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

    Neuronpedia

    INDEX
    Explanations

    references to entrances and openings in structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.54
    JNIEnv
    -0.47
    <thead>
    -0.47
     désolés
    -0.47
    σθαι
    -0.44
     co
    -0.44
    ритори
    -0.44
    onomía
    -0.43
    cabul
    -0.43
    vdots
    -0.43
    POSITIVE LOGITS
     door
    1.56
     gate
    1.53
     gates
    1.53
     doors
    1.49
     Gate
    1.46
     Door
    1.38
    door
    1.38
     doorway
    1.38
     doorways
    1.36
     DOOR
    1.36
    Act Density 0.285%

    No Known Activations