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

    Neuronpedia

    INDEX
    Explanations

    the word "mint"(s) in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to mint and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ake
    -0.74
    HUD
    -0.62
     IPM
    -0.60
     voc
    -0.60
     Airbnb
    -0.59
     behav
    -0.59
     extrap
    -0.58
     extradition
    -0.57
     Dropbox
    -0.57
     Dele
    -0.56
    POSITIVE LOGITS
     Seym
    1.40
    stones
    0.91
    erity
    0.88
    ed
    0.82
    uries
    0.82
    ing
    0.82
    ulously
    0.81
    eer
    0.80
    mint
    0.80
    marks
    0.79
    Act Density 0.027%

    No Known Activations