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

    Neuronpedia

    INDEX
    Explanations

    references to deserts

    oai_token-act-pair · gpt-3.5-turbo

    references to desert environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.84
    soType
    -0.80
    ttle
    -0.77
    OPA
    -0.74
    yright
    -0.72
    Reviewer
    -0.70
    OA
    -0.69
    nder
    -0.69
    enny
    -0.67
    anchester
    -0.66
    POSITIVE LOGITS
     sands
    1.04
    ification
    0.92
     tort
    0.92
     dwell
    0.87
    ashtra
    0.84
     wasteland
    0.82
    urous
    0.80
     desert
    0.78
     island
    0.77
    ion
    0.76
    Act Density 0.029%

    No Known Activations