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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions related to percentages and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mant
    -0.16
    ects
    -0.15
    ickt
    -0.14
    endimento
    -0.14
    reno
    -0.14
    imas
    -0.14
    inka
    -0.14
    گاÙĩ
    -0.14
     аж
    -0.13
     گاÙĩ
    -0.13
    POSITIVE LOGITS
    ania
    0.17
     per
    0.16
    ecast
    0.16
     åĮ
    0.14
     Rebel
    0.14
    firm
    0.14
    voje
    0.13
    å°
    0.13
     firm
    0.13
     wind
    0.13
    Act Density 0.143%

    No Known Activations