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

    Neuronpedia

    INDEX
    Explanations

    the name "Claire" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Claire Sinclair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Niko
    -0.43
     Niko
    -0.42
    écution
    -0.40
     RPS
    -0.40
    HttpMethod
    -0.40
    cessite
    -0.39
    ுக
    -0.38
    MatButtonModule
    -0.38
     GN
    -0.38
    -(
    -0.38
    POSITIVE LOGITS
     Claire
    2.13
    Claire
    1.98
     claire
    1.51
    claire
    1.43
     Clair
    1.41
    Clair
    1.26
     Clare
    1.17
    Clare
    1.03
    clare
    0.96
     clair
    0.94
    Act Density 0.004%

    No Known Activations