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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer hardware and technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of DRAM and related abbreviations

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Negative Logits
     Pose
    -1.07
     Corpus
    -1.06
    hiro
    -0.99
    ropolitan
    -0.97
     ç¥ŀ
    -0.92
    geist
    -0.91
    than
    -0.87
     Wildcats
    -0.86
    terson
    -0.85
     quo
    -0.84
    POSITIVE LOGITS
    ESS
    1.38
    adeon
    1.26
    inks
    1.21
    IVE
    1.20
    IVER
    1.14
    INK
    1.13
    IVERS
    1.12
    ESH
    1.10
    inking
    1.09
    UCT
    1.05
    Act Density 0.276%

    No Known Activations