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

    Neuronpedia

    INDEX
    Explanations

    elements related to writing or composing documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arges
    -0.14
     amort
    -0.13
    Cast
    -0.13
    ãģ¡ãĤī
    -0.13
    ãĥ«ãĥĪ
    -0.13
     DRV
    -0.13
    bildung
    -0.13
    FU
    -0.13
    ADM
    -0.13
    bery
    -0.13
    POSITIVE LOGITS
     description
    0.14
    书记
    0.14
    _Description
    0.14
     æij
    0.14
     antenn
    0.14
    _rng
    0.14
    mie
    0.13
     Lace
    0.13
    244
    0.13
     dept
    0.13
    Act Density 0.049%

    No Known Activations