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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate uncertainty or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     humaines
    -0.71
     humaine
    -0.68
     efficaces
    -0.65
     Drummond
    -0.62
     témoins
    -0.62
     humains
    -0.60
     umana
    -0.58
     spirituale
    -0.57
     camadas
    -0.57
     âgées
    -0.56
    POSITIVE LOGITS
     necessarily
    1.28
    necessarily
    1.08
    RectangleBorder
    0.94
    不一定
    0.91
     necessariamente
    0.86
     forcément
    0.83
     متعلقه
    0.82
     nécessairement
    0.82
    StoryboardSegue
    0.81
     necesariamente
    0.80
    Act Density 0.115%

    No Known Activations