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

    Neuronpedia

    INDEX
    Explanations

    locations and names of places

    oai_token-act-pair · gpt-3.5-turbo

    elements of location and identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.82
    emort
    -0.78
     conclud
    -0.74
    eatures
    -0.74
    uggest
    -0.73
     stimulus
    -0.69
    enhagen
    -0.68
     livest
    -0.68
     memor
    -0.68
     millenn
    -0.67
    POSITIVE LOGITS
     Switzerland
    1.01
    Spain
    0.93
     Spain
    0.92
    pron
    0.91
    France
    0.90
     Italy
    0.90
     Galile
    0.89
     Morocco
    0.87
     Sicily
    0.87
     Belgium
    0.86
    Act Density 0.442%

    No Known Activations