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

    Neuronpedia

    INDEX
    Explanations

    words related to physical pain or negative experiences

    oai_token-act-pair · gpt-3.5-turbo

    words related to intense emotional or physical suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rons
    -0.71
    craft
    -0.67
     Advance
    -0.67
     Supplement
    -0.65
    tower
    -0.65
    brew
    -0.64
    Town
    -0.64
    antry
    -0.63
     Cover
    -0.62
    DM
    -0.61
    POSITIVE LOGITS
     painful
    3.23
     excruciating
    1.92
     humiliating
    1.75
     shameful
    1.71
     traumatic
    1.70
     debilitating
    1.63
     unbearable
    1.60
     embarrassing
    1.55
     uncomfortable
    1.55
     heartbreaking
    1.54
    Act Density 0.021%

    No Known Activations