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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical or emotional pain

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pizarro
    -0.47
     Lehman
    -0.43
     Alain
    -0.43
     Swanson
    -0.43
    Alain
    -0.42
    Sar
    -0.41
     Delano
    -0.41
    Vog
    -0.41
    Cechy
    -0.40
     Coppola
    -0.40
    POSITIVE LOGITS
     hurt
    1.17
     Hurt
    1.16
    Hurt
    1.01
    hurt
    1.00
     hurts
    0.93
     hurting
    0.91
     Hurts
    0.89
     HUR
    0.85
     Hur
    0.67
     hurtful
    0.65
    Act Density 0.067%

    No Known Activations