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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate roles or descriptions of characters in films or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wolff
    -0.18
    ãĥ¼ãĥķ
    -0.16
    weit
    -0.16
    swick
    -0.15
    oped
    -0.14
    tons
    -0.14
    ÐĴС
    -0.14
    keley
    -0.14
    pecting
    -0.14
    heed
    -0.14
    POSITIVE LOGITS
    778
    0.15
     Indust
    0.15
    actory
    0.15
    upro
    0.15
    egin
    0.14
    gings
    0.14
    nic
    0.14
     Fri
    0.14
    annels
    0.13
     Yue
    0.13
    Act Density 0.010%

    No Known Activations