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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "New" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.17
    urgy
    -0.17
    utations
    -0.15
    ulant
    -0.15
    apolis
    -0.15
    ute
    -0.15
    AppBundle
    -0.14
    æŃ©
    -0.14
    ylv
    -0.14
    lopedia
    -0.14
    POSITIVE LOGITS
     Delhi
    0.26
    Del
    0.25
     del
    0.21
    del
    0.20
     DEL
    0.20
    DEL
    0.19
    _del
    0.18
    -del
    0.18
    chw
    0.18
     Zealand
    0.17
    Act Density 0.016%

    No Known Activations