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

    Neuronpedia

    INDEX
    Explanations

    names of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly places named "land."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.75
    chel
    -0.73
    hift
    -0.66
    ongyang
    -0.65
    soDeliveryDate
    -0.65
     inaction
    -0.64
    SOURCE
    -0.64
    isine
    -0.64
    externalActionCode
    -0.63
     periodic
    -0.61
    POSITIVE LOGITS
    scape
    1.00
    marks
    0.92
    ishly
    0.90
    estine
    0.89
     Islands
    0.83
     Park
    0.82
    ward
    0.81
     Heights
    0.81
    ells
    0.78
     Hills
    0.76
    Act Density 0.068%

    No Known Activations