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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to tracking and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eisenberg
    -1.10
    Annette
    -0.88
     déliv
    -0.87
     Bili
    -0.86
    +#+
    -0.85
    HomeAsUpEnabled
    -0.85
     élas
    -0.83
     Heilig
    -0.82
     mû
    -0.82
    tinyos
    -0.82
    POSITIVE LOGITS
     TRA
    1.29
     tra
    1.17
     Tra
    1.16
     Trapp
    1.13
    tra
    1.11
    Trax
    1.02
    Tra
    0.99
     TR
    0.95
    tray
    0.92
     traj
    0.91
    Act Density 0.176%

    No Known Activations