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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating first and second person references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pole
    -0.17
    ÙĦب
    -0.17
    AWN
    -0.16
    umber
    -0.16
     herself
    -0.15
     nat
    -0.15
    uate
    -0.14
     himself
    -0.14
    blink
    -0.14
     solar
    -0.14
    POSITIVE LOGITS
     rằng
    0.16
    NameValuePair
    0.15
    ÑĤон
    0.15
    à¥įतà¤ķ
    0.15
     bahwa
    0.14
    lok
    0.14
    ecast
    0.14
    ecut
    0.14
    lique
    0.14
     Subscriber
    0.13
    Act Density 0.058%

    No Known Activations