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

    Neuronpedia

    INDEX
    Explanations

    words related to the act of shrinking or smallness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    łĢ
    -0.19
    cum
    -0.16
    AXB
    -0.15
    enn
    -0.15
    ennen
    -0.15
    ierre
    -0.14
    haar
    -0.14
    ibar
    -0.14
    oint
    -0.14
    aster
    -0.14
    POSITIVE LOGITS
     shr
    0.31
     Shr
    0.30
    shr
    0.26
    ubs
    0.22
    ugging
    0.21
    unk
    0.20
    inking
    0.19
    nutÃŃ
    0.18
    uti
    0.18
     shrinking
    0.17
    Act Density 0.012%

    No Known Activations