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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uc
    -0.17
    mos
    -0.16
    unc
    -0.15
    reu
    -0.14
     Rolled
    -0.14
    atie
    -0.14
    cooked
    -0.14
    Threads
    -0.14
     Wo
    -0.13
    пов
    -0.13
    POSITIVE LOGITS
     Rosenstein
    0.18
    finity
    0.15
    ãĥ©ãĤ¯
    0.15
     oppos
    0.14
    :Register
    0.14
    getState
    0.14
    ynch
    0.14
    canf
    0.14
    bane
    0.14
     antioxid
    0.14
    Act Density 0.029%

    No Known Activations