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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the "@" symbol, indicating references, citations, or email addresses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atan
    -0.15
    à¤Łà¤°
    -0.15
    TagName
    -0.14
     offsetof
    -0.14
     bä
    -0.14
    eyer
    -0.14
    allis
    -0.14
    ieran
    -0.13
    ipes
    -0.13
    aret
    -0.13
    POSITIVE LOGITS
    misc
    0.22
     misc
    0.21
     Misc
    0.16
    enu
    0.16
    ART
    0.15
    iou
    0.15
    tech
    0.15
    iento
    0.15
    pone
    0.14
     journal
    0.14
    Act Density 0.004%

    No Known Activations