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

    Neuronpedia

    INDEX
    Explanations

    statistics related to proportions or fractions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to proportions and ratios in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jan
    -0.67
    har
    -0.64
    edd
    -0.64
    gang
    -0.64
     emb
    -0.64
    rev
    -0.63
     ramp
    -0.59
    leans
    -0.59
    unct
    -0.58
     Hassan
    -0.58
    POSITIVE LOGITS
     respondents
    0.79
     Americans
    0.73
     (%
    0.72
     households
    0.69
    ones
    0.65
     overall
    0.65
     earners
    0.64
     (%)
    0.64
     cases
    0.64
    NPR
    0.64
    Act Density 0.067%

    No Known Activations