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

    Neuronpedia

    INDEX
    Explanations

    locations or places, particularly ones ending with "heim"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.83
    ciating
    -0.78
    Downloadha
    -0.72
     undermin
    -0.65
    abase
    -0.65
     athlet
    -0.64
    clusively
    -0.62
    positive
    -0.61
    ched
    -0.60
    oute
    -0.60
    POSITIVE LOGITS
    stein
    1.16
    shire
    1.13
    ers
    0.97
    sburg
    0.97
    heim
    0.96
    sson
    0.90
    stadt
    0.87
    roth
    0.82
    gren
    0.82
    lich
    0.78
    Act Density 0.015%

    No Known Activations