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

    Neuronpedia

    INDEX
    Explanations

    instances of characters sitting or moving to a seated position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibase
    -0.16
    æĪ¸
    -0.15
    .grp
    -0.15
    nio
    -0.15
    aser
    -0.15
    asers
    -0.15
    icode
    -0.14
    baz
    -0.14
    ido
    -0.14
    rgan
    -0.13
    POSITIVE LOGITS
     seats
    0.43
     seat
    0.40
     chairs
    0.38
     chair
    0.35
    -seat
    0.34
    seat
    0.34
    åĿIJ
    0.33
    æ¤ħ
    0.33
     Chairs
    0.33
    chair
    0.33
    Act Density 0.164%

    No Known Activations