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

    Neuronpedia

    INDEX
    Explanations

    concepts related to excessiveness or imbalance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exus
    -0.18
    omu
    -0.14
    stoff
    -0.14
    orthand
    -0.14
    cess
    -0.14
    oug
    -0.14
    ikal
    -0.14
    oku
    -0.14
     Cot
    -0.13
    ekl
    -0.13
    POSITIVE LOGITS
    /to
    0.19
     TOO
    0.19
    Too
    0.19
     Too
    0.18
     reliance
    0.17
    -too
    0.17
     too
    0.16
    ãģĻãģİ
    0.16
    too
    0.16
    ãĥ¼ãĥī
    0.16
    Act Density 0.066%

    No Known Activations