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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific analysis and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     splitted
    -0.23
     everybody
    -0.17
     hardly
    -0.15
     utmost
    -0.15
    wich
    -0.15
    wers
    -0.15
    anca
    -0.15
     hubby
    -0.14
     lately
    -0.14
     gonna
    -0.14
    POSITIVE LOGITS
     recieved
    0.16
     Perhaps
    0.16
    ienne
    0.15
    Perhaps
    0.15
     perhaps
    0.15
     whilst
    0.15
    perhaps
    0.14
    mour
    0.14
    ¬ģ
    0.14
     ÙħÛĮتÙĪاÙĨ
    0.14
    Act Density 0.039%

    No Known Activations