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

    Neuronpedia

    INDEX
    Explanations

    references to newspapers and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to newspapers and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.74
    neau
    -0.72
    romy
    -0.72
    artney
    -0.72
    enko
    -0.70
    agne
    -0.70
    illance
    -0.68
    onda
    -0.66
    igree
    -0.66
    artifacts
    -0.65
    POSITIVE LOGITS
     newspaper
    0.80
    lisher
    0.78
    Journal
    0.77
     publisher
    0.77
     columnist
    0.75
     Inqu
    0.75
     editor
    0.69
     newspapers
    0.69
     Tribune
    0.69
     ob
    0.68
    Act Density 0.045%

    No Known Activations