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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the need for citations or references

    oai_token-act-pair · gpt-3.5-turbo

    references to citations or sources in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.72
    inav
    -0.70
    milo
    -0.68
    deals
    -0.65
    graduate
    -0.64
    Jet
    -0.62
    wives
    -0.61
    manship
    -0.61
    quer
    -0.60
    ratulations
    -0.59
    POSITIVE LOGITS
     needed
    0.95
    =]
    0.87
     omitted
    0.85
    ?]
    0.78
    needed
    0.77
    ][
    0.76
     redacted
    0.72
    ]"
    0.72
     requested
    0.71
    needs
    0.70
    Act Density 0.042%

    No Known Activations