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

    Neuronpedia

    INDEX
    Explanations

    year references

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and references to specific years or notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enture
    -0.73
     incent
    -0.65
    scan
    -0.61
    redients
    -0.61
    wcs
    -0.61
     females
    -0.60
     purse
    -0.58
     women
    -0.58
     parity
    -0.58
     equivalents
    -0.57
    POSITIVE LOGITS
    Mr
    1.26
    His
    1.22
     Mr
    1.18
    He
    1.15
     Manziel
    1.14
     Jaune
    1.10
     he
    1.08
     He
    1.07
     Duterte
    1.05
     Rahul
    1.05
    Act Density 1.074%

    No Known Activations