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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism and doubt in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ť
    -0.14
     ÑģебÑı
    -0.13
    inosaur
    -0.13
    ucht
    -0.13
    ernes
    -0.13
    /books
    -0.13
    ãģ¯ãģĦ
    -0.13
    yz
    -0.13
    otec
    -0.12
    getManager
    -0.12
    POSITIVE LOGITS
     nobody
    0.27
     we
    0.24
     people
    0.23
     everybody
    0.23
     there
    0.22
     they
    0.22
     everyone
    0.22
     none
    0.21
     somebody
    0.21
     someone
    0.19
    Act Density 1.575%

    No Known Activations