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

    Neuronpedia

    INDEX
    Explanations

    terms related to governance and societal structures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant differences or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shots
    -0.58
     Happy
    -0.56
     Tours
    -0.56
     Tonight
    -0.54
     Hungry
    -0.53
    anwhile
    -0.53
    hung
    -0.52
     Saturdays
    -0.52
    Buzz
    -0.52
    Happy
    -0.51
    POSITIVE LOGITS
     methodological
    1.02
     fallacy
    0.93
     presupp
    0.90
     heterogeneity
    0.89
     inconsistency
    0.88
     empirical
    0.87
     obfusc
    0.86
     overest
    0.86
     limitation
    0.84
     bias
    0.83
    Act Density 0.812%

    No Known Activations