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

    Neuronpedia

    INDEX
    Explanations

    references to offerings, services, or features in promotional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SelectionMode
    -0.16
    apult
    -0.15
    abar
    -0.15
    ìĩ
    -0.15
    atron
    -0.14
    quotes
    -0.14
    DL
    -0.14
    cola
    -0.14
    mas
    -0.14
    stime
    -0.14
    POSITIVE LOGITS
     Weg
    0.15
    æŃ¢
    0.14
    frei
    0.14
     govern
    0.13
     underlying
    0.13
     unders
    0.13
     entirety
    0.13
    ads
    0.13
    uss
    0.13
    ams
    0.13
    Act Density 0.033%

    No Known Activations