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

    Neuronpedia

    INDEX
    Explanations

    references to the English language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -0.71
    verwijspagina
    -0.71
     ModelExpression
    -0.70
    wezig
    -0.70
     censi
    -0.70
     propOrder
    -0.69
    NameInMap
    -0.67
     ―――――
    -0.66
     bezeichneter
    -0.66
    ADVERTISEMENT
    -0.66
    POSITIVE LOGITS
    en
    4.07
    EN
    2.56
    En
    2.24
     En
    1.98
     en
    1.90
     EN
    1.63
    enic
    1.41
    enha
    1.36
    enb
    1.33
    enin
    1.31
    Act Density 0.058%

    No Known Activations