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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fundamental elements or principles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to foundational concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.87
    govtrack
    -0.66
    wb
    -0.64
    crow
    -0.64
    STON
    -0.64
    ²¾
    -0.63
     awa
    -0.63
    hao
    -0.63
    hiba
    -0.63
    erva
    -0.62
    POSITIVE LOGITS
    arium
    1.17
    ament
    1.08
    ally
    0.93
    als
    0.91
    aments
    0.85
    edly
    0.84
    ations
    0.83
    ados
    0.79
    ation
    0.79
    arie
    0.79
    Act Density 0.013%

    No Known Activations