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

    Neuronpedia

    INDEX
    Explanations

    specific names of individuals mentioned in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     affez
    -1.12
     parati
    -0.94
     anticipo
    -0.87
     marrone
    -0.86
     palab
    -0.84
     cioc
    -0.82
     abito
    -0.82
     palio
    -0.82
     soggior
    -0.82
     tph
    -0.81
    POSITIVE LOGITS
     himself
    0.75
    '
    0.74
    ’
    0.68
     had
    0.57
    URBANA
    0.55
    himself
    0.55
     was
    0.54
     Jego
    0.51
     has
    0.51
     Himself
    0.50
    Act Density 0.157%

    No Known Activations