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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or bureaucratic processes

    oai_token-act-pair · gpt-3.5-turbo

    references to "matter" in various contexts, indicating issues or topics of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.88
    ARP
    -0.78
    NetMessage
    -0.77
    OWN
    -0.73
    cki
    -0.72
    ©¶æ
    -0.71
    elta
    -0.71
    ãĥ¼ãĥĨ
    -0.69
    ESCO
    -0.68
    olkien
    -0.68
    POSITIVE LOGITS
    ional
    0.89
    enance
    0.88
     pertaining
    0.84
    forward
    0.80
     relating
    0.78
     surrounding
    0.78
     particulars
    0.74
    relevant
    0.73
    icular
    0.72
     concerning
    0.72
    Act Density 0.027%

    No Known Activations