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

    Neuronpedia

    INDEX
    Explanations

    terms related to data centers

    oai_token-act-pair · gpt-3.5-turbo

    words related to data and computing technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.69
     contr
    -0.62
     detector
    -0.61
     intention
    -0.61
     editors
    -0.58
    ||||
    -0.57
     altering
    -0.56
    Collins
    -0.56
     unders
    -0.55
     poles
    -0.55
    POSITIVE LOGITS
    henko
    1.35
    urrency
    1.35
    ulture
    1.29
    entric
    1.27
    orpor
    1.22
    urrent
    1.20
    ategory
    1.20
    ontent
    1.18
    ourt
    1.18
    ourse
    1.17
    Act Density 0.064%

    No Known Activations