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

    Neuronpedia

    INDEX
    Explanations

    references to software versions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jefus
    -0.99
     Anſ
    -0.96
     versions
    -0.95
     Majefty
    -0.94
     faſt
    -0.94
     myſelf
    -0.91
     itſelf
    -0.90
     Monfieur
    -0.90
     fhort
    -0.89
     raiſ
    -0.88
    POSITIVE LOGITS
     im
    0.61
     שוליים
    0.53
    RegressionTest
    0.53
    ↵↵
    0.48
    ilíbrio
    0.47
    ↵
    0.47
    FOOTNOTES
    0.46
     cần
    0.45
     estamos
    0.45
    慧
    0.44
    Act Density 0.011%

    No Known Activations