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

    Neuronpedia

    INDEX
    Explanations

    emotional language related to affection or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms that express affection or endearment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.77
    ammers
    -0.71
    IDER
    -0.70
    AMS
    -0.70
    phrine
    -0.70
    UID
    -0.67
     Surv
    -0.66
    DERR
    -0.65
    RAFT
    -0.64
    ARC
    -0.64
    POSITIVE LOGITS
     dear
    1.36
     dearly
    0.99
     departed
    0.83
     lord
    0.79
     uncle
    0.73
     acquaintance
    0.72
     friend
    0.72
    iously
    0.72
     beloved
    0.71
    iors
    0.70
    Act Density 0.004%

    No Known Activations