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

    Neuronpedia

    INDEX
    Explanations

    parentheses in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imposing
    -0.73
     pim
    -0.68
     smugg
    -0.68
     maxim
    -0.68
     copying
    -0.63
     intellig
    -0.63
     invari
    -0.63
     buoy
    -0.63
     obscure
    -0.62
     raiding
    -0.62
    POSITIVE LOGITS
    +)
    1.40
    *)
    1.37
    ?)
    1.29
    -)
    1.26
    SourceFile
    1.22
    tm
    1.17
    edited
    1.17
    ?),
    1.16
    ?).
    1.12
    !)
    1.11
    Act Density 0.033%

    No Known Activations