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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or concepts throughout text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Provided
    -0.73
    *=-
    -0.72
    bane
    -0.63
     Bei
    -0.63
    alf
    -0.63
    arest
    -0.63
    meet
    -0.62
    acus
    -0.62
    ases
    -0.62
     Recomm
    -0.62
    POSITIVE LOGITS
     thing
    1.09
     exact
    1.02
     vein
    1.00
     amount
    0.98
     kind
    0.90
     sort
    0.83
     sized
    0.82
     kinds
    0.82
     fate
    0.79
     principle
    0.79
    Act Density 0.321%

    No Known Activations