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

    Neuronpedia

    INDEX
    Explanations

    references to rights and legal protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vand
    -0.16
    687
    -0.16
    инÑĭ
    -0.15
    incare
    -0.15
    hof
    -0.15
    ัà¸ķ
    -0.15
    aire
    -0.14
    lok
    -0.14
     state
    -0.14
     such
    -0.14
    POSITIVE LOGITS
    fully
    0.18
    evenodd
    0.16
    λλι
    0.15
    rong
    0.15
    urm
    0.15
    -www
    0.14
    ëĵł
    0.14
    몬
    0.14
    posables
    0.14
    vro
    0.14
    Act Density 0.003%

    No Known Activations