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

    Neuronpedia

    INDEX
    Explanations

    words related to familial relationships and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     granddaughter
    -0.18
    αÏģά
    -0.16
     grandson
    -0.15
    amespace
    -0.14
    tility
    -0.14
    phe
    -0.14
    ä¸Ī夫
    -0.14
    .localized
    -0.14
    URA
    -0.14
    argas
    -0.14
    POSITIVE LOGITS
     Grammy
    0.25
     Pap
    0.25
     Pop
    0.24
     nan
    0.22
     Gram
    0.22
     Nan
    0.22
     pops
    0.20
     Grand
    0.19
     pop
    0.19
    nan
    0.19
    Act Density 0.221%

    No Known Activations