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

    Neuronpedia

    INDEX
    Explanations

    actions related to causing harm or exerting control over others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal activities and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.62
    nai
    -0.61
    ftime
    -0.59
    hua
    -0.59
    nen
    -0.57
    atic
    -0.56
    icz
    -0.55
    onte
    -0.54
    ukong
    -0.53
     Accessed
    -0.53
    POSITIVE LOGITS
     them
    2.36
     THEM
    1.95
    them
    1.87
     Them
    1.72
     ones
    1.65
     theirs
    1.54
    they
    1.19
     those
    1.18
    They
    1.17
     hers
    1.09
    Act Density 2.114%

    No Known Activations