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

    Neuronpedia

    INDEX
    Explanations

    words related to different aspects of a subject or topic

    oai_token-act-pair · gpt-3.5-turbo

    references to various elements or components of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wait
    -0.67
    alty
    -0.57
    live
    -0.57
    chance
    -0.57
    ople
    -0.56
    ça
    -0.56
    hold
    -0.56
    rie
    -0.56
    elle
    -0.56
     PET
    -0.55
    POSITIVE LOGITS
     aspects
    3.41
     facets
    2.50
     aspect
    2.19
     elements
    1.85
     qualities
    1.65
     portions
    1.61
     parts
    1.57
     characteristics
    1.52
     manifestations
    1.47
     components
    1.46
    Act Density 0.010%

    No Known Activations