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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "matter" in phrases related to investigations and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific issue or topic being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARP
    -0.86
    NetMessage
    -0.82
    olkien
    -0.79
    cki
    -0.76
    KI
    -0.74
    ãĥ³ãĤ¸
    -0.73
    inka
    -0.72
    ingo
    -0.71
    ©¶æ
    -0.70
    eatures
    -0.66
    POSITIVE LOGITS
    ional
    1.00
    enance
    0.88
     matters
    0.85
    icular
    0.82
     pertaining
    0.81
     relating
    0.80
     matter
    0.78
    forth
    0.75
     involving
    0.75
    matter
    0.75
    Act Density 0.016%

    No Known Activations