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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical values, particularly emphasizing lists or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     analyst
    -0.60
     analys
    -0.59
     knowledgeable
    -0.59
    iott
    -0.57
     crunch
    -0.57
     lett
    -0.57
     kernels
    -0.56
     dogged
    -0.56
     weighing
    -0.56
    ollah
    -0.56
    POSITIVE LOGITS
     Definitions
    0.77
    ():
    0.73
    :]
    0.71
    interstitial
    0.68
    200000
    0.67
    ctuary
    0.66
    00200000
    0.64
    SourceFile
    0.63
    stood
    0.62
    aaa
    0.62
    Act Density 0.098%

    No Known Activations