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

    Neuronpedia

    INDEX
    Explanations

    proper nouns relating to people

    oai_token-act-pair · gpt-3.5-turbo

    geographical and locational references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.81
    behind
    -0.76
    isSpecialOrderable
    -0.74
    vana
    -0.70
    soType
    -0.68
    SpaceEngineers
    -0.67
     ancest
    -0.66
     subp
    -0.65
     lapse
    -0.65
    partisan
    -0.63
    POSITIVE LOGITS
     Wagner
    0.84
    helm
    0.76
    arde
    0.76
    eston
    0.74
     Abbey
    0.74
    stad
    0.71
     Fried
    0.68
     Hardy
    0.67
    Mania
    0.67
     Frey
    0.67
    Act Density 0.191%

    No Known Activations