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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating correlations or relationships in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    correlation, positive, negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.59
    новништво
    -0.59
    StructEnd
    -0.58
    antası
    -0.56
     indígen
    -0.56
     betweenstory
    -0.56
     Autorizaciones
    -0.56
     ſind
    -0.54
     kasarigan
    -0.54
     nahilalakip
    -0.53
    POSITIVE LOGITS
     correlation
    0.62
    Correlation
    0.49
     Correlation
    0.48
    correlation
    0.41
     relationship
    0.40
     Correlations
    0.38
     correlations
    0.38
     Spearman
    0.37
     positive
    0.36
     positively
    0.36
    Act Density 0.282%

    No Known Activations