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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific conditions or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.47
     Seder
    -0.39
    lepiej
    -0.39
     getopt
    -0.39
    rafat
    -0.39
    频繁
    -0.38
     LSA
    -0.38
    stig
    -0.36
    그는
    -0.36
    autique
    -0.36
    POSITIVE LOGITS
     finally
    1.08
     Finally
    0.96
    Finally
    0.87
     FINALLY
    0.86
     Finalmente
    0.84
     наконец
    0.81
     finalmente
    0.80
    finally
    0.79
     eventually
    0.78
     lastly
    0.76
    Act Density 0.088%

    No Known Activations