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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political resistance and activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     !...
    -1.42
     fta
    -1.35
     desir
    -1.31
     ?...
    -1.29
     effe
    -1.29
     impractica
    -1.27
     purcha
    -1.27
     guarante
    -1.27
     fto
    -1.26
     leaft
    -1.26
    POSITIVE LOGITS
     whatever
    0.87
     wherever
    0.81
    whatever
    0.68
     whichever
    0.65
    hichever
    0.65
    writeFieldEnd
    0.64
     BoxFit
    0.63
     whenever
    0.62
     whoever
    0.61
     Whatever
    0.60
    Act Density 0.448%

    No Known Activations