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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The character apostrophe

    np_acts-logits-general · gemini-2.0-flash

    contractions and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”).
    -1.04
    )”.
    -1.04
    ’).
    -0.99
    ”،
    -0.97
    .”)
    -0.94
    ),”
    -0.94
     “.
    -0.93
     “,
    -0.92
    ”),
    -0.91
    “:
    -0.91
    POSITIVE LOGITS
    s
    1.66
     '
    1.01
    '
    0.98
     "
    0.98
    t
    0.84
     ("
    0.78
    ...'
    0.75
    €™
    0.69
    es
    0.68
     ('
    0.67
    Act Density 0.356%

    No Known Activations