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

    Neuronpedia

    INDEX
    Explanations

    names with the string "m" followed by a digit from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
     pitch
    -0.66
     begg
    -0.62
     tipped
    -0.62
     foul
    -0.60
     ramps
    -0.60
     Pengu
    -0.59
    */(
    -0.59
    irtual
    -0.58
    POSITIVE LOGITS
    otor
    1.23
    ichael
    1.21
    asonic
    1.20
    ormon
    1.19
    asonry
    1.17
    obil
    1.16
    obiles
    1.15
    useum
    1.14
    ortal
    1.11
    uppet
    1.08
    Act Density 0.055%

    No Known Activations