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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    to say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.75
     Италијани
    -0.60
     bénéficiaire
    -0.54
     виправивши
    -0.52
     Roskov
    -0.52
    şört
    -0.50
     препратки
    -0.47
    })*/
    -0.47
    ंदीखरीदारी
    -0.46
     noDo
    -0.45
    POSITIVE LOGITS
    remark
    0.42
     comment
    0.40
    ioutil
    0.40
    extAlignment
    0.40
    ToDouble
    0.40
     Comment
    0.40
     commenting
    0.39
    ToReturn
    0.39
     about
    0.39
    printStackTrace
    0.39
    Act Density 0.002%

    No Known Activations