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

    Neuronpedia

    INDEX
    Explanations

    legal or official terms and issues

    oai_token-act-pair · gpt-3.5-turbo

    references to specific issues or topics under discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.79
    ARP
    -0.74
    olkien
    -0.73
    ingo
    -0.72
    inka
    -0.70
    ãĥ³ãĤ¸
    -0.68
    ARK
    -0.67
    eatures
    -0.66
     ceiling
    -0.64
    aimon
    -0.64
    POSITIVE LOGITS
    ional
    0.97
     matters
    0.90
     Matter
    0.89
    enance
    0.88
     matter
    0.84
    matter
    0.84
    mong
    0.78
    ially
    0.75
     Matters
    0.70
    rooms
    0.70
    Act Density 0.021%

    No Known Activations