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

    Neuronpedia

    INDEX
    Explanations

    references to universities and academic institutions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     and
    -0.56
    /
    -0.55
     C
    -0.52
     The
    -0.51
     [
    -0.50
     B
    -0.48
     where
    -0.48
    ↵↵
    -0.47
     (
    -0.47
     W
    -0.47
    POSITIVE LOGITS
     itſelf
    0.96
     myſelf
    0.89
    Datuak
    0.88
     themſelves
    0.84
     سكانية
    0.83
     Shakspeare
    0.81
     дописавши
    0.80
     himſelf
    0.80
     faſt
    0.80
    AccessorTable
    0.79
    Act Density 0.011%

    No Known Activations