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

    Neuronpedia

    INDEX
    Explanations

    expressions of trust and mistrust in relationships

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

    trusting others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WidgetItem
    -0.50
     Bolo
    -0.45
     occasion
    -0.44
    Hozzáférés
    -0.43
     Méri
    -0.42
    iello
    -0.41
     occasioned
    -0.41
    一件
    -0.40
    ias
    -0.39
    الإنجليزية
    -0.39
    POSITIVE LOGITS
     trust
    1.66
     trusting
    1.43
    trust
    1.37
     TRUST
    1.33
     trusts
    1.30
     Trust
    1.26
     trusted
    1.26
    Trust
    1.22
    trusted
    1.18
    TRUST
    1.16
    Act Density 0.007%

    No Known Activations