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

    Neuronpedia

    INDEX
    Explanations

    phrases related to national parks

    oai_token-act-pair · gpt-3.5-turbo

    references to national parks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lip
    -0.78
    Interstitial
    -0.76
    jad
    -0.76
    poll
    -0.76
    ulative
    -0.75
    Bey
    -0.66
     ILCS
    -0.66
    omo
    -0.65
     RPM
    -0.65
    iating
    -0.64
    POSITIVE LOGITS
    conservancy
    0.95
     Conservation
    0.94
     Sanctuary
    0.93
     Refuge
    0.90
     wildlife
    0.90
     Wilderness
    0.88
     Wildlife
    0.81
    querque
    0.81
     refuge
    0.79
     Authority
    0.79
    Act Density 0.065%

    No Known Activations