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

    Neuronpedia

    INDEX
    Explanations

    terms related to alternating current (AC) and its properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.24
     faſt
    -1.09
    Portale
    -1.05
    )))));
    -1.04
     myſelf
    -1.04
     houſe
    -1.02
     Majefty
    -1.00
     stiefel
    -0.99
     themſelves
    -0.98
     Monfieur
    -0.98
    POSITIVE LOGITS
     AC
    1.26
    AC
    1.09
    lin
    0.79
     
    0.72
    s
    0.69
    ly
    0.68
     Po
    0.62
     film
    0.62
     Kar
    0.61
     lin
    0.61
    Act Density 0.011%

    No Known Activations