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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating preservation or lack of change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consistency and preservation over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xy
    -0.67
    ueller
    -0.66
     McKenna
    -0.64
     Typhoon
    -0.62
    udic
    -0.61
    aph
    -0.61
    quickShipAvailable
    -0.59
    gging
    -0.59
    phony
    -0.59
     Xan
    -0.58
    POSITIVE LOGITS
     unchanged
    0.91
    iated
    0.80
    lihood
    0.79
    ledged
    0.78
     intact
    0.76
    aneously
    0.73
    vich
    0.69
    aneous
    0.67
    iate
    0.66
    cy
    0.64
    Act Density 0.042%

    No Known Activations