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

    Neuronpedia

    INDEX
    Explanations

    places or locations within a story

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     michelin
    -0.84
     scrat
    -0.83
     plenti
    -0.82
     swee
    -0.82
     disreg
    -0.78
     panama
    -0.78
     gild
    -0.77
     inext
    -0.77
     frankfurt
    -0.77
     impra
    -0.75
    POSITIVE LOGITS
     headquarters
    0.81
     premises
    0.73
     offices
    0.73
    dataclass
    0.61
     office
    0.61
    principalColumn
    0.59
     home
    0.59
     residence
    0.58
    Headquarters
    0.58
     peniten
    0.55
    Act Density 0.396%

    No Known Activations