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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences in quotes within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    instances of opening parentheses or quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )'
    -0.62
    ?'
    -0.61
    ,'
    -0.54
     shocking
    -0.54
    TPPStreamerBot
    -0.54
    gard
    -0.52
    auga
    -0.52
     manag
    -0.51
    .'
    -0.50
     Bengal
    -0.50
    POSITIVE LOGITS
     ("
    3.51
     ["
    2.05
     ('
    2.05
    ("
    1.75
    /"
    1.72
    —"
    1.58
     (=
    1.56
     (#
    1.46
     ([
    1.44
     ($
    1.41
    Act Density 0.013%

    No Known Activations