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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.60
    ().__
    -0.56
     Litu
    -0.55
     nucle
    -0.54
     phép
    -0.50
    Бахар
    -0.50
    จึง
    -0.49
    mun
    -0.48
    衍
    -0.48
    BX
    -0.47
    POSITIVE LOGITS
     unknow
    1.07
     dunno
    1.06
     AssemblyCulture
    1.03
     unknown
    0.90
    不知道
    0.89
     Unknown
    0.88
    也不知道
    0.87
    我不知道
    0.87
    Dunno
    0.85
    Unknown
    0.83
    Act Density 0.146%

    No Known Activations