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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.20
     “[
    -0.19
     “
    -0.17
     â
    -0.17
     —
    -0.16
     âĢŀ
    -0.15
     âĢķ
    -0.15
     ”
    -0.15
    ,’”
    -0.14
    âĢŀA
    -0.14
    POSITIVE LOGITS
     "
    0.27
    's
    0.23
    've
    0.20
     '
    0.20
    'll
    0.20
    "
    0.20
    'clock
    0.19
    ".↵↵
    0.19
    ",
    0.19
    ".↵
    0.19
    Act Density 0.589%

    No Known Activations