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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.16
    ondheim
    -0.14
    osal
    -0.14
    oso
    -0.14
    ssel
    -0.14
    od
    -0.14
    wards
    -0.14
    ught
    -0.14
    oun
    -0.14
    auc
    -0.13
    POSITIVE LOGITS
    ileged
    0.16
    æĪ
    0.16
    UGE
    0.15
    abbo
    0.15
     Howe
    0.14
    rais
    0.14
    eniable
    0.13
    illions
    0.13
    pcm
    0.13
    .scalablytyped
    0.13
    Act Density 0.035%

    No Known Activations