGITS
    xi
    0.71
     Hayward
    0.70
    ZX
    0.70
    llah
    0.69
    sbm
    0.69
     Shattered
    0.68
    ween
    0.66
     Townsend
    0.66
    heny
    0.65
    anz
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.