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

    Neuronpedia

    INDEX
    Explanations

    expressions related to trust and confidence in relationships

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

    trust and confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gory
    -0.56
     Poche
    -0.54
    oman
    -0.54
     Cama
    -0.54
    aconda
    -0.53
     հղումներ
    -0.51
    ibar
    -0.50
    bootstrapcdn
    -0.50
    ніципалі
    -0.50
     Ultima
    -0.50
    POSITIVE LOGITS
     trust
    1.62
     Trust
    1.33
    Trust
    1.30
    trust
    1.30
     TRUST
    1.27
    TRUST
    1.16
     confianza
    1.04
     trusting
    1.04
     confiança
    1.02
     trusts
    1.02
    Act Density 0.008%

    No Known Activations