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

    Neuronpedia

    INDEX
    Explanations

    phrases and punctuation related to quotations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subur
    -0.16
    qua
    -0.16
     odv
    -0.15
    strap
    -0.15
    erin
    -0.15
    ãĤ¦ãĤ§
    -0.15
    zÄħ
    -0.14
    âĢº
    -0.14
     TMPro
    -0.14
    едж
    -0.14
    POSITIVE LOGITS
    uld
    0.19
    oulos
    0.18
    owell
    0.15
    963
    0.15
    iÅŁti
    0.15
    eln
    0.14
    rell
    0.14
    oshi
    0.14
    igate
    0.14
    indsay
    0.14
    Act Density 0.211%

    No Known Activations