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

    Neuronpedia

    INDEX
    Explanations

    descriptors of places and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugi
    -0.15
     Jakarta
    -0.15
    desk
    -0.15
    architecture
    -0.15
    issors
    -0.14
     ÑĢиз
    -0.14
    zheimer
    -0.14
    edia
    -0.14
    æ¨
    -0.14
    èĬ¸
    -0.14
    POSITIVE LOGITS
     caravan
    0.43
     pitches
    0.40
     pitch
    0.36
     touring
    0.35
     camp
    0.34
     static
    0.33
     Static
    0.33
     Camping
    0.32
     Pitch
    0.32
    pitch
    0.32
    Act Density 0.011%

    No Known Activations