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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     granddaughter
    -0.30
     grandson
    -0.28
     grandchildren
    -0.22
     grandfather
    -0.21
     grandparents
    -0.20
     grand
    -0.20
     niece
    -0.20
     Cousins
    -0.19
    -grand
    -0.19
    åŃĻ
    -0.19
    POSITIVE LOGITS
     late
    0.17
     folks
    0.16
    оже
    0.14
    åĪ
    0.14
     ultra
    0.14
     freelancer
    0.14
     alcoholic
    0.14
     Late
    0.13
     reserved
    0.13
     convention
    0.13
    Act Density 0.118%

    No Known Activations