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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the reader's perspective or inquiry into societal conditions

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

    "you look" or "you compare"

    np_acts-logits-general · gemini-2.0-flash

    you look, compare, ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.56
     nadzieję
    -0.53
     spéciaux
    -0.49
    AtIndexPath
    -0.48
    бяза
    -0.48
     sollten
    -0.47
     noqa
    -0.47
    DoubleQuotes
    -0.46
     powinny
    -0.46
    الحياه
    -0.45
    POSITIVE LOGITS
     look
    1.53
    look
    1.25
     Look
    1.23
    Look
    1.22
     LOOK
    1.20
     looked
    1.13
    LOOK
    1.12
     compare
    1.09
    looked
    0.99
     glance
    0.98
    Act Density 0.192%

    No Known Activations