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

    Neuronpedia

    INDEX
    Explanations

    references to balance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙħاÙĨÛĮ
    -0.17
    hiba
    -0.15
    hey
    -0.15
    lage
    -0.15
    lc
    -0.15
    ÄĽn
    -0.15
    itespace
    -0.14
    lus
    -0.14
    zk
    -0.14
    ùi
    -0.14
    POSITIVE LOGITS
     sheet
    0.34
    -sheet
    0.28
     Sheet
    0.28
     sheets
    0.27
    _sheet
    0.24
    Sheet
    0.23
     prec
    0.23
     beam
    0.22
     scales
    0.21
    sheet
    0.21
    Act Density 0.029%

    No Known Activations