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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diverse collections or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adena
    -0.15
    riel
    -0.15
     Ulus
    -0.15
    aja
    -0.15
     repro
    -0.14
    linger
    -0.14
    ách
    -0.14
    ajas
    -0.14
    بÙĪب
    -0.14
    Ã
    -0.14
    POSITIVE LOGITS
    gre
    0.17
    ipse
    0.16
    gp
    0.14
    راÙĨ
    0.14
    823
    0.14
    SingleNode
    0.14
    -quarters
    0.14
    رد
    0.14
    815
    0.13
     Hann
    0.13
    Act Density 0.016%

    No Known Activations