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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and formal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exampleModal
    -0.17
    unma
    -0.16
    ewise
    -0.15
    ãĥĨãĥ«
    -0.15
    itag
    -0.15
    eken
    -0.14
    emarks
    -0.14
     Tato
    -0.14
    gings
    -0.14
    udas
    -0.14
    POSITIVE LOGITS
    226
    0.15
    ampo
    0.14
    cho
    0.14
    ÑĤеÑĢн
    0.14
    ijn
    0.14
     trif
    0.14
     اÙĦظ
    0.14
    MLE
    0.13
    ensing
    0.13
     fab
    0.13
    Act Density 0.056%

    No Known Activations