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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating quantity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.62
    ΗΣ
    -0.62
    gonic
    -0.62
    SharedCtor
    -0.61
    fml
    -0.60
     Walkover
    -0.59
    참고
    -0.57
    JAXB
    -0.55
    typeorm
    -0.55
    swire
    -0.54
    POSITIVE LOGITS
     amount
    0.66
     fewer
    0.66
     few
    0.64
     more
    0.59
     hundreds
    0.58
     many
    0.58
     dozens
    0.57
     nearly
    0.56
     quantidade
    0.54
     cantidad
    0.54
    Act Density 0.525%

    No Known Activations