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

    Neuronpedia

    INDEX
    Explanations

    contextual references to statistical differences and comparisons in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.59
    клопе
    -0.58
    WebServlet
    -0.51
    로드
    -0.51
    DispatchToProps
    -0.50
    rouvez
    -0.50
    קישורים
    -0.49
     gehör
    -0.49
     referenties
    -0.48
     yerine
    -0.48
    POSITIVE LOGITS
     difference
    0.86
    差
    0.79
     between
    0.77
     gap
    0.74
     Differenz
    0.72
     差
    0.71
    Between
    0.71
     Difference
    0.71
    difference
    0.70
     Gap
    0.69
    Act Density 0.918%

    No Known Activations