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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.66
     sc
    -0.58
    ीय
    -0.57
     Jack
    -0.57
     bas
    -0.55
    -
    -0.55
    ों
    -0.54
     bu
    -0.51
     Ger
    -0.51
    ьев
    -0.51
    POSITIVE LOGITS
     chofe
    1.11
     Anſ
    1.11
     Houſe
    1.11
    paravant
    1.04
     cauſe
    1.03
     againſt
    1.03
     uſed
    1.01
     laſt
    1.01
     Eſ
    1.01
     uſe
    1.01
    Act Density 0.128%

    No Known Activations