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

    Neuronpedia

    INDEX
    Explanations

    references to trust and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anaconda
    -0.86
     Benito
    -0.81
    Appender
    -0.78
    Рабо
    -0.78
     barbarous
    -0.78
     Representatives
    -0.77
     Gillespie
    -0.76
    vento
    -0.76
     Proclamation
    -0.76
    onedDateTime
    -0.76
    POSITIVE LOGITS
     trust
    2.11
     Trust
    2.05
    Trust
    2.05
    TRUST
    1.96
    trust
    1.96
     TRUST
    1.94
     trusts
    1.88
     trusting
    1.64
     Trusts
    1.59
     trusted
    1.58
    Act Density 0.038%

    No Known Activations