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

    Neuronpedia

    INDEX
    Explanations

    keywords related to software and technology tools

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uti
    -0.74
    acious
    -0.72
    called
    -0.68
     tiss
    -0.68
    artifacts
    -0.63
    ickle
    -0.60
    ulty
    -0.60
    ioned
    -0.60
     swayed
    -0.59
    of
    -0.59
    POSITIVE LOGITS
    pload
    0.71
     its
    0.70
    Ħ¢
    0.69
    Ń·
    0.69
     itself
    0.67
    phia
    0.67
    activation
    0.65
     Lifetime
    0.65
     lieu
    0.63
    livion
    0.62
    Act Density 0.429%

    No Known Activations