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

    Neuronpedia

    INDEX
    Explanations

    discrete words or phrases containing the substring "Moh"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Moh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯
    -0.94
    istics
    -0.87
     balloons
    -0.77
    istically
    -0.74
    chnology
    -0.70
    =-=-=-=-=-=-=-=-
    -0.70
    xxxxxxxx
    -0.70
    ãĤ¦
    -0.68
     Tycoon
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    POSITIVE LOGITS
    awk
    1.40
    awks
    1.27
    undai
    1.04
    renheit
    0.94
    abit
    0.93
    sin
    0.93
    doms
    0.92
    azard
    0.89
    atche
    0.87
    adish
    0.86
    Act Density 0.012%

    No Known Activations