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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to tension and conflict in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anes
    -0.16
    ERSIST
    -0.15
     SUBSTITUTE
    -0.15
    hti
    -0.15
    zeÅĪ
    -0.14
    éļľ
    -0.14
    عت
    -0.14
    ÃŃst
    -0.14
    urette
    -0.14
    uco
    -0.14
    POSITIVE LOGITS
    ant
    0.17
    ostel
    0.16
    ettes
    0.15
    ÌĤ
    0.15
    shan
    0.15
    .subscriptions
    0.14
     alt
    0.14
     Poe
    0.14
     Bye
    0.14
    .estado
    0.14
    Act Density 0.007%

    No Known Activations