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

    Neuronpedia

    INDEX
    Explanations

    discussions about balance in various contexts, especially concerning power and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ballo
    -0.16
    hiba
    -0.16
     balloon
    -0.16
    lage
    -0.15
    lc
    -0.15
    ùi
    -0.15
    lus
    -0.15
    ÙħاÙĨÛĮ
    -0.15
    lings
    -0.14
     balcon
    -0.14
    POSITIVE LOGITS
     sheet
    0.36
     Sheet
    0.30
     sheets
    0.30
    -sheet
    0.29
    _sheet
    0.26
    Sheet
    0.25
     prec
    0.23
     Sheets
    0.22
    sheet
    0.22
     beam
    0.21
    Act Density 0.028%

    No Known Activations