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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, particularly focusing on regions such as Oceania and certain countries in Asia

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific letters or letter combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.78
    enegger
    -0.70
     virginity
    -0.64
     ris
    -0.64
    INESS
    -0.63
     caution
    -0.61
    rooms
    -0.61
     futures
    -0.59
     narrator
    -0.57
     invari
    -0.57
    POSITIVE LOGITS
    ana
    0.97
    ka
    0.92
    ko
    0.89
    aga
    0.89
    fa
    0.83
    anas
    0.83
    leck
    0.83
    ola
    0.83
    aqu
    0.82
    ga
    0.82
    Act Density 0.134%

    No Known Activations