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

    Neuronpedia

    INDEX
    Explanations

    terms related to trends and increases

    oai_token-act-pair · gpt-3.5-turbo

    topics related to economic trends and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oath
    -0.82
     purity
    -0.76
     Duchess
    -0.74
     kits
    -0.68
     confessions
    -0.68
     Oath
    -0.67
     voic
    -0.66
     Pack
    -0.65
     commandments
    -0.63
     Kits
    -0.63
    POSITIVE LOGITS
     coincided
    1.21
     accelerating
    1.12
     coincides
    1.05
     paralle
    1.04
    acerb
    1.02
     accelerated
    1.01
     accelerate
    1.01
     attributable
    1.00
     exacerbated
    1.00
    celer
    0.97
    Act Density 0.543%

    No Known Activations