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

    Neuronpedia

    INDEX
    Explanations

    references to political controversies and the impact of governmental decisions on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.64
     intersper
    -1.03
    
    -0.93
    /***
    -0.89
     shenan
    -0.86
    ⓧ
    -0.83
     endeavoured
    -0.81
     chanced
    -0.80
     incarcer
    -0.79
     endeavouring
    -0.78
    POSITIVE LOGITS
     flé
    0.87
     affez
    0.85
     sentier
    0.83
     déplo
    0.81
     fleuve
    0.81
     Gnaden
    0.80
     itinéraire
    0.80
     ibi
    0.80
     epoca
    0.80
     cioc
    0.79
    Act Density 1.212%

    No Known Activations