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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions and interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GMENT
    -0.61
    fils
    -0.56
    Décès
    -0.55
    anstalt
    -0.55
    MSM
    -0.54
    nitts
    -0.53
     Dalio
    -0.52
    ))[
    -0.52
    eleste
    -0.52
     paramString
    -0.52
    POSITIVE LOGITS
     uſed
    0.67
     ранее
    0.59
     previously
    0.59
     laſt
    0.56
     already
    0.55
     recently
    0.55
     uſe
    0.53
     ſtill
    0.51
     ſte
    0.51
     ſtand
    0.49
    Act Density 0.455%

    No Known Activations