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

    Neuronpedia

    INDEX
    Explanations

    words related to identity and dual roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.52
    請繼續往下閱讀
    -0.50
     ReactDOM
    -0.49
    withOpacity
    -0.48
    MEMORANDUM
    -0.48
    itados
    -0.46
    bootstrapcdn
    -0.46
    ResumeLayout
    -0.46
     velkommen
    -0.46
     Tiểu
    -0.45
    POSITIVE LOGITS
     terms
    2.26
     words
    2.14
     term
    2.04
     terminology
    1.93
    terms
    1.86
     termes
    1.78
     word
    1.75
     Terms
    1.71
     phrases
    1.67
    Terms
    1.64
    Act Density 0.720%

    No Known Activations