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

    Neuronpedia

    INDEX
    Explanations

    references to prominent institutions, organizations, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saa
    -0.30
    行
    -0.30
    помним
    -0.30
     промы
    -0.30
    价比
    -0.30
     смы
    -0.30
     enoj
    -0.29
     η
    -0.28
    ifikant
    -0.28
    逾
    -0.28
    POSITIVE LOGITS
     Office
    0.82
     Department
    0.82
     University
    0.71
     Institute
    0.69
    ScopeManager
    0.66
     American
    0.66
     يتيمه
    0.66
    Office
    0.65
    Department
    0.65
     National
    0.65
    Act Density 0.624%

    No Known Activations