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

    Neuronpedia

    INDEX
    Explanations

    percentages and fractions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to statistical data or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sort
    -0.79
    Clar
    -0.75
    nah
    -0.74
    antic
    -0.73
    cule
    -0.72
    ENCE
    -0.71
    otion
    -0.69
    elf
    -0.69
    der
    -0.68
    ibe
    -0.67
    POSITIVE LOGITS
     respondents
    1.34
     households
    1.13
     Americans
    1.01
     those
    0.97
     surveyed
    0.95
     earners
    0.93
     applicants
    0.92
     eligible
    0.91
     Britons
    0.91
     participants
    0.90
    Act Density 0.110%

    No Known Activations