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

    Neuronpedia

    INDEX
    Explanations

    references to programming methods and functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -1.27
     myſelf
    -1.09
     whoſe
    -1.01
     itſelf
    -0.99
     himſelf
    -0.99
     Monfieur
    -0.99
     themſelves
    -0.98
    ſelf
    -0.94
     Jefus
    -0.94
     caufe
    -0.94
    POSITIVE LOGITS
    WithMany
    0.56
    defineProperty
    0.53
    zura
    0.51
     Auss
    0.51
    ${\
    0.50
     dual
    0.49
    SecretKey
    0.49
     Hoffmann
    0.48
     aspect
    0.48
    l
    0.48
    Act Density 0.017%

    No Known Activations