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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and data structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.16
     itſelf
    -1.12
     Efq
    -1.01
     himſelf
    -1.00
     Monfieur
    -1.00
     themſelves
    -0.96
    ſelf
    -0.94
     becauſe
    -0.94
    ſelves
    -0.90
     Majefty
    -0.90
    POSITIVE LOGITS
     g
    0.49
    </u>
    0.47
     tu
    0.42
     kel
    0.41
    kes
    0.40
    </b>
    0.40
    endorff
    0.40
    us
    0.40
    colate
    0.40
    inton
    0.40
    Act Density 0.124%

    No Known Activations