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

    Neuronpedia

    INDEX
    Explanations

    references to reports and associated documents or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ro
    -0.56
     record
    -0.56
     formal
    -0.55
     program
    -0.55
     r
    -0.54
     rend
    -0.52
     ri
    -0.52
     model
    -0.50
     recently
    -0.49
    roe
    -0.49
    POSITIVE LOGITS
     Report
    1.15
     يتيمه
    1.01
    Report
    1.01
     CreateTagHelper
    0.94
     Regulation
    0.94
    providedIn
    0.91
     Review
    0.91
     Regulations
    0.90
     Reformation
    0.88
    rrggbb
    0.85
    Act Density 0.231%

    No Known Activations