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

    Neuronpedia

    INDEX
    Explanations

    references to data sets and models related to machine learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conscience
    -0.15
    che
    -0.15
    -guide
    -0.15
    ipa
    -0.14
     cheat
    -0.14
    loop
    -0.14
    ahoo
    -0.14
    CEE
    -0.14
    asc
    -0.13
    abit
    -0.13
    POSITIVE LOGITS
    ebe
    0.16
    hlen
    0.15
    598
    0.14
    íĢ
    0.14
    allen
    0.14
    .Clock
    0.14
    gil
    0.13
    ãĥ¼ãĥijãĥ¼
    0.13
     tabletop
    0.13
    ITIES
    0.13
    Act Density 0.182%

    No Known Activations