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

    Neuronpedia

    INDEX
    Explanations

    references to software modules and technical documentation

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with coding and programming concepts, particularly those linked to modules and scripts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Negative Logits
    ews
    -0.33
    opia
    -0.33
    merga
    -0.32
    vo
    -0.32
    ãĤ¦ãĤ¹
    -0.32
    iem
    -0.31
    bos
    -0.31
    nee
    -0.31
    lace
    -0.30
    hered
    -0.30
    POSITIVE LOGITS
     bund
    0.38
     servicing
    0.32
     assembled
    0.32
     loader
    0.30
     lodged
    0.28
    ĸļ
    0.28
    irez
    0.28
     Typh
    0.28
     unloaded
    0.28
     shipments
    0.27
    Act Density 0.305%

    No Known Activations