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

    Neuronpedia

    INDEX
    Explanations

    references and instances of comments and opposition within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.56
     możliwe
    -0.54
     HasFactory
    -0.50
    
    -0.50
     uzyskać
    -0.49
     vanguardia
    -0.49
     uveden
    -0.49
    ChildScrollView
    -0.48
     werkzaam
    -0.48
     czł
    -0.47
    POSITIVE LOGITS
     comment
    0.81
     pile
    0.69
    Comment
    0.65
     pin
    0.65
    comments
    0.60
     pins
    0.60
    comment
    0.57
     Comment
    0.57
     patch
    0.56
     caps
    0.56
    Act Density 0.291%

    No Known Activations