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

    Neuronpedia

    INDEX
    Explanations

    particular characters that seem to be separators or special markers in the document

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing significant events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inactive
    -0.77
     engagement
    -0.76
     proport
    -0.75
     engagements
    -0.75
     citiz
    -0.73
     instit
    -0.72
     pan
    -0.72
     imperson
    -0.71
     diving
    -0.69
     duty
    -0.69
    POSITIVE LOGITS
    ³³³³³³³³
    1.14
    Article
    1.08
    Photo
    1.02
    ³³³
    1.02
    Consider
    1.01
    SHARE
    1.01
    ³³³³
    1.00
    Enlarge
    0.98
    ³³³³³³³³³³³³³³³³
    0.98
    Fans
    0.97
    Act Density 0.437%

    No Known Activations