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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "com" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лива
    -0.16
    WithContext
    -0.14
    icut
    -0.14
     Passport
    -0.14
     squared
    -0.14
    intl
    -0.13
    oller
    -0.13
    .debian
    -0.13
    è¯Ŀ
    -0.13
    anger
    -0.13
    POSITIVE LOGITS
    unit
    0.32
    una
    0.29
    unic
    0.28
    uni
    0.27
    and
    0.27
    plet
    0.27
    une
    0.27
    unes
    0.27
    ision
    0.26
    ún
    0.26
    Act Density 0.010%

    No Known Activations