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

    Neuronpedia

    INDEX
    Explanations

    specific types of nouns and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ison
    -0.15
    itet
    -0.14
    ISON
    -0.14
    æ½
    -0.14
     zi
    -0.14
     Retirement
    -0.14
    otr
    -0.14
    ament
    -0.14
    RT
    -0.13
    elic
    -0.13
    POSITIVE LOGITS
    805
    0.17
    ÙĤÙħ
    0.16
    Goods
    0.15
    nicas
    0.15
    lub
    0.15
    opensource
    0.14
    ajo
    0.14
     náklad
    0.14
    reater
    0.14
    maal
    0.14
    Act Density 0.007%

    No Known Activations