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

    Neuronpedia

    INDEX
    Explanations

    terms related to international relations and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.18
    owski
    -0.17
    ourg
    -0.17
    ification
    -0.17
    uld
    -0.16
    led
    -0.16
    rý
    -0.15
    jour
    -0.15
    ipo
    -0.14
    baz
    -0.14
    POSITIVE LOGITS
    åĬ¨çĶŁæĪIJ
    0.19
    polator
    0.17
    eing
    0.17
    rosse
    0.16
    iors
    0.16
    stitial
    0.15
    AFX
    0.15
    ãģªãĤĭ
    0.15
    iosper
    0.15
    halb
    0.15
    Act Density 0.078%

    No Known Activations