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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gement
    -0.78
    struction
    -0.77
    thood
    -0.74
    imon
    -0.70
    ICE
    -0.69
    henko
    -0.68
    ãĥīãĥ©
    -0.67
    lett
    -0.66
    umbledore
    -0.66
    Panel
    -0.66
    POSITIVE LOGITS
     vicinity
    1.11
     surrounding
    0.97
     periphery
    0.93
     illegally
    0.89
     bounded
    0.85
     area
    0.83
     outskirts
    0.81
     perimeter
    0.80
     suburbs
    0.80
     countryside
    0.79
    Act Density 0.153%

    No Known Activations