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

    Neuronpedia

    INDEX
    Explanations

    links and identifiers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     passionate
    -0.74
    lings
    -0.70
     rall
    -0.70
     mutual
    -0.68
     simplicity
    -0.68
     masc
    -0.67
     tourism
    -0.66
     sponsors
    -0.66
     hearty
    -0.66
     beginners
    -0.66
    POSITIVE LOGITS
     partName
    1.20
     CrossRef
    1.05
    806
    1.00
    336
    1.00
    015
    0.98
    01
    0.97
    201
    0.97
    708
    0.95
    641
    0.95
    285
    0.95
    Act Density 1.154%

    No Known Activations