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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms associated with various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.68
    ĸļ
    -0.66
    natureconservancy
    -0.57
     brim
    -0.51
    DragonMagazine
    -0.50
    upuncture
    -0.50
     briefs
    -0.47
     Parables
    -0.47
     diplom
    -0.47
     Boko
    -0.46
    POSITIVE LOGITS
    «
    0.62
    ½
    0.59
    é£
    0.58
    ĩ
    0.58
    ·
    0.56
    Ħ
    0.56
    ³
    0.54
    ĭ
    0.53
    intern
    0.53
    LM
    0.51
    Act Density 0.666%

    No Known Activations