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

    Neuronpedia

    INDEX
    Explanations

    references to daughters and female offspring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esgue
    -0.88
     defaultstate
    -0.86
    المناصب
    -0.83
    kus
    -0.77
    loys
    -0.72
    ."],
    -0.72
    OfWork
    -0.71
     tetra
    -0.71
    sätzlich
    -0.70
    ✨:
    -0.70
    POSITIVE LOGITS
     daughters
    1.38
     filles
    1.24
     daughter
    1.23
    UGHTER
    1.21
    daughter
    1.10
     Daughter
    1.08
    Daughter
    1.07
     girls
    1.04
     Daughters
    1.03
     datter
    0.97
    Act Density 0.057%

    No Known Activations