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

    Neuronpedia

    INDEX
    Explanations

    names of people and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kara
    -0.18
    auge
    -0.15
     dela
    -0.15
     Tod
    -0.15
    tingham
    -0.15
    allah
    -0.15
    andal
    -0.14
    istrovstvÃŃ
    -0.14
     kara
    -0.14
    xford
    -0.14
    POSITIVE LOGITS
     Deep
    0.30
    Deep
    0.27
     Pri
    0.25
     Swap
    0.25
     Pr
    0.23
    .Deep
    0.23
    _deep
    0.22
    deep
    0.22
     Sand
    0.21
     Shr
    0.20
    Act Density 0.554%

    No Known Activations