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

    Neuronpedia

    INDEX
    Explanations

    phrases related to revolutionaries and social change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     secon
    -1.05
     Intere
    -1.04
     intere
    -1.04
     doman
    -1.02
     dispen
    -1.01
     oner
    -1.00
     contex
    -1.00
     maroc
    -1.00
     squa
    -0.98
     effe
    -0.97
    POSITIVE LOGITS
     those
    0.79
    those
    0.79
     Those
    0.77
    Those
    0.72
     whom
    0.72
     who
    0.68
     whose
    0.68
     ones
    0.65
     الذين
    0.64
     These
    0.63
    Act Density 0.658%

    No Known Activations