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

    Neuronpedia

    INDEX
    Explanations

    references to mothers and mother-child relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Danilo
    -0.77
     Nye
    -0.68
    GGLE
    -0.65
     чесно
    -0.65
    udia
    -0.63
     over
    -0.63
    ség
    -0.63
     Hendricks
    -0.62
    Darius
    -0.62
    skosten
    -0.61
    POSITIVE LOGITS
     mother
    1.84
     mothers
    1.82
     Mother
    1.80
     MOTHER
    1.75
    MOTHER
    1.71
    mother
    1.70
     Mothers
    1.70
    Mothers
    1.70
    Mother
    1.68
    mothers
    1.43
    Act Density 0.050%

    No Known Activations