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

    Neuronpedia

    INDEX
    Explanations

    the character apostrophe in various contexts

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

    mentions of possessive forms or contractions related to ownership or belonging

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

    possessive 's endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    “
    -0.76
    ”).
    -0.76
    httphttps
    -0.74
    “:
    -0.74
    RectangleBorder
    -0.73
    ’).
    -0.70
    -0.69
    BeginInit
    -0.67
    ”
    -0.67
    ;">

    -0.66
    POSITIVE LOGITS
    s
    1.87
     '
    0.96
    t
    0.84
    ...'
    0.83
     "
    0.78
    €™
    0.76
    es
    0.73
    ed
    0.73
    ы
    0.73
    d
    0.73
    Act Density 0.360%
    No Known Activations