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

    Neuronpedia

    INDEX
    Explanations

    descriptive elements related to natural landscapes and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .snap
    -0.15
    .metro
    -0.13
    \Bridge
    -0.13
     леÑģ
    -0.13
    stad
    -0.13
     Forest
    -0.13
    ิà¸ķร
    -0.13
    λεκ
    -0.13
    msp
    -0.13
    ewood
    -0.13
    POSITIVE LOGITS
     desert
    0.49
     Desert
    0.46
     des
    0.37
     Sahara
    0.35
     sands
    0.33
     dessert
    0.32
     sand
    0.32
    -des
    0.31
     Dess
    0.30
    Des
    0.30
    Act Density 0.073%

    No Known Activations