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

    Neuronpedia

    INDEX
    Explanations

    concepts and phrases related to trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.79
    ⓧ
    -0.76
    ANNES
    -0.69
    abetes
    -0.67
     CreateTagHelper
    -0.63
    醐
    -0.62
     Suppression
    -0.59
     AssemblyProduct
    -0.58
    migiano
    -0.58
     primas
    -0.57
    POSITIVE LOGITS
    Trust
    1.47
     Trust
    1.40
     trust
    1.36
     TRUST
    1.31
     trusts
    1.31
    trust
    1.31
    TRUST
    1.25
     trusting
    1.09
     Trusts
    1.08
     trusted
    1.00
    Act Density 0.093%

    No Known Activations