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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comprehension or understanding situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,,,,
    -0.72
    !:
    -0.66
     (?,
    -0.58
    ;
    -0.57
    :
    -0.57
     Solitaire
    -0.57
    ':
    -0.57
     âĵĺ
    -0.55
    é¾įåĸļ士
    -0.53
    :#
    -0.53
    POSITIVE LOGITS
    ?).
    0.85
    )).
    0.70
    %).
    0.68
    ¥µ
    0.65
    .).
    0.64
     earlier
    0.61
    ).
    0.61
    )."
    0.61
     ).
    0.60
    ).[
    0.58
    Act Density 2.235%

    No Known Activations