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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript markup related to document structure and type definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.15
    μά
    -0.15
    arde
    -0.15
    бом
    -0.14
    isin
    -0.14
    unkt
    -0.14
    eder
    -0.13
    åº
    -0.13
    itr
    -0.13
    plit
    -0.13
    POSITIVE LOGITS
    abei
    0.21
    adil
    0.17
    face
    0.17
    faces
    0.15
    utch
    0.15
    alim
    0.15
     fee
    0.14
    wat
    0.14
    achi
    0.14
    å¼ı
    0.14
    Act Density 0.010%

    No Known Activations