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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks, indicating direct speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkle
    -0.15
     âĢŀ
    -0.15
     «
    -0.15
    ãĢĮãģĤ
    -0.14
    partment
    -0.14
    ếp
    -0.14
    inkel
    -0.14
    894
    -0.13
    755
    -0.13
    andin
    -0.13
    POSITIVE LOGITS
    arak
    0.18
    ilim
    0.14
    ¦
    0.14
    amba
    0.14
    all
    0.13
    ENTS
    0.13
    {'
    0.13
    ob
    0.13
    illon
    0.13
    ammer
    0.13
    Act Density 0.705%

    No Known Activations