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

    Neuronpedia

    INDEX
    Explanations

    references to quotas and restrictions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WithEvents
    -0.18
    _WM
    -0.16
    rijk
    -0.16
    cant
    -0.15
    ãĤ·ãĤ¢
    -0.15
    ARAM
    -0.14
    WithURL
    -0.14
    ecko
    -0.14
    eniz
    -0.14
    åĽ½ãģ®
    -0.14
    POSITIVE LOGITS
    ilers
    0.17
    ady
    0.17
    HEME
    0.16
    ted
    0.16
    ey
    0.16
     da
    0.15
    ting
    0.14
    inous
    0.14
    uthor
    0.14
    pte
    0.14
    Act Density 0.024%

    No Known Activations