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

    Neuronpedia

    INDEX
    Explanations

    numerical data or statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lath
    -0.75
     Cain
    -0.74
     Guilford
    -0.73
     Balk
    -0.72
     McConnell
    -0.69
     kate
    -0.69
    Guil
    -0.66
     Leith
    -0.66
     McIn
    -0.64
     Lily
    -0.64
    POSITIVE LOGITS
     Humphries
    0.79
     Pies
    0.74
     Ramsey
    0.70
     Kondo
    0.69
     XXII
    0.68
     Bellamy
    0.68
     Herzog
    0.66
     Nanda
    0.66
     Shea
    0.65
     Tyson
    0.64
    Act Density 1.661%

    No Known Activations