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

    Neuronpedia

    INDEX
    Explanations

    references to concepts or items that are being discussed or evaluated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endale
    -0.17
    ำ
    -0.16
    asn
    -0.15
    shan
    -0.15
    lington
    -0.15
    asley
    -0.15
    AndView
    -0.14
    åĮĸ
    -0.14
    asio
    -0.14
    ersh
    -0.14
    POSITIVE LOGITS
     Mann
    0.17
    ģ
    0.15
    ÙĪاÙĩ
    0.15
    nal
    0.14
    pok
    0.14
    iros
    0.14
     Zy
    0.13
    ajÄħc
    0.13
    .abstract
    0.13
    addin
    0.13
    Act Density 0.134%

    No Known Activations