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

    Neuronpedia

    INDEX
    Explanations

    references to pollution and poetic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.08
    GIVEREF
    -0.87
    WebVitals
    -0.85
     ")";
    -0.82
     doInBackground
    -0.81
    chenkt
    -0.78
    例句
    -0.77
    ImageContext
    -0.77
     kyr
    -0.76
    ]';
    -0.74
    POSITIVE LOGITS
     Po
    1.17
     Popov
    1.07
     Poole
    1.06
    Po
    1.05
     Pohl
    1.04
    po
    1.03
     Pollard
    1.01
     po
    0.99
     Pola
    0.98
     Pod
    0.97
    Act Density 0.210%

    No Known Activations