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

    Neuronpedia

    INDEX
    Explanations

    personal names and handles from social media accounts

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and entities, particularly those involved in politics or public life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subdiv
    -0.67
    "),
    -0.66
    '),
    -0.66
    :,
    -0.65
     disadvantage
    -0.65
    rontal
    -0.63
    ',"
    -0.62
     Canaver
    -0.61
    ablished
    -0.61
     favourable
    -0.61
    POSITIVE LOGITS
     (@
    2.28
     ðŁ
    1.34
     âľ
    1.25
    ðŁ
    1.21
    âľ
    1.11
     âĿ
    1.09
     âĺ
    1.08
     ??
    1.06
    âĺ
    1.05
    âĿ
    1.01
    Act Density 0.145%

    No Known Activations