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

    Neuronpedia

    INDEX
    Explanations

    terms associated with adversarial relationships or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arias
    -0.17
     oku
    -0.16
    iks
    -0.16
     stol
    -0.15
    è²¼
    -0.15
    лов
    -0.14
    amm
    -0.14
    763
    -0.14
    ddit
    -0.14
    utations
    -0.14
    POSITIVE LOGITS
    ÏģÏĮÏĤ
    0.16
    elen
    0.15
    ÄĽÅ¾
    0.14
     purs
    0.14
    rschein
    0.14
     Habit
    0.14
    hr
    0.13
     wym
    0.13
    ationToken
    0.13
    .named
    0.13
    Act Density 0.111%

    No Known Activations