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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or special characters within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     —
    -0.26
     â
    -0.20
     <!--
    -0.20
     Â
    -0.19
     &#
    -0.18
     --
    -0.17
    licence
    -0.16
     —↵↵
    -0.16
     kilometres
    -0.15
     ("
    -0.15
    POSITIVE LOGITS
     ‘
    0.39
    ‘
    0.31
    ’
    0.29
    -↵
    0.26
    -
    0.26
    ’s
    0.24
    ’,
    0.23
    ’S
    0.21
     Natalie
    0.21
    ’↵
    0.21
    Act Density 0.002%

    No Known Activations