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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or governmental terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to various forms of development and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.83
    ortium
    -0.81
    odan
    -0.80
    hov
    -0.80
    llan
    -0.79
    gerald
    -0.77
    lda
    -0.75
    Newsletter
    -0.75
    sonian
    -0.74
    yi
    -0.74
    POSITIVE LOGITS
    ized
    1.56
    ization
    1.51
    izing
    1.46
    ised
    1.35
    ists
    1.28
    ities
    1.28
    ism
    1.26
    ize
    1.26
    izations
    1.21
    izes
    1.21
    Act Density 0.102%

    No Known Activations