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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streets
    -1.89
     roads
    -1.84
     outskirts
    -1.78
     inland
    -1.73
     trucks
    -1.68
     east
    -1.67
     beaches
    -1.66
     establishments
    -1.65
     northwest
    -1.64
     bikes
    -1.64
    POSITIVE LOGITS
    ĭ
    1.95
    oses
    1.71
     clinician
    1.53
    º
    1.48
    finger
    1.44
     patient
    1.42
    nut
    1.39
    į
    1.39
     touch
    1.38
     promise
    1.38
    Act Density 1.101%

    No Known Activations