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

    Neuronpedia

    INDEX
    Explanations

    text related to questions, inquiries, and the pursuit of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĨµ
    -0.14
     Komment
    -0.13
    ï¿¥
    -0.13
    اض
    -0.13
     libertine
    -0.13
    anton
    -0.13
    rana
    -0.13
     none
    -0.12
    lieÃŁlich
    -0.12
    нÑĤ
    -0.12
    POSITIVE LOGITS
     Wikipedia
    0.31
     wikipedia
    0.30
     Basically
    0.28
     Trad
    0.27
     Essentially
    0.27
    Basically
    0.27
     basically
    0.27
     essentially
    0.26
     Histor
    0.26
     Typically
    0.25
    Act Density 0.182%

    No Known Activations