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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mue
    -0.16
    an
    -0.15
    uai
    -0.15
    rema
    -0.15
     cuff
    -0.15
     hereby
    -0.14
    most
    -0.14
    many
    -0.14
    lat
    -0.14
    Ñİн
    -0.14
    POSITIVE LOGITS
    friend
    0.18
    aucoup
    0.17
    ckett
    0.17
    COME
    0.15
    fits
    0.15
    ardless
    0.15
    arded
    0.15
    cloud
    0.14
    emoth
    0.14
    /sources
    0.14
    Act Density 0.346%

    No Known Activations