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

    Neuronpedia

    INDEX
    Explanations

    terms of endearment related to close relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms of endearment and expressions of affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.88
    ammers
    -0.80
    ulhu
    -0.79
     Enhancement
    -0.77
     Cheong
    -0.71
    oker
    -0.70
    RAFT
    -0.70
    ept
    -0.69
    NetMessage
    -0.69
    icist
    -0.68
    POSITIVE LOGITS
     dear
    1.21
     dearly
    0.97
     departed
    0.82
     hearts
    0.80
     beloved
    0.75
     friend
    0.75
    born
    0.74
     memories
    0.72
    lier
    0.71
     old
    0.70
    Act Density 0.016%

    No Known Activations