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

    Neuronpedia

    INDEX
    Explanations

    sections that contain interviews or dialogues

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

    interviews

    np_acts-logits-general · gemini-2.0-flash

    interview content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.56
    InputTagHelper
    -0.56
    GEBURTSDATUM
    -0.55
    verwijspagina
    -0.51
    MessageTagHelper
    -0.49
     tiguan
    -0.49
    ]=>
    -0.49
     disambiguazione
    -0.49
     ModelRenderer
    -0.47
    @[+][
    -0.47
    POSITIVE LOGITS
     interview
    1.06
     interviews
    0.96
    Interview
    0.95
     interviewed
    0.93
     Interview
    0.91
     entrevistas
    0.83
    interview
    0.82
    Interviews
    0.82
     Interviews
    0.81
     entrevista
    0.79
    Act Density 0.129%

    No Known Activations