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

    Neuronpedia

    INDEX
    Explanations

    locations or regions within countries

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the letter "U" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.66
    )=(
    -0.63
    assetsadobe
    -0.60
     [...]
    -0.59
     pus
    -0.59
     underpin
    -0.58
    orative
    -0.57
     Blanc
    -0.55
     mars
    -0.54
     paralysis
    -0.54
    POSITIVE LOGITS
    uthor
    0.92
    ´
    0.82
    ¦
    0.81
    ¶æ
    0.77
    URI
    0.77
    »
    0.74
    £
    0.73
    Ĵ
    0.73
    Ĺ
    0.72
    §
    0.71
    Act Density 0.084%

    No Known Activations