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

    Neuronpedia

    INDEX
    Explanations

    family members, relatives, and relationships related words

    oai_token-act-pair · gpt-3.5-turbo

    references to family members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettlement
    -0.83
    ulent
    -0.78
    çķ
    -0.77
     tainted
    -0.72
    ensus
    -0.68
    kefeller
    -0.67
    ãĤ¤ãĥĪ
    -0.66
    tain
    -0.65
    utterstock
    -0.65
     Shutterstock
    -0.64
    POSITIVE LOGITS
     commented
    0.91
     loves
    0.80
     OCD
    0.78
     hooked
    0.78
    ÃŃs
    0.77
     niece
    0.77
     smokes
    0.76
     coworkers
    0.76
     ______
    0.73
     subscrib
    0.72
    Act Density 0.279%

    No Known Activations