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

    Neuronpedia

    INDEX
    Explanations

    references to various types of jackets

    oai_token-act-pair · gpt-3.5-turbo

    references to jackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.90
    rament
    -0.82
    ruck
    -0.72
    rum
    -0.71
    inction
    -0.70
    rians
    -0.69
    lish
    -0.69
    agram
    -0.69
    rete
    -0.69
    ciplinary
    -0.69
    POSITIVE LOGITS
     jacket
    1.04
     Jacket
    1.00
     jackets
    0.99
     sleeve
    0.88
     sleeves
    0.86
     Bagg
    0.77
     Hogan
    0.76
    isted
    0.73
    velength
    0.72
     Kev
    0.72
    Act Density 0.045%

    No Known Activations