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

    Neuronpedia

    INDEX
    Explanations

    references to specific cities or capitals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    subcategory
    -0.16
    erk
    -0.16
    اÙģت
    -0.16
    -widgets
    -0.15
    enheim
    -0.14
     bÄĻd
    -0.14
    alars
    -0.14
    vor
    -0.14
    posables
    -0.14
    ElementException
    -0.13
    POSITIVE LOGITS
     premises
    0.15
    ãģıãĤĭ
    0.14
     struct
    0.14
     bullets
    0.14
    stru
    0.14
    otten
    0.14
    utta
    0.14
    illa
    0.14
    plotlib
    0.13
    probe
    0.13
    Act Density 0.011%

    No Known Activations