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

    Neuronpedia

    INDEX
    Explanations

    opening parenthesis

    oai_token-act-pair · gpt-3.5-turbo

    the use of parentheses, particularly in reference to sourcing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veget
    -0.87
     inund
    -0.81
     appreci
    -0.80
     cones
    -0.77
     appropri
    -0.76
     invari
    -0.76
     stud
    -0.74
     erect
    -0.72
     decor
    -0.70
     explan
    -0.70
    POSITIVE LOGITS
    *)
    1.37
    âĢ¦)
    1.13
    ...)
    1.09
    -)
    1.06
    ?)
    1.03
    +)
    1.02
    MORE
    1.00
    click
    0.96
    BOOK
    0.96
    aka
    0.93
    Act Density 0.021%

    No Known Activations