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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legitimacy and legal implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    енча
    -0.71
    duled
    -0.64
    ciless
    -0.64
    zegor
    -0.63
     BoxFit
    -0.63
    bourhood
    -0.61
    spaceBetween
    -0.61
    IZABETH
    -0.60
    ochlor
    -0.60
    mallow
    -0.60
    POSITIVE LOGITS
    Skocz
    0.66
    </em>
    0.63
     StatefulWidget
    0.58
    #![
    0.57
    fhir
    0.55
     Storms
    0.54
    杵
    0.54
    MathML
    0.53
    ko
    0.52
    chdir
    0.52
    Act Density 0.010%

    No Known Activations