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

    Neuronpedia

    INDEX
    Explanations

    references to specific individual names

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.56
    rage
    -0.55
     faſt
    -0.54
     Monfieur
    -0.54
     Jacobian
    -0.53
     maximization
    -0.52
     Anita
    -0.52
     noft
    -0.51
     Pernambuco
    -0.51
     Procedural
    -0.51
    POSITIVE LOGITS
     Jung
    2.20
    Jung
    2.00
    nikov
    1.88
    jung
    1.84
     jung
    1.34
     Jong
    1.11
    nikova
    0.95
    Jong
    0.91
     Jeong
    0.76
    niko
    0.75
    Act Density 0.001%

    No Known Activations