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

    Neuronpedia

    INDEX
    Explanations

    locations, such as cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    significant places and events that are relevant to historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positives
    -0.49
    ãĤª
    -0.48
    osite
    -0.45
    ÃįÃį
    -0.44
    pac
    -0.43
     possibilities
    -0.42
     moderation
    -0.42
    oret
    -0.42
     necessities
    -0.41
     listener
    -0.41
    POSITIVE LOGITS
     respectively
    0.67
    .
    0.61
    .''.
    0.60
    *.
    0.57
    ãĢĤ
    0.54
    Footnote
    0.53
    .(
    0.53
    ,...
    0.52
    .).
    0.51
    .''
    0.50
    Act Density 0.928%

    No Known Activations