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

    Neuronpedia

    INDEX
    Explanations

    words related to human emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Broad
    -0.69
    aks
    -0.67
    wise
    -0.66
     Conserv
    -0.65
    Minimum
    -0.65
     Recommended
    -0.64
     Labs
    -0.63
     Telescope
    -0.63
    recomm
    -0.63
     Silk
    -0.62
    POSITIVE LOGITS
     emotion
    3.60
     emotions
    3.00
     emotional
    1.99
     emotionally
    1.61
     empathy
    1.57
     emot
    1.56
     sadness
    1.55
     feelings
    1.46
     sorrow
    1.38
     sentiment
    1.37
    Act Density 0.019%

    No Known Activations