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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geopolitical relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.86
     ftate
    -0.82
     myſelf
    -0.78
     Monfieur
    -0.78
     fubject
    -0.76
    expandindo
    -0.76
     perfons
    -0.74
     pleaſure
    -0.72
     NSCoder
    -0.72
     Jefus
    -0.71
    POSITIVE LOGITS
     forgiving
    0.65
     forgiven
    0.57
     friendly
    0.56
     truce
    0.56
     goodwill
    0.53
     ändå
    0.52
     grud
    0.51
     accept
    0.51
     concili
    0.48
     benign
    0.48
    Act Density 0.453%

    No Known Activations