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

    Neuronpedia

    INDEX
    Explanations

    code snippets in a programming language

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.70
    .
    -0.69
     West
    -0.66
     Saint
    -0.65
     So
    -0.64
     J
    -0.63
    QMetaType
    -0.63
     St
    -0.63
     so
    -0.62
     Jets
    -0.61
    POSITIVE LOGITS
     !...
    1.59
    fordable
    1.47
     chande
    1.42
     michelin
    1.41
     dises
    1.40
     vogli
    1.39
     parma
    1.39
     ?...
    1.38
    !!</
    1.35
     seiz
    1.34
    Act Density 0.069%

    No Known Activations