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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctors
    -0.15
    chaft
    -0.15
    aucoup
    -0.15
    sembly
    -0.15
    shine
    -0.14
    änder
    -0.14
     Ø´Ùħ
    -0.14
     Zaman
    -0.14
    licos
    -0.14
     Lantern
    -0.14
    POSITIVE LOGITS
    ibase
    0.17
    æĭ
    0.15
    eci
    0.15
     unp
    0.14
    edd
    0.14
    thane
    0.14
    preced
    0.14
    aran
    0.14
     Rolls
    0.14
    erd
    0.14
    Act Density 0.362%

    No Known Activations