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

    Neuronpedia

    INDEX
    Explanations

    numerical data and comparisons related to performance metrics or approval ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anse
    -0.16
    mayan
    -0.15
    алог
    -0.15
    aft
    -0.15
    eming
    -0.14
    aan
    -0.14
    ongoose
    -0.14
     Wikispecies
    -0.14
    otland
    -0.14
    äd
    -0.14
    POSITIVE LOGITS
     Shir
    0.17
     Aleppo
    0.15
     deleg
    0.15
    Jvm
    0.14
    its
    0.14
     pap
    0.14
    rozen
    0.14
    imilar
    0.13
     ãģ¾
    0.13
    roke
    0.13
    Act Density 0.327%

    No Known Activations