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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "Geo" regardless of context

    oai_token-act-pair · gpt-4-turbo

    terms related to geographical locations, specifically related to the term "Geo" and "Surrey"

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.95
    ato
    -0.92
    amental
    -0.85
    lain
    -0.82
    stall
    -0.81
    uum
    -0.78
    ament
    -0.77
    manship
    -0.77
    uous
    -0.76
    icles
    -0.75
    POSITIVE LOGITS
     geo
    0.92
    engineering
    0.83
     Geo
    0.78
     lobe
    0.68
    DX
    0.66
    ignty
    0.65
     ther
    0.65
    engine
    0.64
     mind
    0.63
    Beh
    0.63
    Act Density 0.021%

    No Known Activations