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

    Neuronpedia

    INDEX
    Explanations

    website and email domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scheme
    -0.83
     Genie
    -0.77
     Hai
    -0.74
     Philippe
    -0.74
     Flav
    -0.74
     Majesty
    -0.73
     Bout
    -0.72
     Stall
    -0.72
     Kut
    -0.72
     Lung
    -0.71
    POSITIVE LOGITS
    news
    1.08
    politics
    1.03
    ribune
    0.90
    podcast
    0.86
    reports
    0.85
    abc
    0.85
    legraph
    0.83
    photos
    0.82
    blogs
    0.82
    journal
    0.82
    Act Density 0.063%

    No Known Activations