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

    Neuronpedia

    INDEX
    Explanations

    capital letters followed by a number, possibly representing alphanumeric identifiers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "b"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bilt
    -0.73
    Plex
    -0.66
     Nadu
    -0.66
     Spartan
    -0.66
     XY
    -0.64
    æ©Ł
    -0.63
     Pharaoh
    -0.61
    ãĥ´ãĤ¡
    -0.61
     por
    -0.61
     Deity
    -0.60
    POSITIVE LOGITS
    ibli
    1.28
    idd
    1.24
    rows
    1.19
    abb
    1.17
    aked
    1.16
    ibliography
    1.16
    raid
    1.09
    abbling
    1.09
    urt
    1.09
    uch
    1.08
    Act Density 0.027%

    No Known Activations