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

    Neuronpedia

    INDEX
    Explanations

    parentheses indicating emphasis or additional information

    oai_token-act-pair · gpt-3.5-turbo

    the presence of parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     orn
    -0.75
     retard
    -0.74
     inund
    -0.74
     nutrient
    -0.71
     pine
    -0.71
     millenn
    -0.71
     glare
    -0.69
     entitle
    -0.68
     dow
    -0.66
     flee
    -0.65
    POSITIVE LOGITS
    emphasis
    1.28
    albeit
    1.28
    sic
    1.28
    again
    1.27
    possibly
    1.25
    !)
    1.23
    ?)
    1.22
    ...)
    1.20
    âĢ¦)
    1.20
    perhaps
    1.19
    Act Density 0.173%

    No Known Activations