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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Mo" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ka
    -0.20
    mente
    -0.20
    nya
    -0.19
    pu
    -0.19
    ru
    -0.18
    no
    -0.18
    ners
    -0.18
    pro
    -0.17
    ma
    -0.17
    li
    -0.17
    POSITIVE LOGITS
    ehler
    0.26
    'nun
    0.18
    key
    0.16
    ìį¨
    0.15
    resh
    0.15
     far
    0.15
    ress
    0.15
    ctype
    0.15
    elman
    0.15
    Ø¡
    0.15
    Act Density 0.112%

    No Known Activations