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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unction
    -0.17
    rema
    -0.16
    oplevel
    -0.15
    irie
    -0.15
    =value
    -0.15
    ilogy
    -0.15
    uguay
    -0.15
    lom
    -0.14
    ération
    -0.14
    veau
    -0.14
    POSITIVE LOGITS
     easily
    0.18
    ’t
    0.17
    't
    0.15
    ola
    0.15
    862
    0.15
    Įĵ
    0.15
    OLA
    0.15
     eas
    0.14
    anything
    0.14
     Schul
    0.14
    Act Density 0.068%

    No Known Activations