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

    Neuronpedia

    INDEX
    Explanations

    references to the word "our" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yf
    -0.56
     Dijk
    -0.55
    jine
    -0.54
    arynx
    -0.54
    ency
    -0.53
    yym
    -0.52
     Dimen
    -0.51
    childs
    -0.51
    ibb
    -0.51
     Fayette
    -0.51
    POSITIVE LOGITS
     our
    0.89
    Our
    0.86
     Our
    0.84
     våre
    0.83
     våra
    0.83
     OUR
    0.80
     meille
    0.78
     nuestra
    0.74
     nuestros
    0.72
     we
    0.71
    Act Density 0.085%

    No Known Activations