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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to writing and summarizing content concisely

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     detailed
    -0.14
     gradual
    -0.13
    åŁº
    -0.13
     buffering
    -0.13
    orough
    -0.13
    fo
    -0.13
    ож
    -0.13
    slow
    -0.13
    pez
    -0.13
     Nit
    -0.13
    POSITIVE LOGITS
     brief
    0.30
     quick
    0.28
     short
    0.26
    SHORT
    0.26
     shorter
    0.26
    brief
    0.25
     Brief
    0.25
     SHORT
    0.24
     elevator
    0.24
    Brief
    0.23
    Act Density 0.145%

    No Known Activations