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

    Neuronpedia

    INDEX
    Explanations

    endearments or terms of affection

    oai_token-act-pair · gpt-3.5-turbo

    terms of endearment and affectionate language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammers
    -0.84
    hner
    -0.80
     Cheong
    -0.79
    DoS
    -0.76
    ioch
    -0.76
    TPPStreamerBot
    -0.74
    IDER
    -0.73
    RAFT
    -0.71
    oker
    -0.71
    vernment
    -0.70
    POSITIVE LOGITS
     dear
    1.12
     dearly
    0.89
     departed
    0.87
     friend
    0.81
     old
    0.78
     hearts
    0.77
     admiration
    0.75
     friends
    0.73
     memories
    0.73
     uncle
    0.72
    Act Density 0.019%

    No Known Activations