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

    Neuronpedia

    INDEX
    Explanations

    multiple expressions of trust and distrust in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scenes
    -0.81
     Anaconda
    -0.80
    Рабо
    -0.79
     EDS
    -0.72
     Taub
    -0.72
     Representatives
    -0.71
    PhysRevD
    -0.71
     Capo
    -0.71
     ALC
    -0.71
    ecera
    -0.71
    POSITIVE LOGITS
     trust
    2.52
     Trust
    2.41
    Trust
    2.40
    trust
    2.31
     TRUST
    2.24
    TRUST
    2.18
     trusts
    2.15
     trusted
    1.96
     trusting
    1.95
     Trusts
    1.77
    Act Density 0.090%

    No Known Activations