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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations related to inner products and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    下载附件
    -0.63
    bewah
    -0.56
     浜
    -0.54
    retweeted
    -0.52
    ="+
    -0.51
    InvalidProtocol
    -0.51
     Roch
    -0.50
    ecore
    -0.50
     canto
    -0.50
     Dinah
    -0.49
    POSITIVE LOGITS
    jLabel
    0.94
     Sacrific
    0.84
    sacrific
    0.81
     sacrifice
    0.81
     sacrifices
    0.79
    sacrifice
    0.79
    ProductService
    0.79
     Sacrifice
    0.78
     sacrificial
    0.78
    QPushButton
    0.77
    Act Density 0.106%

    No Known Activations