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

    Neuronpedia

    INDEX
    Explanations

    numeric values and specific details about accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -0.17
    inde
    -0.16
    assen
    -0.15
    atsapp
    -0.15
     vain
    -0.15
     Cookbook
    -0.15
    arden
    -0.15
     Native
    -0.14
    ollapse
    -0.14
    inters
    -0.13
    POSITIVE LOGITS
    yscale
    0.18
     overlaps
    0.15
     жиÑĢ
    0.14
     законодав
    0.14
    filesize
    0.14
    endra
    0.13
    à¸Ńาร
    0.13
    iston
    0.13
    bonus
    0.13
     Pound
    0.13
    Act Density 0.117%

    No Known Activations