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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KeyType
    -0.16
    ptions
    -0.14
    LEGRO
    -0.14
     reserve
    -0.14
    ovan
    -0.14
     statist
    -0.14
    zl
    -0.14
    æī¶
    -0.13
    ccount
    -0.13
    onder
    -0.13
    POSITIVE LOGITS
    uire
    0.15
    space
    0.15
    safe
    0.15
    -transitional
    0.14
    æĻ
    0.14
    elon
    0.14
    /arch
    0.14
    itect
    0.14
    bishop
    0.14
    uÃŃ
    0.14
    Act Density 0.022%

    No Known Activations