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

    Neuronpedia

    INDEX
    Explanations

    nouns and related forms in a non-English language context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heath
    -0.15
    upert
    -0.15
     feet
    -0.15
     focal
    -0.15
     neatly
    -0.14
     straight
    -0.14
     fig
    -0.14
     dramatically
    -0.14
     ample
    -0.14
     vertically
    -0.14
    POSITIVE LOGITS
    yonel
    0.18
     вико
    0.18
    oks
    0.17
    kart
    0.17
    LOPT
    0.17
    GINE
    0.16
    krv
    0.16
    Å¡et
    0.16
    âĢ¦↵↵↵
    0.15
    anness
    0.15
    Act Density 0.024%

    No Known Activations