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

    Neuronpedia

    INDEX
    Explanations

    names, acronyms, and important terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onia
    -0.14
    è²
    -0.14
     ton
    -0.14
    lyn
    -0.14
    ONS
    -0.14
    adar
    -0.14
    /node
    -0.13
    abar
    -0.13
    æĭ¼
    -0.13
    Rnd
    -0.13
    POSITIVE LOGITS
     flooding
    0.16
     Loch
    0.15
    gang
    0.15
    ovenant
    0.15
    Iso
    0.15
    olare
    0.15
    rim
    0.14
    ामन
    0.14
    ster
    0.14
    aksi
    0.14
    Act Density 0.030%

    No Known Activations