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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic location or region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.83
    enstein
    -0.74
    gement
    -0.71
    upiter
    -0.71
    士
    -0.68
    vation
    -0.66
    imon
    -0.65
    ptions
    -0.65
    inen
    -0.63
    lett
    -0.63
    POSITIVE LOGITS
     surrounding
    1.02
     vicinity
    1.00
     illegally
    0.99
     periphery
    0.97
     bounded
    0.96
     south
    0.84
     bordering
    0.82
     perimeter
    0.80
     evacuated
    0.80
     adjacent
    0.79
    Act Density 0.154%

    No Known Activations