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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word 'under' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥªãĤ«
    -0.16
    ümÃ¼ÅŁ
    -0.16
    uno
    -0.16
     Wake
    -0.16
    ãĤ¦ãĥĪ
    -0.15
    bach
    -0.14
    iego
    -0.14
    RAL
    -0.14
     Walls
    -0.14
    sert
    -0.14
    POSITIVE LOGITS
    neath
    0.28
     covers
    0.24
     hood
    0.23
     layers
    0.23
    foot
    0.22
    hood
    0.20
     Covers
    0.20
    covers
    0.19
     Hood
    0.18
     microscope
    0.18
    Act Density 0.036%

    No Known Activations