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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shirley
    -0.17
    Larry
    -0.17
    ilda
    -0.17
     Judith
    -0.16
     Diane
    -0.16
     Debbie
    -0.16
    ça
    -0.15
     Joan
    -0.15
     Judy
    -0.15
    å±±å¸Ĥ
    -0.15
    POSITIVE LOGITS
     Brittany
    0.25
     Matt
    0.23
    Matt
    0.20
     matt
    0.20
     Meghan
    0.20
     Chase
    0.19
     Adam
    0.19
     Josh
    0.18
     Ryan
    0.18
     Matthew
    0.18
    Act Density 0.326%

    No Known Activations