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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations, particularly city names

    oai_token-act-pair · gpt-3.5-turbo

    certain geographical or cultural names, particularly focusing on the prefix "Gw" and "Dj"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.94
    姫
    -0.76
     Candy
    -0.71
     contraceptives
    -0.66
     contraception
    -0.65
     Bunny
    -0.65
    ãĥ¼ãĥĨ
    -0.65
    tenance
    -0.65
    ++++++++++++++++
    -0.65
    sight
    -0.63
    POSITIVE LOGITS
    argo
    1.00
    uran
    0.95
    athed
    0.94
    izoph
    0.94
    ork
    0.92
    adr
    0.90
    ör
    0.88
    arm
    0.87
    orn
    0.87
    ouls
    0.87
    Act Density 0.021%

    No Known Activations