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

    Neuronpedia

    INDEX
    Explanations

    numerical information (such as counts, quantities, or rankings)

    oai_token-act-pair · gpt-3.5-turbo

    quantitative references indicating frequency or quantity of events and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icz
    -0.69
    uncture
    -0.69
    ãĥ¼ãĥ
    -0.67
    lement
    -0.62
    ategory
    -0.59
    variable
    -0.58
    ocol
    -0.57
    Movie
    -0.57
    SpaceEngineers
    -0.56
    Spoiler
    -0.56
    POSITIVE LOGITS
     apiece
    1.04
     involving
    0.95
     since
    0.95
     besides
    0.94
     totaling
    0.89
     ones
    0.89
     others
    0.88
     in
    0.88
     before
    0.88
    .:
    0.83
    Act Density 0.240%

    No Known Activations