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

    Neuronpedia

    INDEX
    Explanations

    references to dental care or dental issues

    oai_token-act-pair · gpt-3.5-turbo

    references to teeth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.77
    arters
    -0.77
    ukong
    -0.75
    thumbnails
    -0.73
     Alic
    -0.71
    aird
    -0.71
     Archdemon
    -0.70
     Santos
    -0.69
    ISS
    -0.68
     Sisters
    -0.67
    POSITIVE LOGITS
     teeth
    1.24
    bone
    1.03
    paste
    1.02
     tooth
    0.96
     cavity
    0.94
    bite
    0.94
    brush
    0.93
     braces
    0.93
     dent
    0.91
     clen
    0.91
    Act Density 0.014%

    No Known Activations