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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support, collaboration, and opportunities for engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uÄį
    -0.14
    Ю
    -0.14
     Commun
    -0.14
    åħ
    -0.14
    ehler
    -0.14
    onders
    -0.14
    aths
    -0.13
    å±
    -0.13
    ighth
    -0.13
    ajo
    -0.13
    POSITIVE LOGITS
    dik
    0.15
    achuset
    0.15
    ÑĮÑı
    0.14
    greens
    0.14
    ugin
    0.14
     ourselves
    0.14
    andro
    0.14
     Dud
    0.14
    SGlobal
    0.14
    conti
    0.14
    Act Density 0.210%

    No Known Activations