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

    Neuronpedia

    INDEX
    Explanations

    terms associated with critiques and assessments of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.80
     snippetHide
    -0.78
     houſe
    -0.77
    rawDesc
    -0.75
    adaptiveStyles
    -0.74
    出版年
    -0.70
     endwhile
    -0.70
     становника
    -0.69
    ScopeManager
    -0.69
     foon
    -0.66
    POSITIVE LOGITS
    DriverManager
    0.52
     Executive
    0.49
     Donnelly
    0.48
    rolo
    0.47
    ige
    0.45
    markt
    0.43
    방
    0.43
    dont
    0.43
     Millar
    0.43
     don
    0.43
    Act Density 0.456%

    No Known Activations