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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology and syntax errors in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tackle
    -0.62
    ¥µ
    -0.61
    "?
    -0.56
    ¥ŀ
    -0.56
    "/>
    -0.56
    peror
    -0.55
     municip
    -0.54
     flavorful
    -0.54
     âĸ
    -0.53
    uve
    -0.53
    POSITIVE LOGITS
     '
    2.73
     '[
    2.53
     '.
    2.43
     ',
    2.33
     '/
    2.06
     '(
    2.05
     ('
    2.01
     ['
    1.91
    ,'
    1.86
    .'
    1.82
    Act Density 0.154%

    No Known Activations