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

    Neuronpedia

    INDEX
    Explanations

    mentions of various quantities of money

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" or "an" followed by nouns, indicating the introduction of new concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    words
    -0.74
    Finish
    -0.72
     engagements
    -0.71
    bars
    -0.71
    marks
    -0.71
     aliases
    -0.71
    agents
    -0.70
     interactions
    -0.70
    events
    -0.69
     gestures
    -0.68
    POSITIVE LOGITS
     dozen
    1.48
     plethora
    1.46
     handful
    1.43
     lot
    1.38
     whopping
    1.35
     slew
    1.32
     multitude
    1.32
     bunch
    1.28
     hundred
    1.19
     variety
    1.18
    Act Density 0.508%

    No Known Activations