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

    Neuronpedia

    INDEX
    Explanations

    variation in the use of personal pronouns and common verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.15
    raya
    -0.14
    à¸ŀระราà¸Ĭ
    -0.13
     Χα
    -0.13
    imet
    -0.13
    bane
    -0.13
    667
    -0.13
    rome
    -0.13
    ube
    -0.13
    @qq
    -0.13
    POSITIVE LOGITS
     experience
    0.15
    kea
    0.14
     affected
    0.14
    esel
    0.14
    801
    0.14
    Lang
    0.14
    uppy
    0.14
    μο
    0.14
     Lang
    0.14
    claim
    0.14
    Act Density 0.006%

    No Known Activations