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

    Neuronpedia

    INDEX
    Explanations

    specific names, particularly associated with legal or scientific references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Moc
    -0.67
    s
    -0.66
    volmente
    -0.63
    ed
    -0.62
    >>>>>
    -0.62
    Moc
    -0.62
     Ciro
    -0.62
     Trom
    -0.60
     Houghton
    -0.60
    ppert
    -0.60
    POSITIVE LOGITS
     EIS
    1.10
     Willis
    1.09
     nahilalakip
    1.05
    eis
    1.02
     tris
    1.02
     Elis
    1.02
    llis
    1.01
    ellis
    1.00
    Tris
    0.96
     LIS
    0.96
    Act Density 0.169%

    No Known Activations