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

    Neuronpedia

    INDEX
    Explanations

    specific dates or time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    time-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometers
    -0.93
    facts
    -0.92
    units
    -0.89
    zees
    -0.89
    ernels
    -0.86
    codes
    -0.85
    ittens
    -0.85
    verbs
    -0.83
    icides
    -0.83
    flows
    -0.82
    POSITIVE LOGITS
     appearance
    1.33
     outing
    1.31
     stint
    1.31
     showdown
    1.23
     foray
    1.21
     trip
    1.19
     berth
    1.17
     cameo
    1.17
     comeback
    1.08
     outburst
    1.05
    Act Density 0.256%

    No Known Activations