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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fal
    -0.15
    oje
    -0.14
    bjerg
    -0.14
    민êµŃ
    -0.14
     blanket
    -0.14
    apan
    -0.14
    oger
    -0.14
    onth
    -0.14
    oader
    -0.13
    iverse
    -0.13
    POSITIVE LOGITS
    ipel
    0.17
    roma
    0.17
    itect
    0.16
    -transitional
    0.15
    ayers
    0.14
    steder
    0.14
    silent
    0.14
    Ī
    0.14
    /arch
    0.14
    िण
    0.14
    Act Density 0.017%

    No Known Activations