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

    Neuronpedia

    INDEX
    Explanations

    words associated with beginnings, initiatives, and actions taken by individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eton
    -0.16
    eee
    -0.16
     Ulus
    -0.15
    ea
    -0.15
    thal
    -0.14
    luž
    -0.14
    endors
    -0.14
     Around
    -0.14
     DoÄŁ
    -0.14
    ystate
    -0.14
    POSITIVE LOGITS
    éŁ
    0.15
    ware
    0.15
    .configure
    0.15
     phá
    0.14
    è©
    0.14
    uhn
    0.14
    outil
    0.14
    tract
    0.14
    .circular
    0.13
    roken
    0.13
    Act Density 0.334%

    No Known Activations