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

    Neuronpedia

    INDEX
    Explanations

    numerical and legal citation references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rest
    -0.63
     rest
    -0.62
     colspan
    -0.59
    </em>
    -0.56
    <strong>
    -0.55
    <b>
    -0.52
    </h2>
    -0.51
     re
    -0.51
     ride
    -0.51
    </h3>
    -0.50
    POSITIVE LOGITS
     Efq
    0.88
     myſelf
    0.79
     Monfieur
    0.78
     becauſe
    0.77
     Jefus
    0.76
     chofe
    0.74
     Meksiku
    0.73
    <?
    0.73
     raiſ
    0.73
     Chriftian
    0.73
    Act Density 0.041%

    No Known Activations