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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to legal cases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Vuitton
    -0.84
    Autowired
    -0.81
    Muffin
    -0.74
    raulic
    -0.73
     Wigan
    -0.73
     presidencial
    -0.70
     fluence
    -0.70
    äumt
    -0.70
     Viana
    -0.70
    vét
    -0.70
    POSITIVE LOGITS
    Datuak
    0.73
    XmlAccessType
    0.71
     Kef
    0.71
     kra
    0.70
    createNewFile
    0.68
     Kra
    0.67
    awtextra
    0.67
     Kep
    0.66
     CMM
    0.66
    ɵ
    0.66
    Act Density 0.554%

    No Known Activations