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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and ethical judgments

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

    legalconsequencewithouttherefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.89
     المعيارى
    -0.87
     resourceCulture
    -0.84
    <unused14>
    -0.83
    <unused68>
    -0.83
    <unused8>
    -0.83
    <unused41>
    -0.83
    Чыгана
    -0.83
    [@BOS@]
    -0.83
    <unused3>
    -0.83
    POSITIVE LOGITS
    2
    0.39
    #
    0.37
    ↵↵
    0.37
    1
    0.36
    A
    0.36
    OK
    0.34
    
    0.34
    I
    0.33
    you
    0.32
    ↵
    0.32
    Act Density 0.058%

    No Known Activations