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

    Neuronpedia

    INDEX
    Explanations

    mentions of global or world-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to global or world events and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -1.13
    SourceFile
    -0.81
    maid
    -0.79
    yrinth
    -0.79
    merce
    -0.78
    veland
    -0.73
     confir
    -0.72
    WARE
    -0.71
    IENT
    -0.71
    _(
    -0.71
    POSITIVE LOGITS
     treaty
    0.88
     economy
    0.81
    econom
    0.79
     treaties
    0.78
     proletariat
    0.77
     summit
    0.77
     nation
    0.76
     superpower
    0.75
     nations
    0.75
     diplomat
    0.75
    Act Density 0.066%

    No Known Activations