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

    Neuronpedia

    INDEX
    Explanations

    references to contributions and contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibern
    -0.18
    stalk
    -0.17
    ัวร
    -0.15
    elves
    -0.15
    stag
    -0.15
    stav
    -0.14
    zeigt
    -0.14
    arro
    -0.14
    inged
    -0.14
    ucking
    -0.14
    POSITIVE LOGITS
    olare
    0.17
    Contrib
    0.15
    contrib
    0.15
    ìĪ
    0.14
     contrib
    0.13
     Craw
    0.13
    itar
    0.13
    awy
    0.13
    .fhir
    0.13
     Katz
    0.13
    Act Density 0.018%

    No Known Activations