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

    Neuronpedia

    INDEX
    Explanations

    references to Oxford University and its associated publications or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Oxford institutions and publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tifact
    -0.47
    expandindo
    -0.47
     Theron
    -0.44
    InMillis
    -0.43
    tagext
    -0.43
    ьаж
    -0.43
     iload
    -0.42
     bVar
    -0.42
    Jim
    -0.42
     مشين
    -0.42
    POSITIVE LOGITS
     Oxford
    2.28
    Oxford
    2.11
     OXFORD
    1.80
     oxford
    1.76
    oxford
    1.53
     Cambridge
    0.98
     Oxfordshire
    0.88
     Ox
    0.85
    OX
    0.84
    Cambridge
    0.84
    Act Density 0.002%

    No Known Activations