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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or emotional pain

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hurt" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.81
    pires
    -0.70
    guyen
    -0.70
    ullivan
    -0.68
    iasco
    -0.65
    å¸
    -0.63
     Collider
    -0.61
     Prospect
    -0.60
     pedigree
    -0.60
     liner
    -0.60
    POSITIVE LOGITS
    ful
    1.20
    fully
    1.03
    lessly
    0.99
    staking
    0.99
    onies
    0.95
     feelings
    0.94
    elo
    0.91
    ega
    0.88
    les
    0.84
    ted
    0.84
    Act Density 0.019%

    No Known Activations