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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.75
    ⓧ
    -0.74
    -------------</
    -0.73
    amaño
    -0.73
    struzioni
    -0.69
     AssemblyProduct
    -0.69
    Pautan
    -0.67
     Limoges
    -0.66
     Riproduzione
    -0.66
     Pergamon
    -0.65
    POSITIVE LOGITS
     making
    0.62
    er
    0.59
     */}
    0.55
    to
    0.53
    \
    0.52
    ron
    0.51
    making
    0.50
     providing
    0.49
    To
    0.49
    ра
    0.49
    Act Density 0.696%

    No Known Activations