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

    Neuronpedia

    INDEX
    Explanations

    visual representations or images within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.19
     purpoſe
    -1.10
     houſe
    -1.06
     myſelf
    -1.04
     leaſt
    -1.00
     ſtate
    -0.98
     ſtre
    -0.98
     greateſt
    -0.97
     Monfieur
    -0.95
     themſelves
    -0.94
    POSITIVE LOGITS
     ExecuteAsync
    0.52
     N
    0.51
    onema
    0.50
    ParseTree
    0.50
     prakti
    0.49
     (
    0.48
     acceptez
    0.48
    RegressionTest
    0.48
     S
    0.45
    alanta
    0.45
    Act Density 0.014%

    No Known Activations