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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to description and articulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tanke
    -0.50
     quoque
    -0.50
    sant
    -0.49
    стори
    -0.49
     use
    -0.48
    maxcdn
    -0.48
    יסטור
    -0.47
     χρήση
    -0.47
    copus
    -0.47
    føl
    -0.46
    POSITIVE LOGITS
     depicting
    1.04
     describing
    1.03
     décrire
    1.02
     captures
    0.95
     depictions
    0.95
     conveys
    0.94
     depicts
    0.94
     describes
    0.92
     capturing
    0.90
     depiction
    0.90
    Act Density 0.477%

    No Known Activations