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

    Neuronpedia

    INDEX
    Explanations

    specific percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    the word "of" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.72
    ollah
    -0.71
     caching
    -0.62
    dl
    -0.61
    sort
    -0.61
    archive
    -0.61
    hran
    -0.59
    edin
    -0.59
     reim
    -0.58
     aside
    -0.58
    POSITIVE LOGITS
    pees
    0.91
     respondents
    0.81
     GDP
    0.79
     households
    0.76
     surveyed
    0.72
    Initialized
    0.66
     applicants
    0.64
     variance
    0.63
    âķIJ
    0.63
     earners
    0.63
    Act Density 0.080%

    No Known Activations