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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quat
    -0.15
    大åħ¨
    -0.15
    modal
    -0.14
    UCCEEDED
    -0.14
    rema
    -0.14
    enburg
    -0.13
    lse
    -0.13
    inium
    -0.13
    pai
    -0.13
    ytut
    -0.13
    POSITIVE LOGITS
    ardless
    0.19
    aucoup
    0.18
     sure
    0.16
    friend
    0.15
    COME
    0.15
    ethoven
    0.15
     able
    0.14
    ieve
    0.14
    473
    0.14
     Equals
    0.14
    Act Density 0.135%

    No Known Activations