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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values or terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.97
    Geplaatst
    -0.89
     Theſe
    -0.89
     Majefty
    -0.87
     myſelf
    -0.83
     ſtate
    -0.81
     houſe
    -0.81
     himſelf
    -0.79
     Houſe
    -0.79
     ―――――
    -0.78
    POSITIVE LOGITS
     M
    0.55
     “
    0.52
    CodedInputStream
    0.50
     her
    0.50
     R
    0.48
    #
    0.48
    новништво
    0.46
    </h3>
    0.46
     #
    0.46
     co
    0.44
    Act Density 0.022%

    No Known Activations