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

    Neuronpedia

    INDEX
    Explanations

    tables and their summaries in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arma
    -0.17
     elephant
    -0.15
     Magn
    -0.14
    anko
    -0.14
     aggregate
    -0.14
    ollapse
    -0.14
     ed
    -0.14
     faithful
    -0.14
     bo
    -0.13
     Tom
    -0.13
    POSITIVE LOGITS
    asic
    0.19
    .gdx
    0.16
    ercul
    0.15
    Verdana
    0.15
    craper
    0.15
    okrat
    0.14
    rik
    0.14
     createSelector
    0.14
    AVIS
    0.14
    uxt
    0.14
    Act Density 0.030%

    No Known Activations