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

    Neuronpedia

    INDEX
    Explanations

    indicators of comparison or gradation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Up
    -0.15
    Up
    -0.15
    alet
    -0.14
    cce
    -0.14
    leitung
    -0.14
    unal
    -0.13
    รà¸ĵ
    -0.13
    culate
    -0.13
    arah
    -0.13
    alie
    -0.13
    POSITIVE LOGITS
     over
    0.42
     under
    0.41
     less
    0.29
    under
    0.28
     fewer
    0.26
    _under
    0.26
     shy
    0.26
    -under
    0.24
     dÆ°á»Ľi
    0.24
     below
    0.24
    Act Density 0.023%

    No Known Activations