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

    Neuronpedia

    INDEX
    Explanations

    comparisons between quantities or states

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparison between different groups or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adia
    -0.65
    authorized
    -0.63
    allo
    -0.62
     recess
    -0.60
    stall
    -0.60
     oats
    -0.59
    acco
    -0.58
    eland
    -0.58
    wered
    -0.58
     Nebula
    -0.58
    POSITIVE LOGITS
     favorably
    0.89
    lihood
    0.87
     Compare
    0.74
    Compare
    0.73
     Chart
    0.70
    bryce
    0.69
    onyms
    0.67
     thereto
    0.67
     sexes
    0.66
     compare
    0.66
    Act Density 0.021%

    No Known Activations