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

    Neuronpedia

    INDEX
    Explanations

    specific words related to certain industries or fields, such as "ticket", "card", "loan", and "table"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to items or aspects that are objects or concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.95
    creen
    -0.84
    hip
    -0.82
    krit
    -0.79
    ensitive
    -0.76
    ync
    -0.74
    oup
    -0.73
    arnaev
    -0.72
    paces
    -0.72
    lip
    -0.71
    POSITIVE LOGITS
     count
    0.89
    holders
    0.88
     counts
    0.84
    holder
    0.83
     holders
    0.75
     allele
    0.75
    fleet
    0.73
    Names
    0.73
    Count
    0.72
     heterogeneity
    0.71
    Act Density 0.586%

    No Known Activations