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

    Neuronpedia

    INDEX
    Explanations

    references to experimental errors or biases in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IConfiguration
    -0.43
     Мексичка
    -0.42
    principalColumn
    -0.40
     '\\;'
    -0.40
    енча
    -0.39
     BytesLike
    -0.38
    setContentView
    -0.38
     mainstay
    -0.37
    меч
    -0.37
    ᅠ
    -0.36
    POSITIVE LOGITS
     caused
    2.30
    caused
    1.97
     Caused
    1.88
     occasioned
    1.87
     arising
    1.79
     resulting
    1.75
     spowod
    1.73
     induced
    1.73
     generated
    1.63
     engendered
    1.57
    Act Density 2.334%

    No Known Activations