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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions and statistics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mtrl
    -0.88
    BlockPos
    -0.74
    Tikang
    -0.72
    Tembelea
    -0.71
    JAXB
    -0.69
    XmlEnum
    -0.68
    oredCriteria
    -0.68
     albicans
    -0.66
     beginnetje
    -0.66
    afficheront
    -0.64
    POSITIVE LOGITS
     many
    0.74
    Cuánt
    0.72
     fewer
    0.71
     dozens
    0.69
     lots
    0.67
     more
    0.67
     thousands
    0.66
     hundreds
    0.66
     nearly
    0.66
     dozen
    0.64
    Act Density 0.309%

    No Known Activations