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

    Neuronpedia

    INDEX
    Explanations

    statistical data related to specific demographic groups and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beziehungs
    -0.93
    <em>
    -0.72
     például
    -0.60
     například
    -0.57
     cinquante
    -0.54
     
    -0.54
     beispielsweise
    -0.53
    <i>
    -0.53
    <sup>
    -0.52
     eighty
    -0.52
    POSITIVE LOGITS
     
    1.33
     ppl
    1.26
    1.20
     govt
    1.18
     -->
    1.02
     --->
    0.98
     ->
    0.98
     yg
    0.95
     gov
    0.94
     Govt
    0.93
    Act Density 0.728%

    No Known Activations