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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations or territories

    oai_token-act-pair · gpt-3.5-turbo

    references to specific areas or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -1.06
    lio
    -0.83
    inn
    -0.81
    icial
    -0.78
    aldi
    -0.75
    enstein
    -0.74
    artz
    -0.72
    estamp
    -0.71
    ging
    -0.68
    inen
    -0.67
    POSITIVE LOGITS
     area
    0.89
     areas
    0.82
    area
    0.80
     bounded
    0.79
     adjacent
    0.79
     adjoining
    0.77
     surrounding
    0.76
     rug
    0.74
     Areas
    0.74
     malls
    0.74
    Act Density 0.046%

    No Known Activations