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

    Neuronpedia

    INDEX
    Explanations

    expressions related to political controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.84
     Cot
    -0.77
     Wol
    -0.77
     Dres
    -0.75
     KS
    -0.74
     Phelps
    -0.74
     Elves
    -0.73
     Mend
    -0.72
     Lauder
    -0.72
     Frey
    -0.70
    POSITIVE LOGITS
    tenance
    1.22
    withstanding
    1.15
    actly
    1.13
    usterity
    1.07
    actory
    1.07
    secut
    1.06
    ificantly
    1.06
    acted
    1.04
    pect
    1.02
    astic
    1.01
    Act Density 1.037%

    No Known Activations