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

    Neuronpedia

    INDEX
    Explanations

    data related to statistical significance and multivariate analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.68
    __':
    -0.57
    Попис
    -0.55
     propOrder
    -0.54
    __":
    -0.54
    findpost
    -0.54
    __':
    -0.54
    __":
    -0.51
     CreateTagHelper
    -0.50
    awtextra
    -0.49
    POSITIVE LOGITS
     regularization
    0.72
     normalization
    0.69
     weights
    0.68
     clipping
    0.67
     scaling
    0.65
     normalize
    0.65
     weight
    0.64
    std
    0.63
     std
    0.62
    weight
    0.62
    Act Density 1.399%

    No Known Activations