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

    Neuronpedia

    INDEX
    Explanations

    interactions and relationships between characters in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Synopsis
    -0.15
    éĽĨä¸Ń
    -0.14
    REA
    -0.14
     raining
    -0.14
     Landing
    -0.14
    гаÑĢ
    -0.14
    concert
    -0.13
    escal
    -0.13
     foc
    -0.13
    arih
    -0.13
    POSITIVE LOGITS
     amb
    0.34
     sa
    0.33
     walks
    0.29
     walk
    0.29
     lim
    0.28
     walking
    0.27
    walk
    0.27
     tr
    0.27
     tra
    0.27
     walked
    0.26
    Act Density 0.358%

    No Known Activations