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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or expressions, particularly the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.70
     Paglinawan
    -0.69
    InitStruct
    -0.67
     specimens
    -0.65
    IndentedString
    -0.63
    queryInterface
    -0.62
     Specimens
    -0.62
     sache
    -0.60
     AspNetCore
    -0.60
    Bronnen
    -0.59
    POSITIVE LOGITS
     not
    0.82
     cuchillo
    0.59
     אשר
    0.57
    not
    0.56
    Tl
    0.54
     سكانية
    0.54
    indl
    0.53
     Vikipedi
    0.53
     úgy
    0.53
     direct
    0.53
    Act Density 0.168%

    No Known Activations