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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to complexity and simplicity characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
    Stand
    -0.15
    áÄį
    -0.15
    ensi
    -0.15
     Stand
    -0.14
    undos
    -0.14
    iets
    -0.14
    ensen
    -0.14
    kre
    -0.14
     Kelvin
    -0.14
    POSITIVE LOGITS
    ByExample
    0.16
    .transition
    0.16
     Meadows
    0.15
     Rosenstein
    0.15
    ny
    0.15
    orado
    0.15
    igne
    0.14
    illez
    0.14
    presso
    0.14
    éĩ
    0.14
    Act Density 0.336%

    No Known Activations