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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical lemmas and theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Doherty
    -0.71
     Malone
    -0.64
    édric
    -0.62
     Regency
    -0.61
    alium
    -0.60
     Larkin
    -0.60
    efty
    -0.60
    ed
    -0.58
     Rangers
    -0.58
     Richter
    -0.58
    POSITIVE LOGITS
    Lem
    1.02
     lem
    0.93
    lem
    0.93
     Monfieur
    0.91
     Alem
    0.90
    Klem
    0.89
     Lem
    0.86
    DockStyle
    0.86
    LEM
    0.84
     Clem
    0.81
    Act Density 0.005%

    No Known Activations