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

    Neuronpedia

    INDEX
    Explanations

    words that denote high regard or affection towards individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToProps
    -0.17
    roadcast
    -0.15
    Ĺ
    -0.15
    etty
    -0.15
    dialogs
    -0.15
    redits
    -0.15
    digest
    -0.15
    #End
    -0.14
    ourcem
    -0.14
    898
    -0.14
    POSITIVE LOGITS
    boot
    0.15
    mys
    0.14
    ä¼ı
    0.14
    edges
    0.14
    eq
    0.13
    ÏĦοÏį
    0.13
     amongst
    0.13
     Viktor
    0.13
    avn
    0.13
    ens
    0.13
    Act Density 0.181%

    No Known Activations