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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "confidence" in various contexts

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

    confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.51
     Escolar
    -0.49
     houſe
    -0.47
    ing
    -0.46
     Nacionales
    -0.44
    er
    -0.44
     Ráp
    -0.44
     Orm
    -0.44
    sqcup
    -0.42
    Pemer
    -0.42
    POSITIVE LOGITS
     confidence
    2.05
     Confidence
    1.96
    confidence
    1.84
    Confidence
    1.80
     confianza
    1.29
     confiança
    1.19
    信心
    1.13
     confiance
    1.05
     vertrouwen
    0.97
     Vertrauen
    0.93
    Act Density 0.006%

    No Known Activations