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

    Neuronpedia

    INDEX
    Explanations

    structured information like dates, names, and places

    oai_token-act-pair · gpt-3.5-turbo

    structured data or information headers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accordingly
    -0.82
    .</
    -0.78
    endif
    -0.78
    .).
    -0.77
    theless
    -0.75
    .''
    -0.75
    $.
    -0.74
    .}
    -0.72
    .")
    -0.72
    .]
    -0.70
    POSITIVE LOGITS
     Entered
    0.77
     Conversation
    0.66
     Located
    0.66
     Ember
    0.61
     Blaze
    0.61
     Ruins
    0.61
     Bundesliga
    0.61
     Templ
    0.60
     Seg
    0.60
     Ft
    0.60
    Act Density 0.349%

    No Known Activations