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

    Neuronpedia

    INDEX
    Explanations

    technical terms and scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or formal documentation and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    needed
    -0.78
     awa
    -0.71
     TAMADRA
    -0.69
     accordingly
    -0.61
     furthermore
    -0.59
    OVA
    -0.59
     challeng
    -0.59
     needed
    -0.57
     therefore
    -0.57
    ignty
    -0.56
    POSITIVE LOGITS
     standpoint
    1.41
     onwards
    1.08
     vantage
    1.06
     perspective
    0.95
     onward
    0.83
     Shutterstock
    0.81
    ratch
    0.79
     sources
    0.78
     outset
    0.76
     infancy
    0.72
    Act Density 0.760%

    No Known Activations