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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve inquiry or conditions related to what is being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.69
     newBuilder
    -0.65
     fubject
    -0.62
     greateſt
    -0.61
    škin
    -0.61
     houſe
    -0.60
     pleaf
    -0.60
     Eſ
    -0.58
     ſtate
    -0.57
     bezeichneter
    -0.57
    POSITIVE LOGITS
     что
    1.20
     що
    0.98
     że
    0.98
     že
    0.96
     когда
    0.93
     które
    0.92
     который
    0.90
     który
    0.87
     которые
    0.84
     jakie
    0.84
    Act Density 0.045%

    No Known Activations