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

    Neuronpedia

    INDEX
    Explanations

    questions that start with "Who" and include someone's name, with a focus on identifying people or characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    karet
    -0.53
     NUKAT
    -0.51
    patu
    -0.47
    FetchType
    -0.45
    beni
    -0.44
     Banten
    -0.42
     afectados
    -0.41
     benzina
    -0.41
    ServletException
    -0.40
     particolar
    -0.39
    POSITIVE LOGITS
    Who
    0.82
     Who
    0.79
     who
    0.75
    who
    0.74
    WHO
    0.69
     Quem
    0.68
     WHO
    0.67
     whom
    0.66
     Quien
    0.66
    Quem
    0.63
    Act Density 0.125%

    No Known Activations