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

    Neuronpedia

    INDEX
    Explanations

    terms related to geographical features, specifically deserts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.81
    OPA
    -0.79
    soType
    -0.77
    Reviewer
    -0.75
    ttle
    -0.72
    yright
    -0.71
    thood
    -0.68
    colo
    -0.66
    LM
    -0.65
    nder
    -0.65
    POSITIVE LOGITS
     sands
    1.03
    ification
    0.95
     tort
    0.90
     dwell
    0.90
    ashtra
    0.85
     wasteland
    0.80
     desert
    0.80
    urous
    0.80
     island
    0.79
     outpost
    0.79
    Act Density 0.021%

    No Known Activations