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

    Neuronpedia

    INDEX
    Explanations

    expressions of faith and confidence

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

    faith in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBOutlet
    -0.51
     يتيمه
    -0.49
    ſelf
    -0.49
    ſelves
    -0.48
    IUrlHelper
    -0.44
     disambiguazione
    -0.43
     Majefty
    -0.43
    HtmlAttribute
    -0.43
     houſe
    -0.42
    Head
    -0.42
    POSITIVE LOGITS
     trust
    1.06
     confidence
    1.05
     confiance
    0.97
    confidence
    0.95
     confianza
    0.91
     Vertrauen
    0.90
     Confidence
    0.89
     Trust
    0.89
     fiducia
    0.87
     vertrouwen
    0.86
    Act Density 0.072%

    No Known Activations