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

    Neuronpedia

    INDEX
    Explanations

    code snippets and structured data definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.52
    istream
    -0.51
     and
    -0.51
     (
    -0.48
     +
    -0.48
     mobil
    -0.47
     of
    -0.46
    modelBuilder
    -0.46
     '
    -0.45
     Y
    -0.45
    POSITIVE LOGITS
     beſt
    0.85
    expandindo
    0.80
     purpoſe
    0.78
     ainfi
    0.76
     leaſt
    0.76
     שוליים
    0.76
    $")
    0.76
     whoſe
    0.74
     kasarigan
    0.74
     greateſt
    0.73
    Act Density 0.094%

    No Known Activations