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

    Neuronpedia

    INDEX
    Explanations

    references to small or miniature entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umber
    -0.17
    icer
    -0.15
    imedia
    -0.15
     lumber
    -0.14
    thren
    -0.13
     Bunu
    -0.13
    stal
    -0.13
    uzzi
    -0.13
    iken
    -0.13
     Åŀu
    -0.13
    POSITIVE LOGITS
    /small
    0.37
    /tiny
    0.32
     smaller
    0.32
    -small
    0.32
     tiny
    0.32
     SMALL
    0.31
     small
    0.30
    -sized
    0.28
    small
    0.28
     nhá»ı
    0.28
    Act Density 0.430%

    No Known Activations