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

    Neuronpedia

    INDEX
    Explanations

    words related to intense physical or emotional pain

    oai_token-act-pair · gpt-3.5-turbo

    references to pain and suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.92
    available
    -0.84
    ordan
    -0.82
    RAFT
    -0.81
    ioch
    -0.81
    ept
    -0.80
    ribution
    -0.80
    AA
    -0.78
    resp
    -0.78
    izen
    -0.77
    POSITIVE LOGITS
     painful
    1.22
     pain
    1.01
     agony
    0.92
     excruciating
    0.89
     prick
    0.87
     pains
    0.86
     deflation
    0.83
     wounds
    0.82
     torment
    0.81
     discomfort
    0.80
    Act Density 0.011%

    No Known Activations