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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or qualifiers in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.81
    RegressionTest
    -0.72
    \{\\
    -0.62
    λέον
    -0.61
     rowspan
    -0.58
     للمعارف
    -0.58
     AssemblyCulture
    -0.55
    exus
    -0.55
    例句
    -0.54
     utafitiHapana
    -0.52
    POSITIVE LOGITS
     only
    1.00
     лишь
    0.84
     Only
    0.84
    only
    0.83
    Only
    0.81
     ONLY
    0.78
    ONLY
    0.73
     только
    0.71
    只会
    0.70
     uniquement
    0.70
    Act Density 0.270%

    No Known Activations