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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to saving and improving lives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rost
    -0.18
     Lawson
    -0.16
     corpse
    -0.15
    LEM
    -0.14
    olest
    -0.14
    entials
    -0.13
    \CMS
    -0.13
     shrink
    -0.13
    ategories
    -0.13
    aby
    -0.13
    POSITIVE LOGITS
     lives
    1.05
     Lives
    0.82
    ives
    0.34
     futures
    0.33
     жизни
    0.30
    IVES
    0.30
    -l
    0.28
     lived
    0.28
     hearts
    0.27
     života
    0.27
    Act Density 0.111%

    No Known Activations