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

    Neuronpedia

    INDEX
    Explanations

    references to mothers and maternal figures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ).]
    -0.79
     ſhall
    -0.77
    PreferredItem
    -0.74
    ashqai
    -0.74
    Asie
    -0.73
     Destin
    -0.73
     propOrder
    -0.73
    %)$
    -0.72
    }`}>
    -0.72
     Hermit
    -0.71
    POSITIVE LOGITS
     mothers
    0.86
    Mothers
    0.78
    mother
    0.75
     Mothers
    0.75
    MOTHER
    0.75
    Octo
    0.74
     MOTHER
    0.69
     scor
    0.68
    ofa
    0.67
     Mother
    0.67
    Act Density 0.015%

    No Known Activations