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

    Neuronpedia

    INDEX
    Explanations

    words related to statements and quotations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hels
    -0.64
     Consortium
    -0.63
     Gutenberg
    -0.60
     Alternative
    -0.59
     PTS
    -0.58
     Redmond
    -0.57
     Violet
    -0.57
     Annotations
    -0.57
     Mobile
    -0.56
     extant
    -0.55
    POSITIVE LOGITS
    'm
    1.51
    've
    1.31
     guess
    1.26
     think
    1.17
    'll
    1.12
    ggy
    1.07
    'd
    1.06
    zzo
    1.03
     believe
    1.01
     suppose
    1.00
    Act Density 0.191%

    No Known Activations