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

    Neuronpedia

    INDEX
    Explanations

    sequences of tokens that start with an underscore followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CUIT
    -0.42
     EconPapers
    -0.42
    עו
    -0.42
     gynhyrchwyd
    -0.42
     ид
    -0.42
    ffion
    -0.41
     történ
    -0.41
     Lakukan
    -0.41
    stopwatch
    -0.40
     đội
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.94
    LabelTagHelper
    0.90
     beginnetje
    0.84
    TagMode
    0.81
     Roskov
    0.79
    WriteLiteral
    0.79
     betweenstory
    0.78
    awtextra
    0.76
    richTextPanel
    0.73
    ंदीखरीदारी
    0.72
    Act Density 0.530%

    No Known Activations