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

    Neuronpedia

    INDEX
    Explanations

    references to geographical features, specifically mountains and hills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    庁
    -0.42
    teva
    -0.33
     AFL
    -0.31
    CHICAGO
    -0.31
    protocol
    -0.30
     Astra
    -0.30
    script
    -0.30
    ịp
    -0.30
    intent
    -0.29
    InteropServices
    -0.29
    POSITIVE LOGITS
     mountain
    1.60
    Mountain
    1.57
     Mountain
    1.57
     mountains
    1.53
    mountain
    1.51
     Mountains
    1.48
     MOUNTAIN
    1.45
    Mountains
    1.41
    mountains
    1.41
     montagne
    1.21
    Act Density 0.242%

    No Known Activations