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

    Neuronpedia

    INDEX
    Explanations

    family relationships and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.86
    CAP
    -0.75
    Scale
    -0.73
    è£ħ
    -0.73
    aly
    -0.72
    Ĥİ
    -0.71
    £ı
    -0.69
    pmwiki
    -0.67
    ãģ®å®
    -0.66
     Painting
    -0.66
    POSITIVE LOGITS
     sister
    1.79
     aunt
    1.78
     sisters
    1.78
     nephew
    1.76
     grandmother
    1.75
     grandparents
    1.75
     cousins
    1.73
     niece
    1.72
     grandfather
    1.70
     brother
    1.66
    Act Density 0.131%

    No Known Activations