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-miniTriggered by @bot

    mother

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slant
    -0.61
    igurumi
    -0.56
    lewati
    -0.55
     Skyline
    -0.54
    ĵ
    -0.52
    lightning
    -0.51
    YourGuide
    -0.51
     Zap
    -0.51
     Gust
    -0.50
     DX
    -0.50
    POSITIVE LOGITS
     mother
    1.11
     Mother
    1.09
    Mother
    1.02
     MOTHER
    0.95
    mother
    0.94
     Mothers
    0.93
    Mothers
    0.93
    MOTHER
    0.88
     mothers
    0.87
     father
    0.81
    Act Density 0.013%

    No Known Activations