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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or complexity in relationships and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someone
    -0.15
    à¹īวย
    -0.14
    ãģĵãĤĵãģ«
    -0.14
    opis
    -0.14
    aning
    -0.14
     either
    -0.14
    eus
    -0.14
    ->[
    -0.14
    Already
    -0.14
     somebody
    -0.14
    POSITIVE LOGITS
     somewhat
    0.20
     slightly
    0.18
     rather
    0.17
    aled
    0.16
     suitable
    0.16
    ä¸Ģèµ·
    0.16
     realistic
    0.16
    -ish
    0.16
    ables
    0.15
     Beste
    0.15
    Act Density 0.010%

    No Known Activations