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

    Neuronpedia

    INDEX
    Explanations

    instances where a person's name is mentioned in a text passage

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibel
    -1.03
    edly
    -0.99
    ly
    -0.90
    liness
    -0.90
    ership
    -0.90
    cies
    -0.90
    lement
    -0.88
    ation
    -0.88
    hip
    -0.88
    wikipedia
    -0.88
    POSITIVE LOGITS
     queens
    0.69
     Bride
    0.63
     nanop
    0.63
     [&
    0.60
     Scotia
    0.60
     Barg
    0.59
     fracture
    0.59
     Âł Âł Âł Âł
    0.59
    anches
    0.57
     Cla
    0.57
    Act Density 0.320%

    No Known Activations