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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to programming and technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eni
    -0.18
    urum
    -0.15
    ibold
    -0.15
    /helper
    -0.14
    áp
    -0.14
    鹿
    -0.14
    ÏĥÏĦα
    -0.14
    ãģĹãĤĩãģĨ
    -0.14
    agrams
    -0.13
    URRE
    -0.13
    POSITIVE LOGITS
    opes
    0.18
    iban
    0.16
    TeV
    0.15
    odos
    0.15
     Ting
    0.14
     Hanson
    0.14
    emen
    0.14
    éĥİ
    0.14
    stown
    0.14
     Kes
    0.14
    Act Density 0.009%

    No Known Activations