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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences requesting feedback or information

    oai_token-act-pair · gpt-3.5-turbo

    requests for feedback or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.95
    phrine
    -0.83
    interstitial
    -0.73
    orie
    -0.67
    aution
    -0.67
    erva
    -0.65
    ĪĴ
    -0.65
    ŃĶ
    -0.62
    otion
    -0.62
    conservancy
    -0.62
    POSITIVE LOGITS
    lege
    0.96
    ledged
    0.95
    ledge
    0.93
     how
    0.87
    yll
    0.75
    afer
    0.75
     HOW
    0.75
     ABOUT
    0.72
    Õ
    0.72
    к
    0.72
    Act Density 0.055%

    No Known Activations