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

    Neuronpedia

    INDEX
    Explanations

    instances of relationships or connections with siblings

    oai_token-act-pair · gpt-3.5-turbo

    the word "sister" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustomed
    -0.70
    ustom
    -0.68
    ocobo
    -0.64
    asu
    -0.64
    uliffe
    -0.63
    tech
    -0.63
    ered
    -0.62
    uden
    -0.62
    veyard
    -0.61
    idays
    -0.61
    POSITIVE LOGITS
    hood
    1.29
    hips
    1.03
     sisters
    0.93
     Sister
    0.85
     Bella
    0.82
     sister
    0.80
     Sisters
    0.80
     Sakuya
    0.78
    heses
    0.76
    ystem
    0.75
    Act Density 0.027%

    No Known Activations