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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives expressing enjoyment or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuilderInterface
    -0.16
    endar
    -0.15
    /dat
    -0.15
    agem
    -0.14
    FACE
    -0.14
    agt
    -0.14
    úi
    -0.14
     Dro
    -0.14
     Clara
    -0.14
    ä¿
    -0.13
    POSITIVE LOGITS
     Kral
    0.16
    okit
    0.15
    -Smith
    0.15
    kovi
    0.15
     Král
    0.14
     Gund
    0.14
    elpers
    0.14
    ERC
    0.14
    489
    0.13
     HomeController
    0.13
    Act Density 0.216%

    No Known Activations