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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and research topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jer
    -0.16
    isl
    -0.14
    agan
    -0.14
    еÑĢв
    -0.14
    ÑĥÑħ
    -0.14
    ç
    -0.13
     gangs
    -0.13
     watershed
    -0.13
     Bers
    -0.13
    loor
    -0.13
    POSITIVE LOGITS
    ãģ°ãģĭãĤĬ
    0.17
     accordingly
    0.15
    Ïģή
    0.15
    Coins
    0.14
    uno
    0.14
    oun
    0.14
    elyn
    0.14
    aný
    0.14
    addtogroup
    0.14
    ebo
    0.14
    Act Density 0.002%

    No Known Activations