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

    Neuronpedia

    INDEX
    Explanations

    text surrounded by parentheses with a numerical value inside the parentheses

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their prevalence in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imposing
    -0.73
     embargo
    -0.71
     abroad
    -0.69
     imperson
    -0.68
     intellig
    -0.68
     electr
    -0.67
     vil
    -0.67
     invari
    -0.67
     cellar
    -0.66
     surrogate
    -0.66
    POSITIVE LOGITS
    SourceFile
    1.29
    *)
    1.24
    +)
    1.12
    edited
    1.10
    -)
    1.10
    ?)
    1.07
    ...)
    1.05
    tm
    1.04
    TM
    0.99
    sic
    0.99
    Act Density 0.033%

    No Known Activations