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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and accountability in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.51
    sto
    -0.49
     quite
    -0.48
    quite
    -0.44
     généralement
    -0.44
     pinulongan
    -0.43
    èvement
    -0.43
    Non
    -0.43
    igshid
    -0.43
     generalmente
    -0.43
    POSITIVE LOGITS
     Theſe
    0.88
     Diſ
    0.86
     Jefus
    0.86
     houſe
    0.80
     Efq
    0.79
     ſche
    0.78
     myſelf
    0.77
     whoſe
    0.77
     Houſe
    0.77
     Chriftian
    0.75
    Act Density 0.687%

    No Known Activations